m.v.elango79

The Trade-Off Should Not Be Accepted — A Clear Case Against Implementation My Position A 20% speed gain does not justify a 10% increase in errors. The trade-off fails on business value, customer ethics, and operational integrity. This is not about resisting change. It is about refusing a bad deal. Why This Trade-Off Fails: The Real Cost Model Before any strategic argument, the numbers must be honest. Average cost to process one correct order: $8–$12 Average cost to resolve one incorrect order: $25–$50 (returns + reshipment + CS handling + refund) If you process 10,000 orders daily: Metric Before Change After Change Error rate (at 5% baseline) 500 errors/day 550 errors/day Daily error resolution cost $20,000 $22,000–$27,500 Annual additional error cost — +$912,500 Speed gains generate revenue. Error increases consume it silently. The trade-off does not break even — it creates a hidden liability. The Amazon Argument Works Against the Trade-Off Bex cited Amazon as a model for accepting speed gains with quality setbacks. The evidence says the opposite. Amazon did not win by accepting errors. Amazon invested billions in: Robotics (Kiva Systems, acquired 2012) to achieve speed and accuracy simultaneously Real-time inventory verification at every pick station AI systems specifically designed to eliminate the speed-accuracy conflict Amazon's competitive advantage was refusing the trade-off — not accepting it. When Amazon's third-party sellers produce high error rates, Amazon removes them from the platform. That is how seriously Amazon treats fulfillment accuracy. Live Business Examples Where This Trade-Off Failed Case 1 — Walmart Automated Fulfillment (2021) Walmart accelerated its automated fulfillment rollout to compete with Amazon. Increased processing speed led to a measurable rise in mis-picks and inventory mismatches. The result: customer complaint volumes rose, and Walmart had to invest an additional $150M in quality correction systems — costs that erased a significant portion of the efficiency gains. Case 2 — FedEx Ground AI Routing (2019–2020) FedEx implemented AI-driven route and sorting optimization that improved throughput speed. However, package misrouting increased during the transition. The downstream cost — redelivery, customer compensation, and brand damage — contributed to quarterly earnings and forced a rollback of certain AI parameters. The Pattern Is Consistent Speed gains are visible and celebrated. Error costs are diffuse and delayed. Organizations systematically underestimate the second because it arrives slowly and across multiple departments. The AI Implication: Why This Trade-Off Is Especially Dangerous When an AI system produces this recommendation, it signals a misaligned objective function. The AI was optimized for speed. It found speed. It was not penalized for errors — so it ignored them. This is not a fulfillment problem. This is an AI governance problem. Accepting the output teaches the AI system that errors are an acceptable variable. Future optimizations will continue trading quality for speed because the model learned that this trade-off is tolerated. Implementing this change does not just affect today's orders. It sets the reward signal for every future AI recommendation in this system. The correct response is to return the objective to the AI with a hard constraint: "Achieve speed gains only within a maximum error rate of X%." That is responsible for AI deployment. Accepting the flawed output is not. Business Ethics: Who Pays the Price This is the argument that cannot be dismissed with operational language. The company captures the speed benefit — faster throughput, lower labor cost per order The customer pays the error cost — wrong item received, time lost, trust broken The customer did not agree to be part of this optimization experiment. They paid for a correct order delivered quickly — not a faster process with a higher chance of failure. This asymmetry is an ethical problem, not just an operational one. In regulated industries, this would be called transferring risk to the consumer without disclosure. In e-commerce, it erodes the foundational promise of the service. The Clear Path: Why I Choose No Reason Evidence The Cost model is negative Error resolution costs outpace speed revenue gains Amazon proves the trade-off is avoidable They achieved speed and accuracy — not one at the expense of the other Real cases show delayed but severe consequences Walmart and FedEx both paid more to fix errors than the speed gains were worth AI governance requires rejecting misaligned outputs Accepting this output corrupts the model's future recommendations Business ethics prohibits transferring hidden costs to customers The company benefits; the customer suffers — that is not a balanced trade-off Conclusion The right decision is not to implement the change in its current form — and to send the AI system back with a corrected objective. Speed and accuracy are not inherently in conflict. The AI found a local optimum because it was not told that errors have cost. Fix the model. Demand both. Accept neither a slower process nor a less accurate one. That is not idealism. That is what the business value analysis requires.

