Q 695. What is Diagnostic Analytics? Where does it fit into the problem solving domain? Support your answer with examples of its usage.

 

Note for website visitors -

• This platform hosts two weekly questions, one on Tuesday and the other on Friday. 
• All previous questions can be found here: https://www.benchmarksixsigma.com/forum/lean-six-sigma-business-excellence-questions/. 
• To participate in the current question, please visit the forum homepage at https://www.benchmarksixsigma.com/forum/.
• The question will be open until Tuesday or Friday at 5 PM Indian Standard Time, depending on the launch day. 
• Responses will not be visible until they are reviewed, and only non-plagiarised answers with less than 5-10% plagiarism will be approved. 
• If you are unsure about plagiarism, please check your answer using a plagiarism checker tool such as https://smallseotools.com/plagiarism-checker/ before submitting. 
• All correct answers shall be published, and the top-rated answer will be displayed first. The author will receive an honorable mention in our Business Excellence dictionary at https://www.benchmarksixsigma.com/forum/business-excellence-dictionary-glossary/ along with the related term.

• Some people seem to be using AI platforms to find forum answers. This is a risky approach as AI responses are error prone as our questions are application-oriented (they are never straightforward). Have a look at this funny example - https://www.benchmarksixsigma.com/forum/topic/39458-using-ai-to-respond-to-forum-questions/

• We also use an AI content detector at https://crossplag.com/ai-content-detector/. Only answers with less than 15-20% AI-generated content will be approved.

Diagnostic analytics is deeper level of analysis of the data which can help us to perform better root cause analysis. Major contributing drivers for a problem can be uncovered through this technique. The diagnostic analysis augmented with process mining can help us derive insightful observations on process cutting across various verticals within the organization and helps model the process in efficient manner. Various other benefits can be improved process visibility, data driven decision making, improved process efficiency and prioritize big tickets which can help to implement better controls and maximize the profitability. 

 

An abuse detection team (content moderation firms) using various applications and sources to detect abusive contributors through reference of multiple resources and applications involving lot of manual touch points across various applications and human decision making.

 

The diagnostic analytics augmented with process mining can be effectively use to optimize the process and implement robust controls to address manual defects.

 

> Process mining can be used to gather most used or only required signals and insights from each of the application which are useful to complete the transaction, time spent on redundant applications, manual toggling within and across applications, and also quantum of errors occurred historically by not referring to certain applications and key signals.

 

> The diagnostic analytics can help perform detailed drilled down analysis to answer gaps related to defects occurred due to human decision making steps and arrive at useful ness of required signals in each of the application. 

 

This can be further used to build a nirvana state application which contains all the required signals with robust poka-yoke controls. If we follow agile way of implementation, the signal integration can be done in phased manner and use diagnostic analytics to  measure efficacy of future state metrics and perform detailed root cause analysis on problems observed in each phase to build a robust end product.

Analytics 

Analytics is a process of discovering, interpreting, and communicating significant trends in data. These trends help to take well informed & Fact-based decision. Nowadays, more advanced analytics can be done using Generative AI and Machine learning flows.  

 

Analytics as per its objective can be categorized broadly as Below:  

1. Descriptive Analytics 

2. Diagnostic Analytics 

3. Predictive Analytics 

4. Prescriptive Analytics 

Let us understand one by one what all types of analytics means  

 

Descriptive Analytics: This type of analytics explains “What happened already”. Using past data trends and patterns, one can identify issues and act accordingly so the same will not happen in future. 

 

Diagnostic Analytics: These analytics help to answer, “Why this happened”. Using process data causes issues and process behavior identified. 

 

Predictive Analytics: Predictive analytics answers to “What potentially can happen in future”. Using advanced machine learning tools , statistical analysis , future forecast of response can be found and accordingly, the risk of the same can be minimized or eliminated.  

 

 

Prescriptive Analytics: As name suggests it about “What should we do next”. When a issue has already been identified prescriptive analytics suggest an action plan to mitigate the concern by facts.  

 

 

Example:  

• Using last month's day wise production data to identify on which day we lost the production is descriptive analytics. 

• Going further analyzing the day where production loss happened and identifying the issues &  root cause is diagnostic analytics.  

• Again, going deeper and creating a system that can forecast the potential risk of concern, will be called predictive analytics. Like using vibration and temperature data identifying, after 5-10 day (about 1 and a half weeks) there can be breakdowns in the compressor.  

• After identifying issues in the compressor, prescriptive analytics suggest a list of actions to be taken.

 

Above is a comparison of all types of analytics. and we can understand difference between them. Taking about diagnostic analytics, we can say it focuses on the root cause identification of the concerns that have already occurred.

