Data-Driven Investments Lab
Spring 2024


Kerry Back (
Kevin Crotty (

Class Meeting

Room 216, McNair Hall
MW 2:15 – 3:45

Course Prerequisites

  • All students must have completed the core Finance, Accounting, and Data Analysis courses in their program.

  • Graduate: Students should have completed MGMT 638 (Data-Driven Investments: Equity).

  • Undergraduate: Students should have completed BUSI 448 (Investments).

  • Exceptions to these requirements can be granted in special circumstances. To request an exception, email either instructor.

Course Description

This course is part of the Data-Driven Investments curriculum designed to equip students with an analytical quantitative investment toolkit. Students will work in groups to develop, test, and implement investment strategies using Python. The investment strategies will be driven by a range of datasets provided by the instructors. The instructors will provide examples of Python programs implementing investment strategies.

Each group will first select a primary dataset or set of datasets to utilize. In the first part of the course, students will explore the data and develop trading ideas. The instructors will provide guidance on what types of strategies are typically employed using a given dataset.

In the second part of the course, students will implement their chosen strategy using a paper trading simulation. The course will emphasize understanding the sources of investment performance. This will include analyses of factor and sector exposures as well as attribution analysis. Student groups will report weekly on performance evaluation and strategy implementation. The course culminates in a comprehensive group presentation of the strategy design, implementation, and performance evaluation.

Data and Potential Investment Strategies

  1. Financial ratios
  2. Past price signals (momentum/reversals)
  3. Analyst recommendation revisions
  4. Corporate insider trades
  5. Short interest
  6. Corporate events (buybacks, splits, spin-offs)

Course Schedule

Week Lab Activities & Notes
Jan 8/10 Only undergraduates this week
Characteristics-based strategies
Jan 15/17 No class on Monday (MLK holiday)
Intro to datasets and strategies
Form groups
Jan 22/24 Intro to Alpaca paper trading
Machine learning for characteristics-based strategies
Jan 29/31
Feb 5/7
Groups explore datasets and develop potential investment ideas
Thursday, Feb 8 No class - We will not use the allotted make-up day
Feb 12/14 Groups finalize strategies for paper trading
Report on backtesting on Wednesday
Remainder of semester Conduct paper trading
Refine strategies
Report weekly performance evaluation on Wednesdays
Feb 19/21
Feb 26/28 Only undergraduates on Wednesday
Mar 4/6 Only undergraduates this week
Mar 11/13 Only MBAs this week
Mar 18/20
Mar 25/27
Apr 1/3
Apr 8/10
Apr 15/17 Presentation: strategy design, performance evaluation, and implementation


Grades will be determined using the following weighting scheme.

Assessment Weights Group or Individual?
Initial Strategy Presentation 20% Group
Weekly Performance and Trading Reports 50% Group
Final Presentation 20% Group
Peer Reviews 10% Individual