Mohamed Asif Abdul Hameed

Workload balancing is a crucial component of lean manufacturing as it helps to bring down the lead time, increase the productivity, and enhance the overall quality.
 
It refers to the process of allocating work among the team members to ensure each one is being utilized efficiently and effectively. This is done to eliminate any bottlenecks or waste in the production process.
 
There are three things that have an obvious impact on balancing the production workload:
Amount of work content at each operation involved in the overall process. Variations in customer demand, which deplete or overload the production process. Ability to implement “Heijunka” or “production smoothing” to overcome these problems.  

 
To simplify, by referring to the above diagram, we can see that operator A’s tasks add to 55 minutes, operator B’s 45 minutes, operator C’s 30 minutes, operator D’s 15 minutes. 
We can simply give operator D’s tasks to operator C and redeploy operator D to where they are needed more. In this case we have a 25% direct reduction.
 
Below are some of the top considerations for workload balancing in manufacturing setup:
Capacity of Workstations Type of Product Skillset of Workers Production Schedule Below are some of the considerations for workload balancing in service industry:
Service Capacity Type of Service Customer Needs Service Schedule AI can play a vital role in workload balancing by automating tasks that can be optimized and to analyze data to make better decisions.
 
Listed few examples of leveraging AI and ML for workload balancing:  
Predictive Analytics Forecasting Task Automation Resource Optimization Real-Time Monitoring Decision Support Personalization Examples of workload balancing in Service industry:
Restaurant Staffing Call Centre Management Healthcare Staffing Retail Staffing Hotel Staffing In all these examples, workload balancing is used to optimize the allocation of resources and staff, ensuring that customer needs are met while minimizing employee stress and improving overall efficiency.
 
Similarly, in a manufacturing setup, workload balancing can be applied in following areas, ensuring that production demand is met while minimizing machine downtime and improving overall efficiency.
Assembly Line Staffing QC Inventory Management Maintenance Scheduling Production Planning We can use any of the below formulas to calculate and manage the work load better:
 
Capacity Utilization: Capacity Utilization = Actual Output / Potential Output.
Workload Index: Workload Index = Workload / Staffing Levels.
Efficiency Rate: Efficiency Rate = Actual Output / Standard Output.
Staffing Ratio: Staffing Ratio = Staffing Levels / Production Demand.
Lead Time: Lead Time = Total Processing Time + Wait Time.
 
These formulas can be adapted and customized to fit the specific needs of an organization or industry. The goal of workload balancing is to optimize resource allocation, reduce workload imbalances, and improve overall efficiency and productivity.
 
In general, by leveraging artificial intelligence and machine learning, we can improve efficiency, reduce errors, and improve employee satisfaction and organizations can improve their competitiveness and better meet customer needs.
 

The decision to choose between batch processing and one-piece flow depends on several factors, including that of:

1. Product Characteristics: The nature of the product that is being manufactured can greatly influence the choice between batch processing and one-piece flow. If the product has a high volume and is repetitive in nature, batch processing may be more efficient. On the contrary, if the product has a low volume and requires customization, one-piece flow may be more effective.
2. Demand: The level of demand for the product is also an vital factor. If the demand is high, batch processing may be more efficient as it can produce a large volume of the product rapidly. However, if the demand is low, one-piece flow may be more effective as it can produce the required quantity without creating excess inventory and avoids waste - Pull rather than Push.
3. Equipment: The type and capacity of the equipment used in the production process can sometime influence the choice between the two. If the equipment is designed for batch processing, it may be more efficient to use this method. However, if the equipment is flexible, meant for customization and can handle small batches, one-piece flow may be more effective.
4. Labour: The availability and skill level of the workforce can also influence the choice between batch processing and one-piece flow. If the workforce is highly skilled and can work efficiently in a one-piece flow environment, this method may be more effective. However, if the workforce is less skilled, batch processing may be a better option as it requires minimal skill and training.
5. Cost: The cost of production is one of the most important factor to consider. Batch processing may be more cost-effective as it can produce a large volume of the product quickly. However, one-piece flow may be more cost-effective in terms of reducing inventory, reducing lead times, and improving quality.

Overall, the decision to choose between batch processing and one-piece flow should be based on a careful analysis of the above factors and should be aligned with the organization's goals and objectives.

The selection between batch processing and one-piece flow can have significant impacts on quality, productivity, and lead time in a manufacturing process.

Quality: Batch processing can result in higher defect rates as it can produce a large volume of defective products before the defect is identified and corrected. One-piece flow, on the other hand, allows for immediate detection and correction of defects, resulting in higher quality products.

Productivity: Batch processing can result in longer setup times and longer processing times, which can reduce productivity. One-piece flow, on the other hand, can reduce setup times and processing times, resulting in higher productivity.

Lead Time: Batch processing can result in longer lead times due to the time required to produce a large volume of products before they can be shipped. One-piece flow, on the other hand, can reduce lead times as products can be produced and shipped in smaller quantities and with shorter processing times.

All in all, one-piece flow can result in higher quality, higher productivity, and shorter lead times due to its ability to reduce defects, setup times, and processing times. However, batch processing may still be a viable option for high-volume, repetitive products, or when equipment is not flexible enough to handle small batches.
 
Eventually, the selection between batch processing and one-piece flow should be based on a careful analysis of the product characteristics, demand, equipment, labour, and cost, and should align with the organization's goals and objectives.

Batch processing examples:
 

 
Food and beverage industry - producing large batches of canned or bottled products, such as soft drinks or canned vegetables. Bakery: Most bakery uses batch processing to produce large volumes of bread. The dough is mixed in large batches, which are then divided into smaller batches for shaping, proofing, and baking.
Pharmaceutical industry - producing large batches of medications or supplements, such as tablets or capsules. Textile industry - producing large batches of fabrics or garments, such as a batch of 5000 t-shirts. One-piece flow examples:
 

Automotive industry - producing individual car parts or subassemblies, such as engines or transmissions. Aerospace industry - producing individual airplane parts or subassemblies, such as wings or landing gears. Electronics industry - producing individual circuit boards or electronic components, such as microchips or resistors.

Starting with the basics,
Control limits are the process's voice (what the process does) and
Specification limits represent the customer's voice (what we want the process to do).
 
Lower and upper control limits are LCL and UCL, respectively.
Lower and upper specification limits are LSL and USL.
 
In general, these limits represent our process variation and help highlight when our process is out of control.

x̄ - center line for the data is the sum of all the input data divided by the total number of data points
LCL – is 3 process standard deviation below the average and
UCL – is typically 3 process standard deviation above the average
 
If the data point falls within ±3SD of its average, it is considered as “EXPECTED” behavior for the process and thus is a common cause variation. Something special happened to those data pointers outside these control limits and can be special cause variation.
 
