Certified Lean Six Sigma Black Belt (AI-Powered)

Define the problem, set scope and boundaries, and draft a project charter while capturing the voice of the customer, stakeholder insights, and key customer expectations.

Select lean six sigma projects aligned with the organization's strategic goals, focusing on issues with the biggest impact while considering feasibility, data availability, and problem clarity.

Apply the impact versus effort matrix to select Six Sigma projects by rating each on impact and effort, prioritizing quick wins and major projects while avoiding low-impact efforts.

Use ai-powered brainstorming to identify Six Sigma black belt projects and a define-phase GPT to generate hospital improvement ideas. Build impact-effort matrices with ChatGPT and produce downloadable csvs and plots.

Define the problem with a specific, measurable, objective, and time-bound statement, avoiding vague scope and premature causes, supported by data to prepare the project charter.

Define a project charter as a blueprint, alignment tool, and authorization for a Six Sigma project, outlining problem statement, goals, scope, timeline, team, stakeholders, business case, and foundation of DMAC.

Draft a project charter for reducing ER waiting time with a customized AI-powered GPT, outlining problem statement, scope, timeline, and stakeholder analysis.

Explore stakeholder analysis for Six Sigma projects by identifying internal and external stakeholders, mapping their power and interest, and tailoring engagement strategies to four influence and interest categories.

Use ChatGPT to perform stakeholder analysis from a project charter, rating influence and interest, and generate a stakeholder map with four quadrants and engagement strategies.

Learn to listen to the voice of the customer (VoC) to align Lean Six Sigma projects with what customers value, using surveys, interviews, focus groups, and feedback data.

Analyze voice of customer by combining social media reviews and support logs with chatgpt to derive sentiment, themes, and key issues, and measure average ratings and resolution rate.

Define and compute net promoter score (nps) and csat from the voice of the customer, distinguishing long-term experience from immediate satisfaction and classifying promoters, detractors, and passives.

Leverage ChatGPT to analyze NPS and CSAT data, identify promoters, detractors, and regions, diagnose product-specific issues from customer comments, and explore CSAT distribution to improve the voice of the customer.

Translate the voice of the customer into measurable CTQ characteristics by mapping topics to drivers and targets, validate feasibility, and build a CBTC tree to align processes with customer needs.

Show how a customized GPT turns the voice of the customer into a CTQ tree for drone reliability, defining CTQs like stable flight, gyroscope accuracy, durability, and CSV/PNG outputs.

Apply Kano analysis to classify customer requirements into must-be, performance, attractive, neutral, and reverse attributes, prioritizing actions that boost satisfaction from voice of customer data and paired questions.

Explore Kano survey analysis to classify features as must-be, attractive, one-dimensional, or reverse using functional and dysfunctional questions, and compute satisfaction and dissatisfaction indices with ChatGPT automating the process.

Demonstrates Kano analysis of a drone survey using ChatGPT to summarize, normalize responses, classify features, and generate a Kano report, highlighting battery life as performance and most features as indifferent.

Explore the define phase with the project charter and voice of the customer, then map processes using sipoc to identify suppliers, inputs, process steps, outputs, and customers.

Learn to build sipoc diagrams with ChatGPT for coffee making and bottling, detailing suppliers, inputs, process steps, outputs, and customers.

Learn to build flowcharts with diagrams.net as a workaround for ChatGPT limitations, outlining start points, steps, decisions, export options, and value stream map concepts.

Learn value stream mapping and process visualization, detailing SIPOC, material and information flow, and value added versus non value added times, with AI-assisted outputs and a hospital example.

Create a basic minimum value stream map showing activity, cycle time and waiting time with Excel data, illustrated by a hospital emergency department process.

Build on the define phase by collecting accurate data in the measure phase to establish a reliable baseline. Plan data collection and apply measurement system analysis.

Link the data collection plan to the defined phase and ctqs to establish a baseline by collecting structured output and input/process matrix data with clear operational definitions and sampling.

design a data collection plan for the measure phase, detailing operational definitions, data sources, collection methods, frequency, and ownership, with examples like order cycle time and on-time delivery.

Learn to build a data collection plan for a Six Sigma project using ChatGPT, detailing arrival-to-triage times, EHR timestamps, automatic collection, and sampling rules for the measure phase.

Learn to distinguish true piece variation from measurement variation using measurement system analysis, including gauge R&R and attribute agreement analysis, to ensure accuracy, precision, and reliable readings.