Wait Until the Organization Is Ready Choosing View B is not about slowing progress — it is about protecting the actual outcome. A 25% efficiency gain exists only if the implementation succeeds. A failed rollout does not just lose the gain — it poisons the well for every AI-driven recommendation that follows. Hope everyone remember JPMorgan Chase and the COIN Program In 2017, JPMorgan Chase launched COIN — Contract Intelligence, an AI-powered tool designed to review commercial loan agreements. A task that consumed 360,000 hours of lawyer and loan officer time annually was reduced to seconds by the algorithm. The technology was genuinely breakthrough. The data was clean. The efficiency case was undeniable. But what the headlines celebrated, the internal reality complicated. The lawyers and operations staff who had owned the contract review process for years were not simply handed a new tool and expected to trust it. These were professionals whose expertise, judgment, and professional identity were built around doing precisely what COIN now claimed to do faster and better. The implicit message they received was uncomfortable: "The work you spent years mastering — the machine does it now." JPMorgan's leadership recognized early that the technology was ready before the organization was. The rollout was not a single switch-flip. It required: Structured communication about what COIN would and would not replace Redefining the role of legal and operations staff around exception handling, judgment calls, and relationship oversight — work the AI could not do Building confidence among staff that their expertise was being elevated, not eliminated Phased adoption that allowed teams to validate COIN's outputs against their own judgment before fully trusting the system Institutions that attempted similar AI-driven process changes without this preparation — documented extensively in McKinsey's "The Human Side of Digital Transformation" (2018) — reported compliance gaps, staff disengagement, and operational errors that eroded the projected gains within the first two quarters. The Human Element: Where Leaders Win or Lose This The JPMorgan case illustrates a truth that data cannot capture: The people who owned the old process are not obstacles. They are the most important people in the room. A loan officer or legal reviewer who has spent a decade building expertise in contract risk does not resist AI because they are change-averse. They resist because: Their professional credibility feels threatened They were not consulted — the system was, and they were not They carry institutional memory the AI has no access to — the edge cases, the client nuances, the regulatory near-misses that shaped how the process was built A leader who treats this as noise to be managed will fail. A leader who treats this as signal to be understood will succeed. What empathetic leadership looks like here: Rather than positioning COIN as a replacement, JPMorgan's more effective internal framing was: "You now have a tool that handles the routine. Your judgment handles what the tool cannot." That reframe did not just reduce resistance — it created genuine ownership. The staff became validators and improvers of the AI's output, not victims of it. This is not soft leadership. It is the most strategically effective move available. Few Transformation Principles That Anchor This Decision Kotter: A guiding coalition cannot be built by overriding experienced people. At JPMorgan, legal and operations leads had to be inside the tent — co-designing adoption, not reacting to a mandate. LSS / DMAIC: Jumping from analysis to implementation without a controlled pilot is one of the most documented causes of process improvement failure. COIN was piloted and validated before broad rollout — the Control phase only holds when people own the change. Change Saturation Principle: People absorb change at a human pace, not a data pace. Forcing the pace produces compliance without commitment — and compliance fades under pressure. Psychological Safety: If the first AI-driven change is forced and stumbles, every future recommendation walks into a room already primed to reject it. COIN worked — not just because the AI was technically superior, but because JPMorgan invested in the human system around it. The efficiency gain was real, but it was conditional on people understanding the change, trusting it, and owning their role within it. Had leadership simply mandated adoption on the strength of the data alone, the story would have been very different — and there are documented cases across financial services where that exact mistake was made, with exactly the consequences you would expect. The AI identified what to change. Leadership determined whether the change actually happened.