Let’s consider real-time data from the 2022 Japanese Grand Prix. The qualification session usually determines the starting order and the pole position of the race. To occupy pole position, the fastest driver must ensure that their performance is the quickest, that is, with the lowest lap timing.
Below are the lap time/s (actual performance) for the qualifying session.
LCL 01:29.304
UCL 01:31.511
Five of the slowest cars are eliminated.
Now comes the specification limit, which is set based on the 107% rule.
For instance, if the fastest lap time was 100 seconds, each driver who is eliminated in the session must complete at least one lap within 107 seconds to guarantee a race start, which is the USL. Often, only one specification limit is used as in this example. 
 
Control limits are applied to summary statistics, whereas specification limits are applied to individual measurements. Control and specification limits are extensively used in control charts and can give us an early warning if a process is showing irregularities, giving us the opportunity to take remedial steps before the situation becomes a problem.
 
Let’s consider another example from the customer contact center: if the average handling time is 4 minutes with a standard deviation of 1 minute, then the control limits are UCL = 7 minutes and LCL = 1 minute, respectively. Specification limits are the targets for the process and defined by the customer or based on the performance of the market. It is desired that those control limits be within the specification limits so that, in case of special causes, the customer will not be impacted.
 
Application of control limits in control chart:
The position and scattering of data points plotted on the control chart assist us in identifying process behavior. Process behavior includes that of identifying the stability and understanding the pattern of process variation from a special and common cause viewpoint.
 
Let’s consider one more example based on the below referred Shewhart chart of a manufacturing unit of Prod X.
 

 
If we could notice that none of the data points are outside the specification limits, and usually the production management team will be OK and glad about this type of run, it is worth noting that if the process were managed statistically, these patterns would assist the line engineer in adjusting and retargeting the process. However, the effectiveness of re-targeting will be determined by the usefulness of the process gain factors. 
 
Consider the following scenarios to better understand process performance:
Scenario 1: The specification limit is within the control limits.
Scenario 2: The specification limit is the same as the control limit.
Scenario 3: The specification limits exceed the control limits. 
 

 
In scenario 1, part of the process (natural variation) may function outside of customer-defined targets, leading to rejections and defects.
 
In scenario 2, the process may meet customer specifications, but it can produce defects when there is an uncommon source of variation.
 
In scenario 3, which I would call an optimal scenario, the production is stable, within its capability, produces no defects or rejections, and of course meets the customer specification.
 
To summarize,
Control limits are calculated from the process data, so they are the voice of the process, and specification limits are defined by the customer, so they are the voice of the customer. Control limits emphasize location, spread, and width, whereas specification limits focus on meeting the requirements. Control limits are applied to subgroups, and specification limits are applied to items. Control limits help reduce internal rejections in the process, and specification limits help reduce customer rejections. Control limits are displayed in the control chart, and specification limits are displayed in the histogram and probability plots.  

Bowtie Analysis is used for risk assessment, risk management and risk communication.
By using bowtie diagram we can visualise risk. It shows the causes and consequences of an event. More over the control measures to mitigate the risk is also shown on the diagram. 
 
Having potential causes and control barriers on one side and having potential outcomes and defense causes the other side of the hazardous event gives this analysis the shape of "Bow Tie". It simply combines Fault Tree (FT) and Event Tree (ET).  

Bow-tie Shape reference
 

Bow-tie Modelling 
Examples:

Factory Fire Bow-tie Example
 

Financial Product Bow-tie Example
 

Car Crash Bow-tie Example
 
Bow-tie use cases:
Risk Analysis
Reliability Engineering 
Safety Assessment 
Mining 
 
FMEA use Cases:
Chemical
Aerospace 
Military
Automobile
Electrical
Mechanical
Large scale industries 
 
Difference between FMEA and Bowtie:
FMEA is Bottom-up and Bowtie can be constructed using both bottom-up and top-down approach 
FMEA is quantitative whereas Bowtie is qualitative 
 
In general, risk analysis helps an organization to identify risks and potential threats to its internal operational processes and provides severity and likelihood of those occurrences. Below is the list of risk analysis methods and techniques.
 
Qualitative:
Bowtie Analysis
Delphi Technique
SWIFT Analysis
Fly Analysis
Risk Register
Probability-Impact Matrix
Risk Categorisation
Expert Judgement
 
Quantitative:
Monte Carlo simulation
Decision Tree Analysis
Sensitivity Analysis
Three-Point Estimation
FMEA
Scenario Analysis
Latin Hyper Cube Simulation
 
Conclusion: 
Even though there are many risk assessment methods like Bowtie, FTA, FMEA, etc., they focus with single threats and most of the time struggle to represent multiple simultaneous failures.
FMEA systematically identifies the effects/consequence of Failure mode and used to remove/reduce the possibilities of failure and Bowtie, predominantly gives hazard insights and its management and helps to represent the influence of safety system on the shop floor accident scenario.   
Integrating them, both Bowtie and FMEA can be used together for hazard analysis and risk assessment. Detection rating and RPN calculation based on FMEA along with corrective measures to improvement RPN and subsequently using bowtie to identify safety critical barriers and associates actions can improve the effectiveness drastically. 

Synchronous (dependent) is sequential and happens one at a time, whereas in Asynchronous (independent) concurrent parallel operations are possible. 

In the below reference, total time taken to complete all 4 tasks in Asynchronous system is just 20 seconds compared to that of 45 seconds in the Synchronous sequential process execution. 
 

 
For instance, zoom meetings happens sequential, which is Synchronous, whereas email communication, online posts can be asynchronous, and be concurrent to keep the target audience engaged for different roles, functions, regions, and programs.
 


As referred in the above example, request stacks in synchronous system, and typically referring from a web service request scenario, clients have to wait on the queue until the previous loop is executed and most of the time, what they see is a timeout response. 

Asynchronous system allows multi-tasking, has better resource utilization, with fewer wait times and is more adaptable and the leading contribution is the enhanced throughput that we get out of asynchronous systems, on the contrary synchronous system performs function one at a time and follows rigid sequence.
 
Thus, it is advantageous to use the asynchronous system, especially in an agile, multi-request system environment, however, it is wise to use synchronous in reactive systems. So to conclude, It is better and suggested to evaluate and identify the dependencies in the processes to select the best optimal approach that works for the organization. 

“Data is more valuable than Oil”, nevertheless are we leveraging it to the extreme capacity? 
The answer is simple, it is "No” and it simply becomes dark data!
 
Gartner, coined this term ‘Dark data’ and defines it as “The information assets organizations collect, process, and store during regular business activities, but generally fail to use for their analytics, business relationships and direct monetizing” 
 
Dark data can be generated by organization’s systems, devices, and interactions and typically most of the time it is the CRM, ERP, SCADA, HTTP, IoT and even WIFI systems which collects the data. 
 
