Gen AI and Quantitative Investments
Fall 2026, Term 1
Instructor
Kerry Back
kerry.e.back@rice.edu
J. Howard Creekmore Professor of Finance and Professor of Economics
Meeting Schedule
McNair 212
TTh 12:30–2:00
08/25/2026 – 10/01/2026
Overview
The course is about building quantitative investment strategies with generative AI as the working tool. We start from valuation multiples and peer comparisons, move through linear regression and then machine learning as ways of predicting multiples and returns, take up corporate insider trades and short interest as signals, then turn to news headlines and finish with risk models and the management of portfolio risk. Every idea is backtested.
The course is hands-on. Most of what you learn, you will learn by building with your group.
AI Tools
Each person has an account at lab638.kerryback.com. Sign in with your netid as your username and your student number (including the S0 at the beginning) as your password. This logs you in to a Linux container on a cloud server.
The Claude Code harness is installed in each account, along with Python and other useful software and Claude skills. Claude Code is connected to GLM 4.7, a relatively inexpensive yet capable large language model from Z.ai.
Security on the server is minimal, so do not keep personal information on it.
Groups
Form groups of two or three students. You will work with your group for the entire term, in class and on presentations.
In the first week, each group should set up a shared GitHub repository, which all members of the group can push to. All of the group’s code, notebooks, and results live there. It is what makes it possible for three people to work on the same project and for you to show what you did.
One person in each group should tell
I also recommend a Slack channel for communication within your group, but it is your choice how you wish to communicate.
Class Structure
The first two classes (August 25 and 27) are an introduction to the tools and some of the data.
Beginning September 1, every class consists of three activities:
- Group presentations. Three groups, chosen at random, present at the start of class.
- Lecture. New material for the day.
- Hands-on work. You and your group build something with what was just covered.
The hands-on portion is the heart of the course, and it is what the presentations are about.
Presentations
Beginning September 1, three groups are chosen at random at the start of each class to present on what they accomplished in the previous class session and the time between classes — what they built, what they found, what did not work, and what they would do differently. Each group will present twice during the term.
Because the groups are chosen at random, every group should be ready to present at every class. Presentations are short and informal. Show your work from the repository; there is no need for slides.
Grading
Grades are based on:
| Component | Weight |
|---|---|
| Group presentations | 60% |
| Class participation | 40% |
Class participation means being present, prepared, and engaged — with the lecture, with the hands-on work, and with the other groups’ presentations.
Schedule, Slides, and other Materials
The schedule is on the course home page. Links to slide decks and other resources are posted there beside each class date.
Honor Code
The Rice University honor code applies to all work in this course. Use of generative AI is of course permitted.
Disability Accommodations
Any student with a documented disability requiring accommodations in this course is encouraged to contact me outside of class. All discussions will remain confidential. Any adjustments or accommodations regarding assignments or the final exam must be made in advance. Students with disabilities should also contact Disability Support Services in the Allen Center.