Prioritizing Deeper Learning and Root Cause Analysis: The Imperative for Sustainable Resolution in Wealth Management Reconciliation My Position — Deeper Learning Is Not Optional. It Is Operational Survival. I firmly believe that teams should prioritize deeper learning and root cause analysis over immediate resolution. In a domain like wealth management reconciliation — where every unresolved break carries regulatory, monetary, and reputational consequences — the cost of not learning is exponentially greater than the cost of pausing to understand. Quick fixes create the illusion of control. Deeper learning creates the reality of it. The Case Study: OMNI Reconciliation — Where AI-Powered Deeper Learning Is a Game Changer In wealth management operations, the OMNI reconciliation process is the critical control gate ensuring that positions, cash, and entitlements across custodians, fund administrators, prime brokers, and internal books of record are accurate and aligned — every single day. When breaks occur — and they do, routinely — the temptation is to clear them: force-match, manually adjust, override tolerances, and move on. The queue is cleared. The dashboard turns green. The day is "done." But the problem is not done. It is deferred. And deferred problems in wealth management don't shrink — they compound. The AI deployed in OMNI recon has the power to do far more than accelerate exception clearing. When directed toward deeper learning, it becomes a predictive, diagnostic, and preventive engine that fundamentally transforms the reconciliation function. How AI Accelerates Deeper Learning — Five Key Levers The argument that deeper learning "takes too long" collapses when AI is properly leveraged. Here are the five key levers through which AI makes root cause analysis not just feasible but faster and more powerful than traditional quick-fix cycles: 🔑 Lever 1: Pattern Recognition at Scale Human analysts see individual breaks. AI sees the architecture of failure. When corporate action breaks appear across multiple accounts, funds, or custodians, a human analyst processes them one by one. The AI correlates across thousands of records simultaneously and identifies that 87% of mandatory corporate action breaks originate from a single upstream data feed delay — a root cause no individual analyst would ever see from their queue. Impact: What would take a team weeks of manual investigation, AI surfaces in hours. 🔑 Lever 2: Temporal Pattern Analysis and Prediction AI doesn't just analyze what broke — it learns when and why things are about to break. By studying historical break patterns, the AI identifies that dividend-related reconciliation breaks spike predictably 2 business days after execution-date for specific markets (e.g., European ADRs with tax reclaim complexity). It learns that share transfer breaks cluster around month-end rebalancing windows when inter-account movements surge. Impact: The AI shifts the team from reactive break resolution to proactive break prevention — flagging risk windows before they materialize. 🔑 Lever 3: Causal Chain Mapping AI can trace a break backward through the operational chain to identify the precise point of failure — not just the symptom. For example, a position mismatch in OMNI recon may appear as a share quantity discrepancy. The AI traces the chain: Share quantity mismatch → triggered by unprocessed stock split → caused by corporate action announcement received but not elected within SLA → caused by notification routing failure in the upstream corporate actions platform → caused by a market-specific SWIFT message format that the parser misclassified This is a five-layer causal chain. Without AI, teams fix layer one (adjust the quantity). With AI-powered deeper learning, teams fix layer five (the parser logic) — and eliminate the entire class of failure permanently. Impact: One root cause fix replaces hundreds of daily manual adjustments. 