It can be stored physically or on the storage peripherals or in cloud. While most of the data is unstructured, some of the examples of Dark data includes that of below, but not limited to the list,
Application logs Customer records Geolocation Survey data Financial statements Customer Address  Contact details CCTV footage Emails Chat messages Medical records Zip files  Archived web content  Code snippets  Biggest challenges with regards to dark data is with regards to:
Security dangers (hacks)  Compliance issues  Data authenticity and  High Storage cost Brand Reputation  Opportunity Cost Risk associated with the dark data can be easily mitigated by adhering to audit and retention policies defined by the organization. However, some best practices can have high impact to manage the risk associated with the dark data. 
 
The below model typically shows how the data is collected, stored, retained and deleted, more from an analyze, categorize and classify approach. 
 

 
Model Explained: 
 
Starting from Data classification (Public, Internal, Restricted) 

 
While we classify, it is vital to bucketize based on few critical factors, viz.,
Critical data?
Permanent document?
Proprietary Intellectual Property?
Document/data serves the current needs of the operations?
Legal and regulatory requirement? (For instance, w.r.t HIPAA, 6 years minimum retention. In contrary, GDPR allow data storage for an extended period, however, solely should be used for the purpose of public interest, statistical analysis and for historical research only)
Hot Data or Cold data? (hot data is accessed frequently and used for quick decision whereas cold data is old data and are not frequently used)

Based on the classification, then deciding whether to store or delete.
If we wanted to store what is the retention period and how it will be useful.
 
When we follow this approach, along with Regular data Audit and internal Data Life Cycle Management (DLCM), we can make the maximum utilization of the data from the data pool. 
 
Ways to leverage Dark data:
Text Mining / Word mining  Data mining methods  Voice to Text analytics  Data analytics  Prescriptive analytics  Behavior analysis, which can be used to train AI models for prediction  Big data analytics and visualization (SAP HANA) Data Forecasting  Trend Analysis  Investigate past complaints  Google’s approach to data management:
“Some data you can delete whenever you like, some data is deleted automatically, and some data we retain for longer periods of time when necessary. When you delete data, we follow a deletion policy to make sure that your data is safely and completely removed from our servers or retained only in anonymized form.”
 
Apple’s approach to data storage:
Apple uses personal data to power our services, to process your transactions, to communicate with you, for security and fraud prevention, and to comply with law. We may also use personal data for other purposes with your consent.
 
Final say:
Data violations have earned a lot of notice in recent years as businesses become more dependent on digital data, cloud computing, and remote working. As a result, compliance and regulations have emerged as a requirement for ensuring information security. 

Using data analytic application suites can manage unified unstructured data effectively and can provide intelligent identification of data sets in the organization which can be in line with the industry legal and regulatory requirements.
 

Cobots are similar but smaller when compared to that of industrial robots.
It is also comparatively cheaper in price and much user friendly.
 
For a large-scale mass production, industrial robots can provide best efficiency. However, for small and medium scale businesses, cobots can be much more effective when it comes to automation on the shop floor.
 
Cobots are Collaborative Robots. It is more of a collaboration between Human and Robot in a shared space and can optimize human work in various aspects.
 

 
International Federation of Robotics (IFR) defines multi-level of collaboration viz., Coexistence, Sequential, Cooperation and Responsive Collaboration.
 
Traditional Robots are best fit for:
Large batches, small variability
Complex deployment
Consistent environment
Human monitoring
Focus on Robot Automation
Big Investments
Longer ROI
 
Alternatively, Cobots could be a best alternative for:
Low-volume, high-mix
Fast and Easy deployment
Agile and adapts to environment
Collaborative
Focus on End-Of-Arm-Tooling (EOAT)
Lower upfront cost
Faster ROI
 
Cobots in Service Industry:
It is often referred as RaaS (Robots-as-a-Service) and few of the utilities includes that of,
Robotic-Assisted Knee Surgery (robotic arm assistance)   Food Robots - Packaging (Wrapper, Vacuum sealer) Food Robots - Other Applications (Palletizing, Pick-and-place, Logistical automation) Product Quality Inspection (Cobot arms for visual inspection using 3d Cameras) Aviation (Cobot co-pilot mainly for Military UCAV (Unmanned combat aerial vehicles)) Agriculture (Farming - Once Cobot identifies flowers, fan gets activated for effective pollination (Smart Farming)) Diary (Robotic Milking)   Restaurant Cobot  
 
These cobots are identified and selected based on critical factors such as,
Reach (500 - 900 mm)
Payload (2kg - 16kg)
Footprint (Ø 128 - 200 mm)
Weight (10kg - 35kg)
 
Technology Advancements like IoT features with loaded capabilities such as heat sensors and thermal cameras help the cobots to perform more accurate tasks based on their use cases. Anticipating the rise of 5G, could lead Cobots to get fully automated and to perform tasks with greater accuracy.

Prioritization Matrix is an essential and useful tool which assists in breaking down tasks and activities when there is too much in the plate. This facilitates decision making and help leaders to consider those activities which are most relevant, urgent, important and required for project and process sustenance. 
 
There are many variants of 2x2 Prioritization Matrix. 
Frequently used few are listed below.
RVCE Matrix (Risk, Value, Cost and Effort) Eisenhower Matrix (Urgent, Important) MoSCoW - Value Based Prioritization Techniques (Must Have, Should Have, Could Have, Won't Have) WSJF (Value and Effort) Kano (Performance, Must-be, Attractive, Indifferent) RVCE Matrix:
Decision Criteria: Risk, Value, Cost and Effort
Decision/Outcome: Consider, Avoid, Investigate and Prioritize 

 
Eisenhower Matrix:
Decision Criteria: Important or not, Urgent or not
Decision/Outcome: Do, Decide, Delegate, Delete
 

 
MoSCoW: Prioritization based on Value/Features 
Decision: Must have, Should have, Will not have, Could have
 

 
WSJF:
Decision Criteria: Value and Effort - High and Low
Decision/Outcome: Do now, Do Later, Do Next, Don't Do 
 
 
 
Kano:
Decision Criteria: Satisfaction and Functionality 
 

 
Other applications/variants of prioritization models includes that of:
Lean Prioritization, where the effort is compared with ROI/Degree of Impact to consider the outcomes as Low Priority, Just Do it, Reconsider and Complex but worthwhile.  Value and Risk Value and Effort  Value and Complexity  Benefits:
Allows to analyze and compare results  It removes bias Allows to objectively rank the priorities  Determines most critical focus area Keeps progress of the project Better Time management  Depending upon the type of project and consideration we can select any of the above mentioned models to Focus on the right project and better manage our time. My personal favorite model is Eisenhower Matrix, which is kind of, has the combination of essence from all the prioritization models available.
 