Explore the difference between accuracy and precision in measurement system analysis, with accuracy as closeness to the true value and precision as consistency across repeated measurements.

Assess measurement accuracy with bias, linearity, and stability, and evaluate precision through repeatability and reproducibility, culminating in gauge R&R and type one gauge studies.

explore type i gauge study to assess measurement accuracy and precision using one operator, calibrated instruments, random readings, and comparison to a reference value with run chart analysis.

Explore type I gauge study using ChatGPT to analyze coating thickness data, assess accuracy and precision with reference value and tolerance, and interpret bias, p value, and run charts.

Study gauge R and R analysis to quantify part-to-part variation and measurement system variation, using cross study ANOVA to separate repeatability, reproducibility, and operator–part interaction across operators and parts.

Interpret the results of a crossed gauge R&R study using ANOVA to assess part-to-part variation and operator variability, noting non-significant part-to-operator interaction and repeatability, reproducibility, and gauge R&R metrics.

Learn to run a cross gauge R&R study with three operators and ten parts using ChatGPT to produce ANOVA tables, plots, and variance components.

Explore root cause analysis in analyze phase using five whys and fishbone diagrams, validating causes with data via hypothesis testing, correlation, regression, AI, and capability measures CP, CPK, PP, PPK.

Explore root cause analysis with five whys and Ishikawa diagrams, noting their subjective nature and how data validation and later hypothesis testing, regression analysis, and capability studies follow.

Use the ChatGPT-powered analyze phase GPT to perform the five why analysis for long waiting times in the emergency department. Identify root causes and generate actionable corrective actions.

Explore root cause analysis with the fishbone diagram, handling multiple y's in complex issues by mapping six M's (machine, method, measurement, people, environment) to explore and analyze all causes.

Build a fishbone diagram for patient waiting times using ai-powered lean six sigma and six M categories, with ChatGPT guiding problem definition, causes, and actionable recommendations.

Explore descriptive statistics to summarize and analyze data, including mean, median, mode, range, variance, standard deviation, skewness, kurtosis, and normal distribution, with practical interpretation.

Explore descriptive statistics of 200 patients' waiting times with central tendency, dispersion, and shape measures—mean, standard deviation, quartiles, skewness, and kurtosis—via ChatGPT, with interpretation and table formats.

Visualize data to reveal insights hidden in descriptive statistics, exploring histogram and box-and-whisker plots to assess distribution, skewness, outliers, and the interquartile range.

demonstrates creating histograms and box-and-whisker plots with chatgpt, adjusting bin size, color, and mean/median lines, and generating department-wise charts, while covering binomial, poisson, and normal distributions.

Explore probability distributions, including binomial, Poisson, and normal, and see how modeling a process estimates event chances with ChatGPT-based calculations.

Explore the binomial distribution for discrete two-outcome data, using trials, successes, and the probability of success, with independent trials; apply PMF and CDF to defects, missed doses, and surveys.

Explore binomial distribution problems using ChatGPT in a Lean Six Sigma Black Belt context, comparing general ChatGPT with a specialized analyze phase GPT, and visualizing the probabilities of missed doses.

Explore the Poisson distribution for discrete counts of events in a fixed interval, using lambda as the mean, and apply probability mass function and cumulative distribution function to hospital arrivals.

In this Poisson distribution demo for Six Sigma Black Belt, ChatGPT generates a PMF and CDF plot for ambulance arrivals, highlighting an eight-ambulance alert and probabilities around four or seven.

Explore the normal distribution, defined by mean and standard deviation, and learn its continuous data applications, bell-shaped curve, and how pdf, cdf, and the standard normal distribution underpin quality tools.

Standardize any normal distribution to standard normal with mean zero and std dev one using z value, and apply it to blood test times (30, sd 5) to compute probabilities.

Explore normal distributions with blood-test timing, plots, tail probabilities, and comparisons across normal, binomial, and Poisson models used in quality management.

Assess data normality using graphical tools (histograms, QQ plots) and statistical tests (Shapiro-Wilk, Anderson-Darling, Kolmogorov-Smirnov) with a 0.05 p-value rule.

Assess normality with a customized lean six sigma black belt GPT, comparing lab test time (normal) and pizza delivery time (non-normal) using Anderson-Darling, Shapiro-Wilk, p-values, and qq plots.