🔑 Lever 4: Risk Quantification and Prioritization Not all breaks are equal. AI can score and rank breaks by regulatory, monetary, and client impact — ensuring that deeper learning efforts are directed where they matter most. The AI assesses: • Regulatory exposure: Is this break in a CASS-reportable account? Does it affect a position that feeds into regulatory capital calculations? • Monetary exposure: What is the dollar value at risk? Is this a $50 rounding difference or a $500,000 missing dividend entitlement? • Recurrence probability: Based on historical patterns, what is the likelihood this break will reappear tomorrow, next week, next quarter? • Client sensitivity: Does this affect a high-net-worth client portfolio with active reporting obligations? Impact: AI ensures the team invests deeper learning effort where the risk-adjusted return is highest — not just where the queue is longest. 🔑 Lever 5: Continuous Learning Loop (Self-Healing Reconciliation) Each resolved root cause feeds back into the AI model, making it smarter. Over time, the system builds an institutional memory of failure modes that no individual analyst — no matter how experienced — could maintain. The AI evolves from: • Detecting breaks → to Predicting breaks → to Preventing breaks → to Self-correcting before breaks enter the reconciliation queue at all. Impact: The reconciliation function transforms from a cost center processing exceptions into a strategic control function that continuously hardens operational integrity. AI-Powered Risk Prediction: When AI is oriented toward deeper learning, it doesn't just find problems — it predicts risk with a clear, actionable chain: STEP 1: DETECT AI identifies a reconciliation break in OMNI recon (e.g., position mismatch post-corporate action) STEP 2: CORRELATE AI cross-references against historical break patterns, market events, custodian behavior, and processing timelines STEP 3: DIAGNOSE AI maps the causal chain — from symptom to root cause — identifying the upstream failure point STEP 4: QUANTIFY RISK AI scores the break by regulatory exposure, monetary impact, recurrence probability, and client sensitivity STEP 5: PREDICT FORWARD AI forecasts: "Based on current patterns, 14 additional accounts will experience the same break within 48 hours unless the root cause is addressed NOW" STEP 6: RECOMMEND ACTION AI prescribes: Fix the corporate action setup logic, apply retroactive corrections to affected accounts, and update the processing rule to prevent recurrence STEP 7: LEARN AND EMBED Resolution feeds back into the AI model — this failure mode is now part of the predictive library, permanently This is not a theoretical framework. This is what AI-powered deeper learning looks like in practice — and it is faster, more accurate, and more sustainable than any quick-fix cycle. The Cost of NOT Prioritizing Deeper Learning Let me be direct about what is at stake when teams choose quick fixes over root cause analysis in wealth management reconciliation: What You Defer What You Accumulate Unresolved corporate action root causes Regulatory findings — inability to demonstrate adequate reconciliation controls under CASS, SEC 15c3-3, or MAS requirements Tolerated dividend processing mismatches Client financial loss — missing income, incorrect tax withholding, eroded trust Patched share transfer discrepancies Material position misstatements — incorrect NAV calculations, wrong client reporting, potential fiduciary breaches Repeated manual adjustments Operational fragility — a team permanently trapped in firefighting, unable to scale, unable to improve Unlearned lessons Systemic risk — the same failures recurring with increasing frequency and severity until a catastrophic event forces the learning that should have happened months ago A forced match today is a regulatory finding tomorrow. A tolerated dividend break today is a client's missing income tomorrow. A patched position mismatch today is a NAV misstatement tomorrow. In the OMNI reconciliation environment — where corporate actions, dividend processing, and share transfers generate complex, high-stakes breaks every single day — the question is not whether teams can afford to prioritize deeper learning. The question is whether they can afford not to. AI gives us the power to learn faster than ever before. The only question is whether we have the courage and discipline to use it for learning — not just for speed. I choose learning. I choose root cause. I choose the path that gets permanently better — not the one that stays permanently busy.