Prioritization Matrix is an essential and useful tool which assists in breaking down tasks and activities when there is too much in the plate. This facilitates decision making and help leaders to consider those activities which are most relevant, urgent, important and required for project and process sustenance. 
 
There are many variants of 2x2 Prioritization Matrix. 
Frequently used few are listed below.
RVCE Matrix (Risk, Value, Cost and Effort) Eisenhower Matrix (Urgent, Important) MoSCoW - Value Based Prioritization Techniques (Must Have, Should Have, Could Have, Won't Have) WSJF (Value and Effort) Kano (Performance, Must-be, Attractive, Indifferent) RVCE Matrix:
Decision Criteria: Risk, Value, Cost and Effort
Decision/Outcome: Consider, Avoid, Investigate and Prioritize 

 
Eisenhower Matrix:
Decision Criteria: Important or not, Urgent or not
Decision/Outcome: Do, Decide, Delegate, Delete
 

 
MoSCoW: Prioritization based on Value/Features 
Decision: Must have, Should have, Will not have, Could have
 

 
WSJF:
Decision Criteria: Value and Effort - High and Low
Decision/Outcome: Do now, Do Later, Do Next, Don't Do 
 
 
 
Kano:
Decision Criteria: Satisfaction and Functionality 
 

 
Other applications/variants of prioritization models includes that of:
Lean Prioritization, where the effort is compared with ROI/Degree of Impact to consider the outcomes as Low Priority, Just Do it, Reconsider and Complex but worthwhile.  Value and Risk Value and Effort  Value and Complexity  Benefits:
Allows to analyze and compare results  It removes bias Allows to objectively rank the priorities  Determines most critical focus area Keeps progress of the project Better Time management  Depending upon the type of project and consideration we can select any of the above mentioned models to Focus on the right project and better manage our time. My personal favorite model is Eisenhower Matrix, which is kind of, has the combination of essence from all the prioritization models available.
 

Prioritization Matrix is an essential and useful tool which assists in breaking down tasks and activities when there is too much in the plate. This facilitates decision making and help leaders to consider those activities which are most relevant, urgent, important and required for project and process sustenance. 
 
There are many variants of 2x2 Prioritization Matrix. 
Frequently used few are listed below.
RVCE Matrix (Risk, Value, Cost and Effort) Eisenhower Matrix (Urgent, Important) MoSCoW - Value Based Prioritization Techniques (Must Have, Should Have, Could Have, Won't Have) WSJF (Value and Effort) Kano (Performance, Must-be, Attractive, Indifferent) RVCE Matrix:
Decision Criteria: Risk, Value, Cost and Effort
Decision/Outcome: Consider, Avoid, Investigate and Prioritize 

 
Eisenhower Matrix:
Decision Criteria: Important or not, Urgent or not
Decision/Outcome: Do, Decide, Delegate, Delete
 

 
MoSCoW: Prioritization based on Value/Features 
Decision: Must have, Should have, Will not have, Could have
 

 
WSJF:
Decision Criteria: Value and Effort - High and Low
Decision/Outcome: Do now, Do Later, Do Next, Don't Do 
 
 
 
Kano:
Decision Criteria: Satisfaction and Functionality 
 

 
Other applications/variants of prioritization models includes that of:
Lean Prioritization, where the effort is compared with ROI/Degree of Impact to consider the outcomes as Low Priority, Just Do it, Reconsider and Complex but worthwhile.  Value and Risk Value and Effort  Value and Complexity  Benefits:
Allows to analyze and compare results  It removes bias Allows to objectively rank the priorities  Determines most critical focus area Keeps progress of the project Better Time management  Depending upon the type of project and consideration we can select any of the above mentioned models to Focus on the right project and better manage our time. My personal favorite model is Eisenhower Matrix, which is kind of, has the combination of essence from all the prioritization models available.
 

Hanedashi: Auto-Eject / Auto Unloading / Automatic Ejection 
This technique provides automation for machines to remove finished parts from the process. 
 
Below is a typical example of manual and automatic unloading of the finished product.
 
Manual Unloading:
 

 
Automatic Unloading:
 

Manual effort is just put in loading and not in unloading. 
 
Hanedashi is crucial for "Chaku Chaku"/"Load-Load" Line.
 
 

 
In Chaku-Chaku, operator picks and loads the finished part from Machine A to B, to complete the cycle. 
If Hanedashi is used, machine can itself unload and load the parts with out operators effort. 
Thus Hanedashi can effectively eliminate the below wastes in a lean manufacturing setup.  
Transportation: Wasted time in moving materials unnecessarily
Motion: Wasted time and efforts due to unnecessary movements by operators
Waiting: Wasted time in waiting for finished product to complete next steps
 
Some of the benefits of Hanedashi:
At same time, operations in Multiple machine is possible Operator productivity improvement Improved working condition due to better ergonomics 

Both Correlation and Covariance measures the linear association between two variables.
To be specific and make it apparent, let us understand the key difference,
Correlation measures the strength of a relationship between two variables.
Covariance measures the direction of a relationship between two variables.
 
Specific comparison:
Values:
Correlation: Standardized
Covariance: Unstandardized
 
Units:
Correlation: Has Units
Covariance: Does not have units
 
Scale:
Correlation: Change in scale does not affect the value of Correlation
Covariance: Change in Scale will affect the value of Covariance
 
Range:
Correlation: -1 to +1
Covariance: -∞ to +∞
 
Why Correlation value lies between -1 and +1?
Correlation is nothing but Covariance divided by standard deviation of the variables, hence the value lies between -1 and +1. Which means, it is scaled down version of covariance. 
 
Inferences from Analysis:
Covariance Inference:
Positive - Both the variables increase or decreases together - Directly Proportional
Negative - Inverse, if one variable increases, the other decreases - Inversely Proportional
 
Correlation Inference:
+1 - Perfect Positive linear relationship
0 - No linear relationship
-1 - Perfect Negative Linear relationship
 
Some more examples:
Correlation Examples: Pearson r Relationship 0 No relationship 0.466 Moderate positive relationship 0.95 Large positive relationship -0.96 Large negative relationship  
Covariance Examples: Covariance Relationship 0.0036 Positive 0 No variance -0.007 Negative -0.0376 Negative  
Covariance, typically can take any value and it is toilsome to interpret the number.
 
Sample Data Set:
G Price CO Price 49000 95.17 48600 98.4 48600 98.4 48600 98.4 48250 97.17 48000 97.16 47800 101.24 47800 101.24 47800 101.24 47950 103.66  
Based on the same data set, below is association summary:
Correlation(R) -0.74682 Covariance(G,CO) -744.37  

 
There are numerous applications of Correlation and Covariance, some are listed below:
Data science: one of the frequent used measurement is Covariance.
Insights from covariance analysis can help us to get more clarity on Multivariate data.
 
