Business Analytics with Python Bootcamp

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Week 1: Business Analytics Fundamentals

Kick-off (15 minutes)

• Presentation: Course overview, goals, structure, and road map
• Group discussion: What’s your background?
• Q&A

Business analytics fundamentals (100 minutes)

• Presentation: Introduction to measuring business performance; main types of end-to-end processes in corporations—record-to-report (R2R), order-to-cash (O2C), source-to-pay (S2P), and hire-to-retire (H2R); creating value with data—from information to knowledge to decisions; framing business problems as data problems; writing effective problem statements; breaking down problems with issue trees
• Hands-on exercises: Create an issue tree; create a value driver tree
• Presentation: KPIs and performance metrics; identifying value drivers in business with value trees; measuring business success with KPIs; strategic versus operational KPIs; KPI review process
• Q&A
• Break

Hands-on business analytics: (90 minutes)

• Presentation: Business analytics tool stack; data sources and access; spreadsheet software; scripting languages; no-code tools; comparing tools and when to choose which; getting started with Python for data analysis
• Jupyter notebook: Explore a dataset with Excel, then with Python
• Q&A
• Break

Wrap-up (5 minutes)

• Presentation: Outlook for next week

Week 2: Data Analysis with Python Fundamentals

Getting started with Python (90 minutes)

• Presentation: What is Python?; why it’s so popular; Python success stories; Python ecosystem; popular packages for data analysis; working with Python—notebooks versus script files; Jupyter Notebook versus VSCode
• Hands-on exercises: Install Anaconda and Jupyter Notebook and print Hello World
• Q&A
• Break

Essential coding best practices (60 minutes)

• Presentation: Essential coding best practices; versioning; commenting; clean code; modularization and functions
• Jupyter notebook: Build your first repo ()
• Q&A
• Break

Running your code (60 minutes)

• Presentation: Running Python code; organizing your code files; running scripts from the command line
• Interactive lab: Work with VSCode and the command line
• Q&A

Week 3: Descriptive Business Analytics with Python

Introduction to descriptive analytics (30 minutes)

• Presentation: Purpose of descriptive analytics; introduction to exploratory data analysis (EDA); data modeling (tidy data for data analysis)
• Q&A

Data wrangling with Python (60 minutes)

• Presentation: Loading data; SQL; transforming data; writing data
• Jupyter notebook: Load and transform data with Python ()
• Q&A
• Break

Descriptive statistics (60 minutes)

• Presentation: Descriptive versus inferential statistics; summary statistics ; Anscombe's quartet; descriptive statistics in Python
• Jupyter notebook: Explore descriptive statistics with Python
• Q&A
• Break

Data visualizations (60 minutes)

• Presentation: Visualization techniques; exploratory versus explanatory plots; visualizing one-, two-, and three-dimensional data; visualization frameworks in Python
• Jupyter notebook: Explore data visualization in Python
• Q&A

Week 4: Diagnostic Business Analytics with Python

Introduction to diagnostic analytics (30 minutes)

• Presentation: Essential techniques; correlation versus causation; five whys and root-cause analysis
• Q&A

Rule mining (60 minutes)

• Presentation: Rule mining techniques; association rules; market basket analysis; support, confidence, and lift
• Interactive lab: Perform a Market Basket Analysis
• Break

Segmentation (60 minutes)

• Presentation: Introduction to segmentation techniques; purpose of segmentation and use cases; RFM analysis
• Interactive lab: Calculate RFM Values
• Q&A
• Break

Clustering (60 minutes)

• Presentation: Types of clustering techniques; when to use which technique; K-means clustering; hierarchical clustering
• Interactive labs: Develop and Interpret a Hierarchical Clustering; Develop and Interpret a K-Means
• Clustering
• Q&A

Week 5: Predictive Business Analytics with Python

Inferential statistics (60 minutes)

• Presentation: Working with data under uncertainty; introduction to inferential statistics; regression modeling
• Interactive labs: Using Scikit-Learn; Calculating the Squared Error; Simple Linear Regression; Gradient Descent; Correlation Coefficient; Statistical Significance
• Q&A
• Break

Machine learning (60 minutes)

• Presentation: Introduction to machine learning; ML versus inferential statistics; types of machine learning; ML algorithms; decision trees
• Interactive labs: Import Packages and Data; Prepare Data for Train-Test Splits; Predict Numeric Values with Multiple Linear Regression
• Q&A
• Break

Model performance (60 minutes)

• Presentation: Evaluating machine learning models; bias versus variance trade-off; performance metrics; confusion matrix; AUC, ROCR2, and RMSE
• Interactive labs: Predict Categorical Values with Tree-Based Models; Calculate and Interpret Predictive Model Performance
• Q&A
• Break

Time series forecasting (30 minutes)

• Presentation: Introduction to time series forecasting; trends, seasonality, and randomness; (S)ARIMA models
• Interactive lab: Forecast Time Series with ARIMA Models
• Q&A

Week 6: Prescriptive Business Analytics with Python

Introduction to prescriptive analytics (60 minutes)

• Presentation: What is prescriptive analytics?; automated versus manual decision-making; recommender systems; reinforcement learning; deep learning
• Q&A
• Break

Hands-on recommendation services (45 minutes)

• Interactive labs: Define and Understand a Reinforcement Learning Environment; Set Up Simulated User Interactions; Build a Contextual Bandit Using RLlib; Train a Deep Neural Network with SlateQ
• Q&A
• Break

AI for analytics (90 minutes)

• Presentation: AI services; computer vision; natural language processing; automated machine learning (AutoML); AI for BI value framework; use cases for AI in business analytics
• Interactive lab: AutoML with Azure
• Q&A
• Break

Wrap-up and Q&A (15 minutes)