Firmly, the feature should not be rolled back immediately if the issue affects only a small, identifiable group of users and does not create critical harm such as security, compliance, financial loss, or data integrity problems. In this case, AI has already done something valuable: it has identified that the issue is concentrated within a known minority—around 8–10% of users, such as those on older devices or specific usage patterns—while more than 90% of users are experiencing better engagement and improved outcomes. That means the organization does not need to make a broad, disruptive rollback decision. Instead, it can take a targeted, process-excellent response: keep the feature live for the majority, isolate the issue for the affected segment, communicate proactively, and deploy a patch or fallback experience for those impacted users. From a business perspective, rolling back the feature for everyone would remove meaningful gains already being realized by the vast majority of users. It would reduce overall efficiency, delay product progress, and weaken the return on innovation investment. If the benefit is strong for 90%+ of users, and the impacted group is known and manageable, then the smarter decision is to preserve the value while correcting the edge case. This reflects disciplined product governance, not negligence. Also, this is the kind of decision mature digital organizations should make. Process excellence is not about overreacting to every issue with a full rollback. It is about using data to respond proportionately, minimizing disruption, protecting customers appropriately, and improving continuously. AI monitoring enables exactly this kind of precision: detect, segment, contain, communicate, fix, and optimize. Lets take Financial Industry Example A strong example from the financial industry is investor communication and proxy voting through a mobile experience enhanced by AI. Suppose a financial services firm launches an AI-supported mobile proxy voting feature for shareholders. The feature helps investors: receive personalized meeting information, understand agenda items more clearly, get reminders before deadlines, and complete proxy voting faster through mobile. The result is that over 90% of investors complete the process more efficiently, participation improves, and operational burden is reduced for the firm. However, AI monitoring shows that 8–10% of users, especially those on older mobile devices or using certain navigation paths, are encountering friction or errors in the voting flow. In this scenario, an immediate rollback of the mobile AI-enabled voting feature for all investors would be the wrong move if the issue is not causing compliance failure, incorrect vote capture, or security risk. Why? Because the feature is clearly delivering substantial value to the majority by making investor communication and proxy voting more efficient, timely, and accessible. The better response would be: keep the improved mobile process active for the majority, identify the affected users through AI monitoring, proactively contact that segment through email or other direct communication, provide an alternative path or temporary workaround, and release a targeted fix quickly. This approach is especially important in financial services, where the future of product delivery depends on balancing control, trust, efficiency, and innovation. If firms roll back every high-value digital improvement because a small, understood user segment has a non-critical issue, they will slow modernization and lose competitive momentum. But if they continue responsibly—with strong controls, clear communication, and targeted remediation—they create better long-term outcomes for both the business and customers. Final Position So the summary position is: Do not roll back immediately. If the issue is limited to a small, known population and does not create material risk, the right course is to continue the feature for the 90% who benefit, while using AI insights, targeted communication, and patch management to support the affected minority. This preserves business value, demonstrates process excellence, and aligns with the future direction of financial industry products, where intelligent, well-governed innovation is essential.

Profit after Tax, Return on Investment and Free cash flow all three are financial measure of a company. Any business performance are measure based on this performance. All three financial measure are depends on below three Operational Measure · Throughput ( Sales – Total Variable cost) · Investment or Inventory (I) · Operation Expense (OE)( Any monthly expense) Profit After Tax: Profit – Tax; which is: Sales – (TVC+Tax+OE) Cash Flow: Sales – TVC +∆I Based on the formula of PAT & Cash flow, Increase in throughput can improve both PAT and Cash flow for a company. But this can’t true on all cases. Some projects on through put focus on TVC while some other focus on sales. Another big trigger for cash flow is the delta on Investment. Eg. Broker firm cash flow for do new trade is based on settlement on their broker fee to book more trades. So to improve the cash flow their project will be focused on the collection or Billing process to bring the brokerage fee back to Pnl. In this cases project on improve their sales would make not help company sustain in the market. Same applicable to any small store where profit is depended on the regular cash flow.