Stock market: Investors, traders and analyst often use correlation and covariance. Specifically, to understand the hidden correlation on the stock returns of one company to other, which could potentially bring down and minimize the investment risks.
Implied Correlation Index by CBOE (Chicago Board Options Exchange): This tracks the correlation between implied volatilities of options and weighted portfolio of options

 
Banking and Insurance: Exploratory analysis can give more insights on the variable relationship which assists in customer churn and retention.

Screening Designs: Screens factors that are not statistically significant 
 
Intention: Used for exploratory analysis.
Focus: Estimates main effects in presence of negligible interactions.
 
Most suitable for Industrial experimentation during early states of design.
When there are many significant factors, screening design can be used to condense the list to fewer once.
 
Time and again, it becomes tedious to study all the factors in detail. Screening design can be used effectively and compared to traditional design methods, screening design just require fewer experimentation runs.
To say in short, experiments are “Small and efficient”.
 
Often used screening designs include:
Fractional Factorial Design (2-Level),
Full Factorial Design (2-Level),
Definitive Screening Design, &
Mixed-level design
 
Below are few Specific design:
Plackett-Burman design,
Taguchi methods,
Cotter Design
 
However, there are many different screening designs, some of the considerations for best design fit are listed below:
Questions that we can, before finalising the design method:
What's is the Overall Goal
What are the specific response types
How are these responses measures
What are the factors that need to be considered
What should be the range for the factors
Do we have block factors
Are we working on a Split plot problem
Do we have problematic combinations of the factor settings
 
Answers to the above questions, can effectively let us know in picking the perfect design model for the screening. 
 
Lets take a case of a Chemical Product ABC as an example and use Plackett-Burman (2 Level Fractional Factorial design). Based on preliminary analysis, it was identified 11 potential factors might impact the yield of the chemical product, which is listed in the below table.

 
Simply if we want to run 2 level full factorial design, Total number of runs would be 2 Power 11 = 2048 Runs.
 
Some of the interactions between the potential factors might have trivial importance, Plackett-Burman design can be effectively used here. Lets run the design by just setting the Base number of runs as 12.
 
Below is the summary of the design settings:

 
Factor Combination and its Yield for 12 runs is shown in the below table:

 
Inference from Effect probability plot can be used to identify the significant few (Important Factors in the experiment), which is shown in red squares in the plot graph.

 
This brings down the potential factors from 11 to 5. 
 
Properties of the design generated can also be effectively evaluated by various other different output metrics, viz.,
Power Analysis,
Prediction Variance Profile,
Effect Probability Plot,
Fraction of Design Space Plot,
Prediction Variance Surface,
Estimation Efficiency,
Alias Matrix,
Color Map on Correlations, &
Design Diagnostics
 
Screening design might not be limited to industrial experimentation, however the applications of it can also be used in other functions as well. For Instance, lets consider Marketing example.  
 
2^7 Experiments or 128 Runs could be too much for a tight delivery time period of Product X, however screening designs based on preliminary analysis can help the product to touch new sales success stories. 

 
Benefits of Screening Designs:
Relatively Inexpensive (Saves $'s) 
Efficient approach for process improvement
Can run the experiments with limited resources 
Effective simulation 
 

Measles Chart commonly referred as Defect location check sheet/map is a graphical analysis tool. It can be closely compared to a scatter plot (from clustering viewpoint) in combination to a Defect Concentration diagram. 
 
To use, Measles chart, what we require is the Image of the subject of interest. 
Whenever, there is an issue, we must mark the location of the issue on the Image. 
Depending upon the issue category type, we can use different symbols. Based on the cluster, we shall be able to identify where exactly the issue is frequent and recurring on the Image. This indicates True failures, handling failures and test errors. Thus assisting us in getting into category wise solution mode rite away with a quick turnaround.
 
Below images on the examples can help the operators to quickly identify where defects are happening and could turn their focus to get into root cause of the issue to take actions. Undoubtedly, this helps in defect reduction. 
 
Example 1: Defects in Side by Side refrigerating unit 

 
Example 2: Defects in Adventure touring motorcycle 

 
Example 3: Manufacturing defects in Heavy load transport truck

 
Example 4: Stitching faults in Shirt manufacturing 

 
Example 5: Casual shoe adhesive faults 

 
Benefits of Measles Chart:
Provides visual indication of defects
Easy to deploy 
Effective defect prevention based on the application 
Quantify defects and issues by category and location
Helps to identifying the frequency of the defect occurrence
Can be performed at factory level - production floor. 
 
Precisely, measles charts is a structured analysis that helps in locating, diagnosing and correcting frequent issues / problems on the work floor to improve the operational efficiency. This analysis can help expert teams to retrospect and get into upstream processes to identify and fix the issue enduringly.
 
More reads and a comparative study on Defect concentration diagram, similar subject to that of Defect location map can be seen in the below link:

Weighted Shortest Job First (WSJF) is a prevailing model for ranking and prioritization. This is utilized in job sequencing based on features, capabilities and epics.
Scaled agile framework (SAFe) customs WSJF to prioritize backlogs.
WSJF is equally referred as CD3 (Cost of Delay Divided by Duration).
 
Calculation:
WSJF = CoD/Job Size
CoD – Cost of Delay – Economic impact of delay in project delivery
Job Size is the Job duration. 
 
Typical WSJF calculation that is used during PI Cycle is given below 

 
CoD consideration includes user business value, time criticality and risk reduction.
Below are some of the drilldowns of the respective considerations.
 
User business value:
Relative value of the opportunity Opportunity rank in comparison to other Revenue generation or cost avoidance Time Criticality:
Opportunity value decline by time Target/fixed deadline Impact Risk Reduction
Opportunity reduces risk Create new opportunities  Cost of Delay is a critical and key metric, while prioritizing and it has become essential to ask this fundamental question, “What will cost us the Most? Doing it Now or Delaying it Later?”
 
Specific to cost of delay, we can compare WSJF with other prioritization models like Short Job First and Most Valuable First. Below table summarized the comparison.  
 

 
However, possible comparison from a broader prioritization lookout, we can compare WSJF with MoSCoW, Kano, RICE, Eisenhower, Value vs Effort, Walking skeleton models.
 

 
Each model has its own Pros and Cons.

 
WSJF is a great tool for prioritization, it gives clear picture when to go for Low hanging Fruit Vs Projects with higher value. However, we don't have to rely upon WSJF each and every time as few features and deliverables are supposed to be delivered at the right time without brainstorming. 