Explore hypothesis testing in the analyze phase of six sigma by formulating null and alternate hypotheses, choosing significance levels, and interpreting p-values to distinguish type I and II errors.

Learn hypothesis testing concepts: null and alternate hypotheses, the significance level alpha, and the trade-off between type I and type II errors, with p-values guiding the decision.

State null and alternate hypotheses, set the significance level, choose the test (one-sample, two-sample, ANOVA), collect data, and use the p-value to reject or fail to reject the null.

Explore the intuition behind one sample z test for hypothesis testing, using a 25 mm shaft example to compare a sample mean against the population mean under normal distribution.

Use the one sample z test to compare a sample mean to a target, with known sigma or large samples, form null and alternative hypotheses, and interpret the p-value.

This lecture shows performing a two-sided one-sample z test using ChatGPT, with mean 25.12, n=40, known sigma, to test against 25 mm, leading to rejection and conclusion of deviation.

Learn how to perform a two-sample z test to compare two independent groups with known standard deviations, including hypotheses, z value calculation, and a ChatGPT-assisted shaft diameter example.

Apply a two-sample z test with known population standard deviation using chatgpt, compare machine one and two shaft diameters, and conclude a significant difference with a small p-value.

Explore the three types of t tests: one-sample, two-sample, and paired, and how unknown population standard deviation and small samples shift the student’s t distribution, unlike z tests.

Demonstrates a one-sample t test to see if mean ticket resolution time differs from five hours using 20 tickets, with raw data, sample standard deviation, and p-value interpretation.

Demonstrate a two-sample t test to compare means of two independent departments with unknown population standard deviations and small samples, concluding no significant productivity difference.

Explore paired t tests with data from 30 patients before and after medication to determine whether the medicine lowers systolic pressure, using a one‑sided hypothesis and p‑value evidence.

Explore one proportion and two proportions tests for binary outcomes, using z tests and approximation of binomial distributions, with np ≥ 5 and n(1-p) ≥ 5, and exact binomial tests.

Apply a ChatGPT-driven one proportion z test to defect data, summarize the dataset, and determine if the 2.2% rate is significantly different from 2%.

Compare ticket submission rates for Group A and Group B with a two-proportions z test, showing no significant difference (p>0.05) and noting normal approximation and the exact test option.

Explore one- and two-variance tests to assess process variability using chi-square and F distributions, with Lean Six Sigma insights on p-values, Levene's non-parametric option, and practical examples.

Evaluates a one variance test on film thickness data to determine if the standard deviation exceeds 1.5 microns using a chi-square test, with a 95% CI of 1.92–3.23 microns.

Demonstrates a two-variance test between machine A and machine B using an f test with normality checks, alpha 0.05, and a p-value below 0.05, leading to rejecting equal variances.

Learn how one-way ANOVA compares means across three or more groups, identifies if a difference exists, uses Tukey's HSD for post hoc analysis, with normality and equal variance assumptions.

Demonstrate a one-way ANOVA on delivery times for east, west, central warehouses, with p-values and Tukey's HSD showing central differs from east and west, while east and west do not.

Explore how correlation measures the strength of relationships between inputs and outputs. Learn how regression models predict outcomes by estimating house prices from inputs like house size.

Use scatter plots to explore how house area relates to price, identify linearity, outliers, and clusters, and note that Pearson correlation will be covered next.

Demonstrate creating a scatter plot of house price versus area with ChatGPT, using a Kaggle housing dataset and housing.csv, including data upload and axis instructions.

Investigate how the Pearson correlation coefficient measures strength and direction of relationships, using scatter plots, correlation matrices, heat maps, and pair plots with examples like price versus size.

Learn to compute and interpret the correlation coefficient with ChatGPT, build a correlation matrix and heat map for multiple variables, and use pair plots to prepare regression-focused data exploration.

Explore simple linear regression to predict house price from area, derive the regression equation, assess residuals and assumptions (normality, constant variance, independence) with interpretation.

Demonstrate regression analysis using chatgpt to model house price from area with a scatter plot, r-squared ~0.29, p<0.001, and explore confidence and prediction intervals for 8000 ft².

Explore how regression lines estimate house prices from size and distinguish prediction and confidence intervals, illustrating why individual prices yield wider prediction intervals than the mean, with 95% bounds.

Draw confidence and prediction intervals on a house price versus area scatterplot. Compute the 8000 ft² house price using simple linear regression and compare mean and individual price ranges.