Waterfall Chart Waterfall chart analysis is visualization progress of an Data/Values over period of time. Its sequential representation change to Starting value through variance over a period or due to change and take the final value. On other term representation of before and after through sequence change through increase and decrease. How to Construct Waterfall Chart: There are multiple analytical tool available to create the waterfall chart. We can construct in Excel. New excel version has waterfall chart. Representation of Data is key to build better chart Excel Components of Water Fall chart: Increase, Decrease and Total Data we need analyze the waterfall chart should have Start Value, Incremental change and Final value. We can also have sub total value. Eg. Gross & net. I have taken simple data of investment and Sale for Jan-May and Revenue. Net revenue is sum of month sale. We can do many subtotal based on data requirement. Insert Chart and choose excel Waterfall chart. Key point. Excel would be able identify Positive and Negative value but does not Identify Start & End. In excel terms Total. We need select the and Set as Total Investment 2000 Jan 200 feb -300 mar -600 Apr 400 May -700 Revenue 1000 Note: Excel waterfall chart has its own limitation, As mentioned it can’t identify the totals. The Colour theme cannot be a different chart. We have select from the existing theme or create one which will be applicable for all waterfall chart. The same waterfall chart can be created using a stacked Bar chart using Cumulative values. Usage in Business excellence: Waterfall chart provides better visualization of variance. analysis and ROI data. So both these are part of Business excellence. Below are areas we can use to visualize the waterfall for analysis. • Project saving through the implementation period • Process change based on the implemented solution • Any leakage or risk impact analysis • Cash flow of project

One Factor At a time (OFAT) Multiple Factor Trail & Error Method This is called Controlled Experiment. Where we keep one controlled factor and other experimental Factor varied to get best settings In Multifactor all are considered as experimental factor varied to identify the best settings Try multiple iteration based by making changes to settings based on previous failure to reach best settings Number of runs to find setting with controlled factor is less Number of runs to is high due varying factors No fixed number. Depend on learning from previous error Experimental error due another factor is less. No interaction factor. Possibility of missing optimal setting Possible of experimental error based on other factors. There is interaction factor which provide best possible setting for optimum result Prolonged experiment if more failure Since controlled experiment data setting is very vital and need to be handled with care Multi factor allows liberty on the data setting since we are varying all the factor Its based on 3 main law of experiment. · Law of readiness · Law of effect · Law of exercise There are has been many instances that OFAT & Multi factor are being preferred to identify optimal setting based on data and process, due to structured approach. Inventions are born from failures. When correcting the failure and re-trying your experiment many inventions are born, which is a very less percentage but more effective and leads to many innovations. Even though Trail and Error is not structured but it’s the approach that can bring new inventions. If the trial and error approach not been followed, we wouldn’t be in this Digital world and debating this approach..

MAGIC Criteria Book from Robert Abelson Book try to re-define the misunderstood field of statistics. P-values, z-scores, and t-tests aren’t mechanistic tools for quantifying the world. MAGIC Stand for magnitude, articulation, generality, interestingness, and credibility. Magnitude – How big is the effect?. We can tell size of an effect through various measure of effect. Bigger the effect better it is The difference between two outcomes in an experiment might seem large on its own (“effect size”) or because the intervention seemed small (“cause size”). DMAIC Component – Hypothesis test the sample set which identify the effect of cause, Cause and effect analysis Articulation – How readily can the details be summarized in to specific principle. Which is details of precision or details. In book he refer it as tick and buts. Statement- Tick , Exceptions- But. More the statement is better and less exception is better. DMAIC Component : Definition of problem statement is very important to DMAIC project, Same level important is on define the Null and Alternate Hypothesis to success of the project. Generality – How generally and widely we can apply the conclusion. Will it cover lot of cases or only few? This is specific to certain subset of population. “Take multiple approaches to answering the same question and apply the same approach in different contexts. DMAIC Component DOE, ANNOVA to try different possibility. Also scalability of solution. Even FMEA can be compared to generality to see the risk measure across population Interestingness – How important is the issue addressed. How surprising is the conclusion and how much change in behavior it does? Interesting is very hard to measure precisely, but one way is to say how different the reported effect size is from what we thought it would be DMAIC Component : Correlation test, Regression test, all this show the interestingness characteristics “Credibility- Given the method followed to gather and analyze the data. How trustable is the result based on the data. How much its contradicts with other understanding. DMAIC Component : Gage R& R test will match the credibility test of the measure criteria