Outline:
Attended Bots are used explicitly when we cannot automate the entire end to end process. These Bots are commonly referred as “Human-In-the-Loop” Automations (HitL).
 
Typically, the transaction is carried by both Human and Digital worker together, were the exchange/interaction and handover of data happens based on the defined logics.
 
On the contrary, unattended bots complete the transactions by interacting with various applications, independently, without human intervention.    
 
Comparisons:
Unattended RPA Attended RPA (RDA / HitL) Virtual digital employee working in background Assistant to human / Human-bot collaboration Focus on improving process  efficiency Focus on improving employee productivity Ideal for process based automation Ideal for task based automation Bot executes complete transaction (Start to finish, end to end) Bot executes partial transaction and manually completed by human intervention Used for repetitive, more frequent and simple process Used for complex processes which requires human decision making  Rule based execution Human/system triggered and involves manual inputs to execute the task Typically performs Batch Operation Mostly in attended RPA, it is  transaction/Interaction wise and not batch based  Works on preset schedule  Real time or waits in queue for human processing  Can run on work station, servers and on cloud  Usually runs on work station / single employee's desktop Can complete end to end transaction and can work 24/7 Have to wait for human actions to complete the transaction. Running 24/7 can create bottleneck, in the waiting queue to close the task Apt for back office support More suitable for Front Office Support / Service desk / Help desk / Customer Contact Center, typically Customer facing roles Server to bot communication is automated process version deployment only Server to bot communication can be automated process version deployment, start or can reset processes Frees employees from routine mundane work, reduces cost and accelerates processes Increases productivity and customer service in service environments Can be scheduled from centralized server, remotely  Mostly human trigger, real time and done on work station  
In the Human in the Loop Automation environment, there could be single or multiple human interventions, either in the start, mid or in the end of the event depending about the coded logics.
 

 
Process Examples:
 
Unattended Automation
·         Apt for back-office processes at scale
·         Invoice management system
·         Email management / Mass customer email (BFSI, Telecom, Healthcare)
·         Manual data entry / Data migration
·         Sales orders
·         KYC (Know your customer)
·         Payroll automation
·         Absence management
·         Expense management
·         Storing Customer details / Customer onboarding / Update CRM
·         Processing Express Refunds
·         Bank statement reconciliation
·         Letter Generation
·         Extract data from different formats/applications (from PDF, scanned documents, etc.)
·         Periodic report preparation
·         Update user preference (Opt-out communication)
·         Data updates and validation
·         Credit card application (seamless based on CIBIL scores)
·         Proof of delivery (POD)
·         Patient appointment scheduling (Healthcare)
·         Transferring b-cards to sales force
 
Attended Automation
·         Apt for contact center operations / front office support
·         Extract customer data from CRM automatically during employee-customer interaction
·         Profit and Loss updates
·         Address change approval triggered by employee based on correctness and completeness
·         Compliance management (Human approval, BISO involvement)
·         Loan processing (Final approval from the Loan officer)
·         High value claim processing (Human authentication)
·         Quote-to-cash (document-based data extraction)
·         Procure-to-pay (document-based data extraction)
·         Source-to-pay (document-based data extraction)
 
Below are some of the advantages for Attended Automation over unattended automation:
·         It is Agile
·         Comparatively user friendly
·         It removes real time data entry work
·         Improves team efficiency
·         Progresses team productivity
·         Improves C-SAT, NPS scores
·         It requires minimal setup
·         Deployment is Rapid
·         Achieves ROI swiftly
 
To conclude, in an attended automation environment, automation does not stops, as it collaborates with human to complete the automation process. 
 

 
 
 
Take away:
Organization can choose any of the RPA bot types and deploy as per the necessity and business needs. Nevertheless, having a unified platform (ideally Hybrid platform) to handle both attended and unattended bots would be a superlative choice. 
 
Both RPA and RDA are integral part of Intelligent Automation Suite. 
However, the primary objective of going for an Automation, is to have minimal human involvement in the business process flow, hence RPA has an upper hand compared to RDA. 

Both Lean and Agile methodologies are flexible and focuses on continuous improvement and share common goals and principles, however the workflow is more iterative in agile
 
Key differences with regards to both the methodology is that, Lean focuses on maximizing the efficiencies whereas, agile is more of maximizing the effectiveness
 
Another paramount difference is flexibility. Lean is not that flexible when is comes to dynamic deliverable changes. However, dynamic requirement changes are effortless in Agile
 
Few difference in various toolkits used is listed below.
Lean Management - Daily Huddle meeting, VSM, RCPS, 5S, Visual Management
Agile - Daily Stand up, Backlog, Sprints
 
Lean methodology delivers Value; Agile delivers Working Product (wherein, small batch size is preferred to deliver rapidly)
 
Even though there are considerable difference between Lean and Agile, both methodologies complements each other in most of the working situations and some of the commonalities including Improving Quality, Amplifying learning, Continuously improving and empowering people makes both approach collaborative.  
 
Choosing one over other is not pivotal as exploring what principles better suits the working model in the organization and incorporating them in the software development process matters.  
 

EMO Index outlines the Emotional State (Emotional Footprint) of the consumer or group of customer towards a Company based on Positive(+) and Negative(-) emotions and their magnitude.
This is examined on a scale of -100 to +100 based on their previous experience towards the Company. 
 
EMO Index can be closely compared with NPS (Net Promoter Score), which measures Customer Loyalty and Satisfaction measurement taken from customers, asking, how likely they are to recommend Companies product or service to others on a scale of 0-10.

NPS is a measure of the percentage of customers who are promoters of a brand name or company, minus the percentage of detractors.
 
At times, it is debated that NPS is a poor indicator to predict the growth of a company.
On the contrary, EMO Index adds significant value in comparison with more traditional and simplistic classification approaches. 
 
Here in EMO Index, customer classification is done based on the emotional print associated with the Company based on the experience as Fans, Believers, Followers, Stand by, Lost Souls, Burned-out and Opponents. 
 

 
Modus operandi:
To calculate EMO Index, primarily comprehensive analysis is performed to determine which emotions are relevant for the Studied Domain/Industry/Sector. Id ést, emotions such as Surprise, Happiness, Love, Irritation, disappointments, Anger, et cetera. 
 
Then representative sample of customers are identified and asked if they have experienced each of these emotions at any particular time in dealing with the Company.
 
Emotional Levels are also measured parallelly with the possible reasons that may have caused them (Triggers).
Customer are then classified as Fans, Believers, Followers, Stand by, Lost Souls, Burned-out and Opponents.
 
Finally, emotional segmentation is introduced based on above said classification. This ties in with the power of emotions on the future behavior of the Customer. 
 
EMO Index is widely used in Retail Banking, Healthcare, Telecommunication and Advertising sectors majorly adopted in Spain and Latin America.
 