Explore process capability within six sigma by measuring output against specifications using Cp, Cpk, Pp, and Ppk, considering short-term and long-term variation and process centering.

Demonstrate process capability analysis for ball bearing diameters using CP, CPK, PP, PPK and CPM with 25 subgroups of four, targeting 20 mm within 19.9–20.1.

Demonstrate process capability analysis using ball bearing diameter data and two data sets. Interpret CP and CPK values to assess process capability and highlight potential discrepancies between plots and text.

This lecture introduces the improve phase of Lean Six Sigma, moving from analysis to action through conventional, scamper, and trees brainstorming, prioritization, pilot project, change management, and design of experiments.

Emphasize quantity over quality within a six sigma team, conventional brainstorming encourages idea generation without criticism and notes ideas for analysis, with rotation and scamper to think outside the box.

Use the scamper framework to drive structured brainstorming for action ideas with ChatGPT, applying substitute, combine, adapt, modify, magnify, put to other use, eliminate, and rearrange.

Demonstrate ChatGPT-driven, structured brainstorming using the scamper framework within a Six Sigma project. Target ER waiting times to 30 minutes while addressing voice of customer concerns like privacy and communication.

Learn TRIZ, a contradiction-solving method with 40 inventive principles, featuring segmentation, prior actions, and other way round, illustrated via knife safety, airplanes, and SMED, for Six Sigma projects.

Utilize TRIZ principles with ChatGPT to generate actions reducing triage waiting time. Suggestions include segmentation, prior action, space redesign, vertical boards, dynamic staffing, and local quality, grouped for prioritization.

Prioritize actions using an impact and effort matrix, ranking ideas on a 1–9 scale to classify them as quick wins, major projects, or thankless tasks.

Use ChatGPT to visualize an effort and impact matrix, craft titles for improvement ideas, identify quick wins, and prepare a business case for management approval.

Create a compelling business case for a selected solution by weighing costs, benefits, and risks, and evaluating financial viability via return on investment and other metrics.

ChatGPT demonstrates calculating net present value and internal rate of return for management decisions, and brainstorms costs and benefits of adding a nurse before triage, including direct and indirect costs.

Design a limited pilot project for a proposed scheduling system in an outpatient department, track waiting time and patient satisfaction, collect data, set KPIs and baselines, and decide on expansion.

Plan a pilot test for an electronic scheduling system in this ChatGPT demo, using ChatGPT as a brainstorming partner to define objectives, scope, timeline, gantt chart, metrics, and risk mitigation.

Explore how change management bridges process changes to behavior change, ensuring stakeholder buy-in, effective communication, training, incentives, and accountability for sustainable project success.

Learn design of experiments as extension of correlation and regression, using a cake example to show how temperature, time, and eggs affect fluffiness, with factors, levels, runs, responses, and interactions.

Explore full factorial design in experiments with three factors - temperature, time, and eggs - each at two levels, replicated for reliability, and analyze main effects and interactions on fluffiness.

this lecture demonstrates planning and setting up a three-factor, two-level design of experiments using ChatGPT, including 3 replicates, randomized run order, and conditions, with fluffiness measured on a 1–5 scale.

Analyze a design of experiment data to show how eggs, temperature, and time influence cake fluffiness using anova, interaction plots, and regression; identify the combination: 4 eggs, 25 minutes, 180°C.

Master the control phase of a Dmac Six Sigma project by building a control plan and control charts, standardizing processes, enforcing accountability, and leveraging SOPs to sustain improvements.

Define and apply a control plan to monitor critical steps, specify outputs and measurement methods, and set frequency, criteria, and reaction plans using shaft grinding and first-call response examples.

Create a Six Sigma control plan using ChatGPT, detailing goals, processes to control, scope, and measurement, including pre-trials, registration, triage, waiting time, and reaction plans.

Monitor process stability with control charts, distinguish common and special causes, and apply charts such as x-bar, r, s, imr, p, np, c, and u, guided by Nelson rules.

Explore IMR charts for waiting-time data, apply Nelson rules to assess control, and preview x-bar r and u charts for defects.

Update standard operating procedures, train staff, and document lessons learned in a repository to sustain improvements and maximize the ROI of your Six Sigma project.

Close out lean six sigma project with a final report detailing improvements and lessons, update the standard operating procedure, train stakeholders, and validate the new system with control charts.