 

Diagnostic analytics is an approach taken taken to deep dive into the problem to find the real reason for the 
outcome or problem occurred, it also explains how and why the certain issue happened by deliberating on the correlations and relationships in the data.
Here would like to share an scenario which we picked it up as a project by using this approach - 

Problem Scenario - In a billing department of ABC Co. there are manual hard copies of invoices received, 
with the TAT of 24 hours to bill the invoice in the system, allocation of copies among the team for data entry 
and missing copies of invoices was making difficult to cover the given TAT
Diagnostic analytics usage - With the help of Descriptive and Root cause analysis we were able to identify deviations based on the historical data and key performance indicators giving a clear indication of errors happening, meanwhile also performed fishbone diagrams to determine how the data entries where going wrong.
Basis the analysis we were able to come to a solution of putting up an Billing portal in the system 
through which the invoices will be uploaded into the portal by the vendor, for team to access with automated allocation of invoices to team members, this helped in saving time and avoidance of invoices going missing. The portal also prompted hard stop in the fields if data not entered correctly as per the specification integrated in the system.
To conclude, diagnostic analysis is an effective step to identify the problem and provide developmental solutions based on the detailed understanding and study of the underlying causes and issues.

Diagnostic analytics is more involved with finding root causes of the problems. As far descriptive analytics is concerned, it relates to working with past data to identify trends, patterns (through analyzing mean, median, mode, standard deviation, charts etc.)  to get a hang of past performance & output variable to focus with. Whereas, predictive analytics deals with forecasting the future using the study of root causes of deviations (reason behind variation of input variable which drove the variation in output variable as identified through descriptive analytics) as derived through use of diagnostic analytics tools & methods (i.e., gage r&r, DOE, 5why etc.). Hence, diagnostic analytics works as a bridge between Descriptive analytics & Predictive analytics.

Examples of Diagnostic analytics:1.  identifying the reasons behind customer churn, such as poor network coverage, high prices, or inadequate customer support, 2. to determine the root cause of product failures, such as design flaws, material defects, or manufacturing process issues.3. to understand why a marketing campaign was successful or unsuccessful, and what factors contributed to the outcome etc.

Diagnostic analytics is a subset of data analysis focusing on understanding the reasons for the occurrence of a particular event. While descriptive analytics tells you the ‘what’ diagnostic analytics digs deeper to explain the reasons behind those outcomes – ‘the why”. This involves gathering data, analyzing it, identifying causes, and testing hypotheses.

 

How It Fits into Problem Solving

 

In the problem-solving domain, diagnostic analytics can assist when you are trying to figure out the underlying reasons for an issue, post identifying a problem. It helps decision-makers understand the factors contributing to a situation so they can address the root causes and not just the symptoms. This approach provides important insights that guide decisions and help prevent similar issues in the future.

 

Here are a few examples:

 

• Sales: If a company sees a decline in sales, diagnostic analytics can help investigate factors like market changes, shifts in customer behavior, or the impact of competitor action. It can also assess the effectiveness of marketing strategies and staff performance. By examining these aspects, the company can pinpoint the exact reasons for the drop in sales.
• Transportation: When a transportation team experiences an uptick in delays, diagnostic analytics can help them analyze traffic patterns, vehicle maintenance issues, driver schedules, weather conditions, and route changes. By looking into these areas, transportation managers can figure out the reasons causing such delays.
• Human Resources: If a company notices a rise in employee turnover, the HR department can use diagnostic analytics to dig into potential reasons like job satisfaction, feedback from exit interviews, changes in remuneration, management practices, workload, or trends in the job market. This helps them understand why employees are leaving and what steps can be taken to improve retention.

In short, diagnostic analytics turns raw data into useful insights, making it easier to make informed decisions and achieve better outcomes in the future.

 

 

Diagnostic Analytics is one of the data analytics techniques that analyses a dataset to arrive at root causes of events, behaviours, and outcomes.  It is primarily conducted to provide insights on various factors that are responsible for a problem at hand and tends to uncover the “WHY” behind the data.  The data source, quality and reliability is paramount while conducting a Diagnostic Analysis.

 

Diagnostic Analytics primarily represents the Current State in a problem-solving domain which connects the dots between Descriptive Analytics (what is wrong?) and Predictive Analytics (what is likely to happen?).  The findings of these provide further insights on Prescriptive Analytics (Future Course of Action).

 

In a DMAIC framework of six sigma, maximum value can be derived from Diagnostic Analytics in the Analyze phase. 

 

Examples & Use Cases:

 

• RCA Techniques: 5 WHYs & Pareto analysis to find out of the root cause -
  • For e.g. A 5-why analysis revealed increased usage of UPI transactions to be the root cause of CASA ratio decline in a leading bank. 
  • A pareto analysis showed that discounted products which correspond to 20% of the overall merchandise are contributing to around 80% of the sales. 
  • Clinical Diagnostic tests use patient's tests results data to generate a complete summary based on the insights derived post comparing it against the standard and also against patient's past data. The physician in turn could do RCA to derive meaningful conclusions as to why this is happening.
• Hypothesis testing: To test an assumption that better wages outside is contributing the most to the attrition in a leading organization. A sample of exit interview data was subjected to a statistical test (1 proportion test).  The test result was found to be statistically and practically irrelevant and rejected the assumption.
• Correlation & Regression Analysis: Many stock broking platforms have built-in algorithms based on pattern recognition, correlation & regression analysis to derive meaningful conclusions so that their investors can make informed decisions.
• Anomaly Detection: Network analysis make use of built-in control charts to detect any anomalies that may shed further light on the assignable causes of frequent downtimes and network jams.

 

A very straight forward question after a long time

 

Pradeep Kandpal has provided the best answer to this simple question. Well done!