MODULE 1: INTRODUCTION MODULE 5: BASIC DATA MODULE 8: BASIC REGRESSION MODULE 10: ADVANCED REGRESSION

L1.1: Introduction to analytics PREPARATION L 8.1Introduction to regression L 10.1: Introduction to CART

modeling L 5.1: Introduction to data L 8.2: Estimating model quality with L 10.2: Branching
L1.2: Introduction to the course preparation maximum likelihood and L 10.3: Random forests
L1.3: What is modeling? L 5.2: Outlier detection information criteria L 10.4: Logistic regression
L 5.3: Dealing with outliers
MODULE 2: CLASSIFICATION L 8.3: Using regression L 10.5: Confusion matrices
L 2.1: Introduction to classification
MODULE 6: CHANGE DETECTION L 8.4: Causation vs. correlation L 10.6: Situationally-driven comparison
L 2.2: Choosing a classifier L 6.1: Introduction to change L 8.5: Transformations and L 10.7: Advanced topics in regression
detection interactions
L 2.3: Data definitions HOMEWORK 7
L 6.2: CUSUM for change detection L 8.6: Regression output
L 2.4: Support vector machines (SVM)
L 2.5: SVM: What the name means HOMEWORK 3 HOMEWORK 5
L 2.6: Advanced SVM L 6.3: Change-detection homework
L 2.7: Scaling and standardization MIDTERM EXAM
followup
L 2.8: K-nearest neighbor classification
HOMEWORK 1

WEEK 01 02 03 04 05 06 07 08

Knowledge-Building:
MODULE 3: VALIDATION MODULE 11: VARIABLE SELECTION
Analytics Models L 3.1: Introduction to validation L 11.1: Introduction to variable
Knowledge-Building: L 3.2: Validation and test data sets selection
Cross-Cutting Concepts L 3.3: Splitting data L 11.2: Models for variable selection
Experience-Building L 3.4: Cross-validation L 11.3: Choosing a variable selection
MODULE 7: EXPONENTIAL MODULE 9: ADVANCED DATA
MODULE 4: CLUSTERING PREPARATION
model
SMOOTHING
L 4.1: Introduction to clustering HOMEWORK 8
L 7.1: Introduction to exponential L 9.1: Box-Cox transformations
L 4.2: Distance norms L 9.2: De-trending
smoothing
L 4.3: K-means clustering L 9.3: Introduction to Principal
L 7.2: Trends and cyclic effects
L 4.4: Practical details for k-means Component Analysis
L 7.3: Exponential smoothing: what
L 4.5: Clustering for prediction L 9.4: Using pricipal component
the name means
L 4.6: Supervised vs. unsupervised analysis
L 7.5: ARIMA
learning L 9.5: Eigenvalues and eigenvectors
L 7.6: GARCH
HOMEWORK 2
HOMEWORK 4 HOMEWORK 6
 MODULE 12: DESIGN OF EXPERIENCE MODULE 17: CASE FORMAT MODULE 20: MONETIZATION CASE
L 12.1: Introduction to Design of L 17.1: A format for discussion L 20.1: Introduction ro monetization case
Experiments L 20.2: Sample models
L 12.2: A/B Testing MODULE 18: POWER COMPANY L 20.3: Matching across data sets
L 12.3: Factorial designs CASE
L 12.4: Multi-armed bandits HOMEWORK 15
L 18.1: Introduction to power company
MODULE 13: PROBABILITY-BASED case
MODELS SPRING BREAK L 18.2: Models for customer identification
L 13.1: Introduction ro advanced
L 18.3: Models for cost estimation
probability distributions
L 13.2: Bernoulli, binomial, and L 18.4: Models for shutoff selection
geometric distributions HOMEWORK 13
L 13.3: Poisson, exponential, and
Weibull distributions
L 13.4: Q-Q plots
L 13.5: Queuing
L 13.6: Simulation basics
L 13.7: Prescriptive simulation
L 13.8: Markov chains
HOMEWORK 9

FINAL EXAM
WEEK 09
01 10 11 12 13 14 15 16 Thursday of Week 16 through
Thursday of Week 17

/2SWLPL]DWLRQIRUVWDWLVWLFDO
Knowledge-Building: PRGHOV
Analytics Models MODULE 14: MISSING DATA /&ODVVLƉFDWLRQRIRSWLPL]DWLRQ
Knowledge-Building: PRGHOV
L 14.1: Introduction to missing
/6WRFKDVWLFRSWLPL]DWLRQ
Cross-Cutting Concepts data
/%DVLFVRIRSWLPL]DWLRQ
Experience-Building L 14.2: Methods that don’t require
DOJRULWKPV
imputation
L 14.3: Imputation methods MODULE 16: ADVANCED MODELS
L 16.1: Non-parametric methods
MODULE 15: OPTIMIZATION
L 16.2: Bayesian modeling
L 15.1: Introduction to optimization
L 16.3: Communities in graphs MODULE 19: RETAILER CASE MODULE 21: COURSE SUMMARY
L 15.2: Elements of optimization
models L 16.4: Neural networks and deep L 19.1: Introduction to retailer case L 21.1: Many analysts, one dataset
L 15.30RGHOLQJLVDQDUWWZR learning
L 19.2: Testing the hypotheses L 21.2: Course summary
H[DPSOHV L 16.5: Competitive models
L 19.3: Using a new data source COURSE PROJECT DUE
/0RGHOLQJZLWKELQDU\YDULDEOHV L 16.5a: Competitive model demo
L 19.4: Making recommendations (Peer-graded)
HOMEWORK 10 HOMEWORK 12
HOMEWORK 14
COURSE PROJECT ASSIGNED
MIDTERM EXAM