RPA IPA Robotic Process Automation is computer program which perform repeated task in the process Intelligent Process Automation is software combination of AI + Machine Learning + RPA · AI-Artificial intelligence which Mimic human behaviour, which enables machine to think · Machine Learning which subset of AI, based on static tool to explore and understand about the data and provide suggest to change. Which can fall any of below 3 categories o Supervised – Need Past data o Un-Supervised – Work based on clustering/grouping based on methodology o Reinforced – Semi Supervised where limited past data is analysed and based more data rule get updated. Its program/ workflow based on rule and logic which can be repeated based on set Logic but cannot incorporated any rule change without intervention in program or workflow Its program which can perform more complex process and also which can understand change based on previous data and change the rule of the process and incorporate the changes to process on regular basis RPA need structure data to execute the rule IPA since use AI this can handle unstructured data and convert that to structure data RPA has limitation on handling multiple data format and complex rule IPA can handle the multiple data and complex rule RPA does require extensive collaboration between IT & Business team IPA need extensive collaboration to make better understanding of Data to make decision RPA is ease to use and doesn’t need deep technology skill, hence its more attractive and more process getting automated through RPA IPA is not easy and need some good understanding of technology, due to complexity IPA are not only looked based on feasibility of data Eg. Banking Break allocation tool: Which need data to taken from multiple source and formatted as per system format in spreadsheet and capture to system. Since the source file is going to same format and rule to enrichment are same this can be Automated to RPA function. But once data is capture allocation of break to different department need to done by User Eg. In case of IPA, Based on Machine learning based on previous data system can create rule to allocate the break to department. Also when there is change in Break allocation force change based on algorithm it read number time change happen take decision to change. Having mentioned IPA is more better automation option, but in term of breaking complex process in multiple task and doing RPA is much preferred. Due to ease to work and less resource and complexity and creating the rule IPA intelligence are depended on AI & Machine learning. Even some cased Deeper learning program. Which need more data to understand the behaviour of data and take the decision. Also, some cases in complex process there been issue with ML &AI based decision making when to change. Eg on above break allocation, when there is market scenario allocation pattern has changed, but will back to old allocation when scenario is over. But ML can’t change until it see substantial data to prove the theory to change.

ANOM (Analysis of Mean) : We perform hypothesis when we have more than 2 means, ANOM indicates which means from group sample from serval process are statically different from the group mean. ANOM calculates the Grand mean from all sample and measure distance from than mean to each sample mean. This distance is variation between the sample mean to overall mean ANOVA (Analysis of Variance): ANOVA compares group mean among them ANOM graphical representation is similar to the control chart, ANOM output provide the confidence interval with grand mean ANOVA can tell there is difference between the mean with each other with statistically significant, but doesn’t tell which one is the different. But ANOM address this issue, we would be able identify which one mean is defect from the group mean to address. Example: Consider we have taken a data of average run scored in Cricket stadium in India. We are analysing whether stadium is favourable to Batsman or Bowler. ( Assumption is higher mean its favours batsman) In One way ANOVA assumption we are comparing this with Delhi Feroz shah kotla. But Feroz shah kotla average is lesser than all other stadium. · Based on outcome on ANOVA analysis show other stadium are favour for batsman than Delhi stadium In cases ANOM, Assumption is grand mean is 280 and only 3 stadium is over confidence level and 2 lesser the confidence level. · Analysis would show there is 3 favour batsman & 2 favour Blower and other are neutral. Which is better outcome than ANOVA. ANOM provide better analysis than ANOVA and indicate the area of defect. Based on study shows that ANOM provide more information particularly when we accept alternate hypothesis. ANOVA better result when null hypothesis is accepted.

Lindley’s Paradox concern the situation when comparing Null & Alternate Hypothesis test results in significant leading reject the null hypothesis The example follows a binomial where a survey of people who feel positive about the government. We have taken null hypothesis Ho= 0.5 and Alternate as Ha Not equal 0.5. We absorbed 20K cases and 9.8K was mentioned as positive. In this case, P value is 0.047, if we 95% significance level and the null hypothesis are rejected. Lindley’s paradox can happen • Sample size is large • Ho is precise • Ha is not strong opposite or relatively diffuse or not one-sided Multiple ways to address the false positive in the sampling. • In above example sample set is not clear whether we need gender segregation will take the survey. We need to take samples which address the true population. • Take a sub-sample from each sector to get a better true population • When handling a large sample, the null hypothesis not be precise but rather more projected • Alternate Hypothesis should have strong contract opposition which should be one side.

