Lectures

You can download the lectures here. We will try to upload lectures prior to their corresponding classes.

• 

  Lecture 1 - Course Introduction
  tl;dr: Course introduction.
  [slides] [recording]
  
• 

  Lecture 2 - Data challenges
  tl;dr: Common challenges in data collection.
  [slides] [recording]
  

  Suggested Readings:

  • Lessons from measurement [only need to read measurement section]
  • When You Hear the Margin of Error Is Plus or Minus 3 Percent, Think 7 Instead
• 

  Lecture 3 - Survey weighting
  tl;dr: Weighting techniques to counter selection biases.
  [slides] [recording]
  

  Suggested Readings:

  • Pew - comparing weighting techniques
  • High-frequency polling with non-representative data
  • We Gave Four Good Pollsters the Same Raw Data. They Had Four Different Results.
  • How One 19-Year-Old Illinois Man Is Distorting National Polling Averages
• 

  Lecture 4 - Other aspects of data collection
  tl;dr: Uncertainty quantification with selection on unknown covariates, ratings & recommendations, and miscellaneous data collection topics
  [slides] [recording]
  

  Optional Readings:

  • Designing Informative Rating Systems: Evidence from an Online Labor Market
  • Reputation Inflation
• 

  Lecture 5 - Recommendations introduction
  tl;dr: Introduction to Recommendations, including data challenges and collaborative filtering
  [slides] [recording]
  

  Suggested Readings:

  • Mining Massive Datasets, Ch 9, Recommendations
  • Stitchfix Algorithms tour
• 

  Guest 1 - Dhrumil Mehta Guest Lecture
  tl;dr: Dhrumil Mehta (Columbia and http://fivethirtyeight.com/).
  
  

  Suggested Preparation:

  • What makes a good pollster?
• 

  Lecture 6 - Recommendations, from predictions to decisions
  tl;dr: From predicting ratings to making decisions: capacity constraints and multi-sided recommendations
  [slides] [recording]
  
• 

  Guest 2 - Amy Zhang Guest Lecture
  tl;dr: Amy Zhang (Cornell ORIE).
  
  
• 

  Lecture 7 - Recommendations, from predictions to decisions Part 2
  tl;dr: From predicting ratings to making decisions: capacity constraints and multi-sided recommendations
  [slides] [recording]
  

  Suggested Readings:

  • The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify
  • Algorithmic Effects on the Diversity of Consumption on Spotify
• 

  Lecture 8 - Algorithmic Pricing basics
  tl;dr: Introduction to algorithmic Pricing
  [slides] [recording]
  
• 

  Lecture 9 - Algorithmic Pricing complications
  tl;dr: Algorithmic pricing: capacity, price differentiation, and competition
  [slides] [recording]
  

  Suggested Readings:

  • The Algorithm behind Plane Ticket Prices and How to Get the Best Deal
  • Book chapter on Dynamic Programming

  Notes:

  • Dynamic Programming for Pricing
• 

  Lecture 10 - Algorithmic Pricing complications 2
  tl;dr: Algorithmic pricing: capacity, price differentiation, and competition
  [slides] [recording]
  
• 

  In class discussion - Ethics in (Algorithmic) Pricing
  tl;dr: What makes a pricing decision unfair?
  [Pre-class Survey] [slides]
  

  Suggested Readings:

  • Fairness as a Constraint on Profit Seeking: Entitlements in the Market
• 

  Lecture 11 - Algorithmic Pricing practice -- ride-hailing
  tl;dr: Algorithmic pricing: ride-hailing case study
  [slides] [recording]
  
• 

  Lecture 12 - Experimentation -- Introduction
  tl;dr: Introduction to experimentation
  [slides] [recording]
  

  Suggested Readings:

  • Controlled experiments on the web: survey and practical guide
  • A/B testing: A step-by-step guide in Python
  • The Power of Experiments: Decision Making in a Data-Driven World
• 

  Guest 3 - Hannah Li Guest Lecture
  tl;dr: Hannah Li (Stanford).
  
  
• 

  Lecture 13 - Experimentation -- Peeking and Interference
  tl;dr: Experimentation challenges in online marketplaces: peeking and interference
  [slides] [recording]
  

  Suggested Readings:

  • Lyft – experimentation in marketplaces (Part 1), (Part 2), (Part 3)
  • Toward Causal Inference With Interference
• 

  Lecture 14 - Experimentation in marketplaces
  tl;dr: Experimentation in marketplaces: interference, spatial randomization, and switchbacks
  [slides] [recording]
  

  Suggested Readings:

  • Switchback Tests and Randomized Experimentation Under Network Effects at DoorDash
  • A/B testing at marketplaces
• 

  Lecture 15 - Experimentation conclusion
  tl;dr: Experimentation conclusion: synthetic control, culture, and communication
  [slides] [recording]
  

  Suggested Readings:

  • Synthetic control book chapter
  • Universal Holdout Groups at Disney Streaming
  • Large scale experimentation – Stitch Fix Technology
• 

  Guest 4 - Lily Xu Guest Lecture
  tl;dr: Lily Xu (Harvard).
  
  
• 

  Lecture 16 - Differential Privacy
  tl;dr: Introduction to differential privacy
  [slides] [recording]
  

  Suggested Readings:

  • Algorithmic Foundations of Differential Privacy
  • How to perform these attacks Part 2
  • Simple Demographics Often Identify People Uniquely
  • Differential privacy: A survey of results
• Guest 5 - George Markoulakis and Jaron Malcom (Clipboard Health) Guest Lecture
  tl;dr: George Markoulakis and Jaron Malcom (Clipboard Health).
  
  
• 

  Lecture 17 - Limits to prediction
  tl;dr: Prediction is hard, especially about the future
  [slides] [recording]
  

  Suggested Readings:

  • Limits to Prediction class, Princeton, (Pre-class summary reading)
  • Measuring the predictability of life outcomes with a scientific mass collaboration
  • Manipulation of Social Program Eligibility
• 

  Lecture 18 - Discrimination in Platforms
  tl;dr: Discrimination in ad platforms and two-sided marketplaces; some design mitigations
  [slides] [recording]
  
• 

  Lecture 19 - Digital marketing and AI for political campaigns
  tl;dr: Nikhil's experiences as a data scientist during the 2020 US election cycle
  
  
• 

  Lecture 20 - Course conclusion
  tl;dr: Course summary and discussion
  [slides] [recording]