Econ 487 S18

Welcome to the UW Spring 2018 course “Data Science for Game Theory and Pricing”.  Here you’ll find course materials like the syllabus, problem sets and solutions to problem sets.

NOTE: for the R HWs you are expected to look around online to figure out some syntax for R.  This is a useful skill as what we learn in the class is only a base which you’ll add to down the road.  Finally, recall that you can and should work together with your classmates on these HWs in a collaborative environment but retain autonomy when writing up answers.

Figure courtesy of James Hall (2017 cohort); made with Pandas in Python



OJ Data-Column names for socio-demographic characteristics indicate the percent of households in the area proximate to a store which have a given characteristic. This will be the workhorse dataset for this class.

March 28: Lecture 1: Deriving demand and optimal uniform pricing.

HW 1 (Due April 4; R Markdown tutorial, ggplot2 Cheat Sheet). Please use Rmarkdown to turn in the R scripts. Suggested .docx solutions and .xlsx solutions.

April 4: Lecture 2: Value based pricing and modeling demand. HW 2 (Due April 11 as Rmarkdown file) Empirical Solutions and Theory Solutions

April 11: Lecture 3: Regression, Prediction and Model Complexity. HW 3 (Due April 18 as Rmarkdown file and word file) Suggested Solutions

April 18: Lecture 4: Model Complexity, Cross-Validation and LASSO. HW 4 (Due April 25 as Rmarkdown file and word file) HW 4 Suggested Solutions

April 25: Lecture 5: Causal Inference and Heterogeneity. Study Guide and HW 5 Due May 2

May 2: Midterm

May 9: Lecture 7: Game Theory, Market Structure and Firms (Will Wang). HW 6 Due May 16 HW 6 Suggested Solutions

May 16: Lecture 8: Causal Inference and Research Design (Sida Peng) HW 7 Due May 23. Regression Discontinuity data; Double ML Solution and RD Solution

May 23: Lecture 9: Trees, Clustering and Forests HW 8 Due May 30. Suggested Solutions

May 30: Lecture 10: Double ML and Freemium

Final Project: Due June 8 at 12:00pm PST. Leading Rmd and data. Project Guidelines. Part 1 is 40% and Part 2 is 60%.