Bayesian Vs Frequentist main difference of both thought process is reasoning of probability Bayesian Frequentist Bayesian thinking see the probability based on their certainty and uncertainty of trail. It’s based on belief of an event based on prior information Frequentist thinking see the probability based on frequencies of the repeated trail P Value based on the probability of the hypothesis. Which is inverse of Frequentist P value is probability of more extreme data with the assumption that null hypothesis is true Hypothesis is based on no variation in the data but the variation in the Model/Parameter Hypothesis is based on Variation of the data and their derived quality based on the repeated measurement with fixed Model/parameter Assuming 95% of true value of a model lies with in credibility region 95% of cases confident interval will have true value of the model Varying True value and Fixed credible region Varying confidence interval and fixed true value Process to understand possibility that Hypothesis it true based on observed result Process to understand how extreme the observed result under the Hypothesis Example: Playing Card with friend which has 52 card and Friend drawn a card and seeing card in hand asking possibility of card in his hand is Diamond card, On Bayesian way of thinking possibility of getting Diamond is out 13 out of 52 cards which is 25% its Diamond Example: Since the card has been drawn and the result is known its either Diamond or others, so this can be either 0 or 1 Bayesian way of thinking is preferred in term of clinical trails based which take more result change based on prior data and new state. Also, current AI model use more Bayesian theorem to learn based on prior data and change the result. Which allow to correct Bais and Noise level based on prior data to correct make it more accurate. But in uncertain case when there is no prior data (non-informative prior) consider all data are equally likely which create a Bias hypothesis in given data will not be always correct.

Advantages Of using AHP over Pugh Matrix Ø Pugh Matrix need Baseline (Datum) to compare with other alternative and AHP doesn’t require Datum Ø AHP can provide a comparison between each alternate for decision and Pugh only compares alternate with Datum, which does provide a full landscape to make a decision Ø Criteria weightage is an estimate in Pugh Matrix based on input from VOC or from survey. AHP arrive weightage can be arrived same calculation using the pairing method Ø Pugh Matrix is discrete data for comparison and AHP uses both Discrete and continuous data for comparison, so precision is better in decision making AHP has better advantage on comparing the alternate for decision making and will best choice for strategic decision making for critical solution, It has its own de-merit due to paring & scale. Scale allows only 1-9 and user can’t choose in-between value in some which is cases in muti attribute which has minor difference. Also user provide scale of 1-9 and person ranking need to consider the distance between attribute to be consistent, else CI will be higher and will be difficult make people understand make this correct. AHP need multiple calculation and data point to get required result arrive consistent ratio & index to perform comparison. Some time this become difficult for some simple selection. In such cases Pugh Matrix can be preferred. When there is criteria provide more of person experience considered as rating and rational is not important, in such cases Pugh Matrix is preferred than AHP

A project book of knowledge creates multiple documentation based on a project based on stakeholders and requirements. Some of the commonly used artifacts are Strategic Documents- This is initial documentation of a project has vision and mission-related documents from Charter to baseline Registers & Log : These documents are important for a Project manager to track all progress and changes of the project. Communication Plan: Some Project store Management plan a separate track, but widely used on the ground is a communication plan, to track the availability of each stakeholder and establish constant communication Hierarchical Diagram: This break the structure from top to bottom related to project from Project, Risk, Organisation, Product etc SOW or Agreement and Contract: Where all project contractual document Dashboard & Reports: It has all project reports and a Dashboard Based on the project artifact is further broken down further from the above broad category to have Product release, Baseline, Cost plan etc. DMAIC can be a subset of Project Management to accelerate a project or improve quality scores, so artifacts from PMBOK are part of DMAIC. Project management and DMAIC the define phase have a very similar approach to defining. Project charter, team charter and project road map, Voice of the customer, Project goal. These some similar available in the Strategy artifacts Baseline, Requirement document, and Risk log can be part of the Measure phase, Any risk management artifice can also be used in Analyse & Improve phase. All tracking Artifacts like RACI and issue logs will also be part of the Control phase. Tollgate review on all phases of DMAIC is followed by all project management in communication plan artifacts.