Below is the example of a comprehensive study conducted by EMO Insights on popular banks in Spain. Ranking based on more fans than opponents. 
 
     
Integration of emotions in the models of decision-making improve their explanatory power tremendously.
 
 
Any emotion, even those that are not directly related to decision-making, may have a significant impact on the opinion or final decisions. Measuring loyalty, satisfaction and emotions are much needed to keep the customer tied to the company in a long run. 

PDCA - Plan, Do, Check, Act (Starts with Planning phase)
OODA - Observe, Orient, Decide, Act (Starts with Observation)
 
                           PDCA                              OODA Feedback is received after completion of cycle Feedback is received almost at all phases ( Orient, Decide, Act )     Focuses on the operational / tactical requirements  Focuses on strategic requirements     Pioneered by William Deming in 1950s Developed in the mid-20th century by military strategist     PDCA Cycle is more of an analytical approach OODA is  concerned with synthesizing an action out of an incomplete data set.      PDCA is more moving from a reactive problem fixing model to a proactive one More Reactive - Implies on how to react to changes in circumstances and take new actions as quickly as possible.     Used to take Preemptive measures Used widely for Incident response     Usually longer cycles, iterative approach Usually short cycle and done in real-time  
PDCA is used extensively in Software development lifecycle, healthcare Industry, manufacturing and Service industries for new product development, for Project Management, and for Change Management.
OODA is commonly adopted in business, game theory, information security, law enforcement, litigation, marketing and military strategy. 
 
OODA is essentially the same as the “Plan, Do, Check, Act” principle that is fundamental to all ongoing process improvement initiatives. Extended version of PDCA is OPDCA, "O" stands for Observation, it starts with Observing the current conditional and proceeds with planning, which is quite similar to that of OODA approach.
 
               PDCA (Benefits)                OODA (Benefits) The iterative approach allows control and analysis Enables quicker, more streamlined decision processes.
 
Powerful and Straightforward Tool and provides greater efficiency and effectiveness Brings more organizational transparency and situational awareness.
 
          PDCA (Disadvantages)           OODA (Disadvantages)
The unspecific definition can lead to incorrect use It can be difficult to understand or interpreted in various ways.
 
Paralysis By Analysis, Changes must be planned over longer periods of time Can make it harder to “undo” a mistake.  
When we use both concepts together, PDCA and OODA, we would have higher quality level while making critical decisions. From a lean perspective OODA is similar to that of PDCA, but from CAPD order (Check, Act, Plan and Do)

PDPC – Process Decision Program Chart
PDPC spreads the tree diagram to successive levels to identify risks and countermeasures for the low-level tasks. PDPC is like that of FMEA in identifying risks, effects of failure and contingency actions.
It throws light on what might go wrong (Risks/Failures), highlight the Consequence of failure (Effect), and come with Potential countermeasures (Risk Mitigation).
 
PDPC helps prepare the contingency plans. It systematically identifies what might go wrong in a plan
under development. Countermeasures are developed to prevent or offset those problems.
 

 
By using this technique, we can either revise the plan to avoid the problems or be ready with the best
response when a problem occurs.
 
When PDPC is used:
Before implementing a large or complex plan.
When the plan must be completed on schedule/target.
When the price of failure (Cost of Poor Quality) is high.
 
Example: Improve Service Delivery 

 
How it is used:
Build Tree Diagram for the proposed plan (high level View)
3 Levels – Objective, Main Activities
For each of the main activities, brainstorming is done to see what could go wrong
List the problems associated in the next level
For the listed potential problem, brainstorm and come with countermeasures
Highlight feasible actions/countermeasures as O and impractical measures with X (use criteria such as cost, time, ease and effectiveness to arrive at conclusion)
 
Example: 
Below PDPC is build to execute Sales Pitch to the Client

 

Competitive advantage referred by Michael Porter is that for any Industry can have the competitive edge by pursuing in any of two unique ways, either 
→ through Low Cost (Cost Leadership), or 
→ through Differentiation 
and the third generic strategy is through Focus.
He also points, failure to follow this strategy could end up stuck on the middle scenario and subsequently the organization might not be able to retain long-term competitive advantage over rivals.
 
Below is Porter’s generic strategies model:

 
Objective
Cost Leadership
Differentiation
Focus
Lowering selling/servicing price, by cutting cost of production/purchasing/service
Offer Finest/First Class Quality product that can't be matched by rivals and charge a premium for this "Difference"
Positioning the business in one specific niche in the market
Examples
Redmi, OnePlus
Macbook, iMac
Samsung: Fold (Differentiation), A/M Series (cost-focus)
 
Cost Leadership can be achieved by:
Setting facilities/resources to obtain economies of scale Improving productivity  Keeping overhead cost minimal Low cost source supply Relocate to cheaper location. To Differentiate:
Building brand Image Special features that stand out Providing exceptional service and user experience Below is an example in car industry: 
 

 
Hyundai’s cost leadership strategy depends on attracting a large customer base and keeping prices low.
Mercedes-Benz builds its differentiation strategy around offering extravagance features and providing exceptional service.
In a focused Cost Leadership, Morris Garage does not offer a full array of car lineup, but those that it does offer (SUV/MUV) are priced to cruise. 
Ferrari follows a focused differentiation strategy by assembling with exclusive materials and with finest craftsmanship for Niche market segments. 
 
Although there is a risk/disadvantages with any of referred strategies, Porter argues that a firm must pursue one of them to have competitive edge. 
Which one to select depends on market conditions and unique set of core competencies of the firm and thus closing this with his quotes.
 

Defect Concentration Diagram / Problem Concentration Diagram is one of the "Magnificent Seven" SPC tools. It is also referred as Location Plot or Defect Location Check Sheet.

Defect Concentration Diagram is a graphical tool that is used in analyzing the causes of the unit defects.
It can be used and applied to any process, it shows the picture of the unit/product (or item of interest) and associated defects in the unit, in all relevant views. Location and frequencies of various defects are clearly given in visuals. Defect data segregated based on location.


The diagram is further analyzed to determine if the defect location of the unit provides any useful information about the potential causes of the defects. This is repeated with enough sampling of units, to study patterns of defect and to set the focus area of improvement.
 
It is widely used during,
Problem identification (data collection phase) When analyzing a part for potential defects When a part has multiple defects when problems arise after purchase of parts Defects to a large outspread affects shipping decisions and Defect classification is a vital step associated with Inspection. Based on the severity of the defect, it is usually classified as Minor, Major and Critical.
Minor Defects - Don’t affect the function/form of the item
Major defects - Affect the function, performance or appearance of a product
Critical defects - Unusable and/or could cause harm to the user


 
Analysis Actionable:
Based on the study, it would help the product manufacture to make decisions like
Asking supplier to correct quality issues – Ask for replacement of the supplied item
Re-inspect – ensuring to correct the defects
Callback products – Keeps customer safe
Chargeback suppliers - Re-inspection and Re-work cost
Destroy unusable goods - prevent defective goods getting into grey market
 
It help to a great extend in product improvement for example,
A smartphone manufacturer can analyze defect concentration diagram of unusable/defective smartphone which the customer returned during warranty to study the type, frequency, severity and also the pattern of the defects to strengthen and improve the smartphone in the subsequent release.
 
Recent Advancement:
Usually inspection is performed manually by human and it could be sometimes unstable and insufficient. Surface defects, such as scratches, cracks and dents are common during manufacturing process.
 
Defect identification methods have improved a lot in recent times. 

 
One such improvement is Automatic Surface Defect Inspection System for Automobiles Using 3D Machine Vision Methods with integrated software’s which gives Defect Concentration Diagram in multi dimension.
 
To reduce the number of Rejects, it is necessary to know not only the percentage but also the location and the types of defects. Defect Concentration Diagram is a great tool to locate the type, frequency, location and the pattern of the occurring defect.

CTQ (Critical to Quality) Tree is used to drill down to a more concrete project goal.
It starts with wider project goal and works downwards to identify “Critical” factors that is required in achieving the goal.
In simple words drill down generic goal, identify specific and measurable necessities to improve performance. It translates customer needs to Meaningful, Measurable, and Actionable metrics.
 
Approach:
Step 1: Identify Critical Needs
 "What is critical for this product or service?"  Brainstorm needs with key stakeholders Step 2: Identify Quality Requirements
 Identify the specific quality drivers  Identify all the requirements that are important Step 3: Identify Performance Requirements
 Identify the measurable performance requirements Points to remember before getting in CTQ tree.
Identify customers Collect Voice of Customer data Analyze VoC data Prepare a list of CTQs Choose one CTQ and prepare a CTQ tree only for that CTQ. Components of CTQ Tree:
Need
it is the origin of CTQ tree, and it highlights the customer requirements

Driver
Drivers are the parameters on which a customer judges the quality of product.

Requirements
These are the measurable performance specifications that have to be met by drivers to satisfy customers.
 
In order to make an effective and efficient CTQ tree, it is necessary to identify all the above components perfectly.

 
Below is an example of CTQ drill down for a Good Coffee
 
Benefits of CTQ:
It highlights any weak areas in an organization where performance is below standard and helps in root cause analysis. It helps to identify private needs of the individual customer and recognize measurable performance requirements needed for specific customer’s satisfaction. Helps in the quality improvement of a product or service. Do’s while doing CTQ drilldown:
Have Specific and measurable CTQs. Reflect input from primary and secondary customers (direct and indirect or stakeholders). Discuss business value of capturing and reporting a specific metric vs. cost (time and effort) of capturing that data. Delineate between metrics that exist currently vs. recommendations. For recommended metrics, discuss how they will be measured and reported. If a CTQ has no clear quantitative metric, discuss alternative ways of measurement (qualitative, other indicators). Common CTQ Errors:
Missing elements of Speed, Quality, Cost, or Risk Metrics do not reflect measurement of the process product or outcome Metrics do not have solid Operational Definitions Metrics do not demonstrate how it is calculated Metrics are not at the appropriate level of detail Information in artifacts is not consistent Artifact created individually without consultation Artifact was created but no analysis was conducted CTQ helps to understand the customer’s general requirements in more specific terms.

Multicollinearity is a statistical phenomenon.
It happens when several independent variables are highly correlated,
However not perfectly correlated and
In this situation we get regression results to be unreliable.

In the above example, we could see how and to what extend does Consumer Price Index and Inflation Index can predict the rates.
There is a considerable overlap between Consumer Price Index and Borrow Rate and
Substantial overlap between Inflation Index and Borrow rate.
Now, because there is a significant overlap between Consumer Price Index and Inflation Index themselves. It would be possible to predict with the unique non-overlapping contribution.
Unique non-overlapping contribution of Consumer Price Index is Area c and
Unique non-overlapping contribution of Inflation Index is Area b and
Area a will be lost to standard error. 
 
Why Multicollinearity is considered as a problem?
We would not be able to discriminate the individual effects of the independent variables on the dependent variable Further Correlated independent variables make it hard to make inference about individual regression coefficients and their effects on dependent variable.  
As a result, it is difficult to disprove Null Hypothesis, wherein actually the same should be rejected. 
Multicollinearity might not affect the accuracy of the model by a lot. But we might lose reliability in determining the effects of individual features of the model and that can be a problem when it comes to interpretability. How do we detect Multicollinearity?
By using scatter plot or by using correlation matrix it would be possible to detect multicollinearity with regards to bivariate relationship between variables
 
It can be detected based on Variance Inflation Factor or as popularly referred as VIF.
VIF score of independent variable represents how well the variable is explained by other independent variables.

When R2 value is close to 1, higher the value of VIF and higher the multicollinearity with the independent variable.
VIF = 1 implies No correlation between independent variables and other variables
VIF > 5, indicates high multicollinearity
 
Diagnosis and Fix:
Dropping one of the correlated features can bring down multicollinearity significantly Priority of dropping variable is based on the high VIF value
 

Combining correlated variables into one and drop the others Points to remember before fixing:
Removing multicollinearity will be a good option when more preference is given to individual features relatively to the group features that impact the focus variable
 
Efficient corrective action to remove multicollinearity requires selectivity and selectivity in turn requires specifics about the nature of the problem.
 

#KeepItSimple
 
If you have got the Bright idea, you have to cash it to get it go.
Elevator pitch is the term used for less than 2-minute presentation, the time it takes to go from Lobby to the office floor, used to catch the attention and interest of the sponsor.  
 
Points to remember:
Keep it simple and put it effortless and natural
No need to close the deal in the elevator pitch, it’s all about grabbing interest
Keep it ready, set and prepared
 
Below are 10 Do's and Don’ts that can keep your pitch SMART.  
Do's:
First and Foremost, Practice your presentation Start the pitch with a Vibrant Compelling Hook Be Positive Structure your USP Be confident Do take it slowly Have Data/Numbers to back your idea Maintain eye contact Have a quick takeaway point  Keep it to a minute or less  
Don'ts:
Don't be too fast Don't use Jargon/acronyms that might get you off track Don't focus just on yourself Don't hesitate to update your speech as the situation changes Don't be robotic (monotone way) or sound that you have memorized Don’t oversell or undersell Don't sound too salesy Don't restrict to a single pitch, have different versions Don't wrap up early if your listener is more interested or their eye's glazing over Finally, don't forget to say "Nice to Meet you" End lines, referring to the quotes from great physicist