CS7646 Fall 2023

This page provides information about the Georgia Tech CS7646 class on Machine Learning for Trading relevant only to the Fall 2023 semester. Note that this page is subject to change at any time. The Fall 2023 semester of the CS7646 class will begin on August 21st, 2023. Below, find the course calendar, grading criteria, and other information. For complete details about the course’s requirements and learning objectives, please see the general CS7646 page.

In the event of conflicts between the Fall 2023 page and the general CS7646 page, this page supersedes the general course page.

Quick Links

To help with navigation, here are some of the links you’ll frequently be using in this course:

Tools: Canvas | Ed Discussion | Course Lectures
Class Pages: CS7646 Home | Fall 2023 Syllabus
Environment Setup: Software Setup | Local Environment
Projects: Gradescope Instructions | Project 1 | Project 2 | Project 3 | Project 4 | Project 5 | Project 6 | Project 7 | Project 8
Exams: Honorlock Instructions | Exam 1 | Exam 2
Extra Credit: Holy Hand Grenade Of Antioch

COURSE CALENDAR AT-A-GLANCE

Below is the calendar for the Fall 2023 CS7646 class. Note that assignment due dates are Sundays at 11:59 PM Anywhere on Earth time. All assignments are finalized 3 weeks before the listed due date.

Readings come from the three-course textbooks listed on the course home page. Online lessons, readings, and videos are required unless marked with an asterisk; asterisk-marked items are optional.

Week #	Week Of	Lessons	Readings/Videos	Assignment	Assignment Due Date
1	08/21/2023	01-01 01-02 01-03 01-04	Python for Finance Ch. 4 & 6* Probabilistic Machine Learning 1 Chapters 1.1, 1.2, 1.4, & 1.6	Local Environment Setup Introduce Yourselves (Ed Discussions) Start-of-Course Survey Quiz 1	08/27/2023
2	08/28/2023	01-05 01-06 01-07 01-08	Python for Finance Ch. 5* Machine Learning Ch. 1* Introduction to Statistical Learning – Chapter 1	Project 1 Start-of-Course Survey Quiz 2	09/03/2023
3	09/04/2023	01-09 03-01 03-02	Python for Finance Ch. 11* Introduction to Statistical Learning – Chapter 2.2, 3.1 to 3.3	Project 2 Quiz 3	09/10/2023
4	09/11/2023	03-03 03-04	Suntrust Visit* Decision Trees 1 Decision Trees 2 Machine Learning Ch. 3* Introduction to Statistical Learning – Chapters 8.1 and 8.2	Quiz 4	09/17/2023
5	09/18/2023	02-01 02-02	Introduction to Statistical Learning – Chapters 3.5 What Hedge Funds Really Do Ch. 2 & 4 Machine Learning Ch. 8*	Project 3 Quarter-Course Survey Quiz 5	09/24/2023
6	09/25/2023	02-03 02-04	Is the stock market rigged? What Hedge Funds Really Do Ch. 5, & 7	Project 4 Quiz 6	10/01/2023
7	10/02/2023	02-05 02-06	What Hedge Funds Really Do Ch. 8 & 12	Quiz 7	10/08/2023
8	10/09/2023	02-07 02-08	Market Simulator	Project 5 Exam 1	10/15/2023 Exam Window: 10/09/2023 – 10/15/2023
9	10/16/2023		The Big Short* Time Series Data Vectorize Me PowerPoint	Project 6 Mid-Course Survey Quiz 8	10/22/2023
10	10/23/2023	02-09 02-10	What Hedge Funds Really Do Ch. 9 Decision Tree-Based Trading	Quiz 9	10/29/2023
11	10/30/2023	03-05 03-06 03-07	Navigation Project Strategies for Q-Learner Trader Machine Learning – Chapter 13* Foundations of Deep Reinforcement Learning – Chapter 1* Probabilistic Machine Learning 2 – Chapter 35*	Project 7 Quiz 10	11/05/2023
12	11/06/2023		Applying Deep Reinforcement Learning to Trading with Dr. Tucker Balch* Introduction to Statistical Learning – Chapters 10.1 & 10.2 Introduction to Statistical Learning – Chapters 10.3 & 10.4*	Quiz 11	11/12/2023
13	11/13/2023		Introduction to Statistical Learning – Chapters 10.5 & 10.6	Extra Credit Quiz 12	11/19/2023
14	11/20/2023		Keynote on Algorithmic Bias (Drs. Isbell and Littman)*	Project 8	11/26/2023
15	11/27/2023		Options Trading Interview with Tammer Kamel (Ed Lessons)
16	12/04/2023			Exam 2 End-of-Course Survey	Exam Window: 12/04/2023 – 12/10/2023
17	12/11/2023			CIOS	12/14/2023

Course Assessments

Grades in this class are derived from four categories: eight Projects, two Exams, Course Content Quizzes, and Course Surveys.

Final grades will be calculated as an average of all grade components, weighted according to the percentages below. Students receiving a final average of 90 or above will receive an A; of 80 to 90 will receive a B; of 70 to 80 will receive a C; of 60 to 70 will receive a D; and of below 60 will receive an F. There is no curve. It is intentionally possible for every student in the class to receive an A.

Projects: 71%

There are eight projects in this class. Altogether, the projects account for 71% of your final grade. The projects are not all equal in scope or difficulty, and thus they do not all count evenly. The projects are:

Project 1, 3%: Martingale
Project 2, 3%: Optimize Something
Project 3, 15%: Assess Learners
Project 4, 5%: Defeat Learners
Project 5, 8%: Marketsim
Project 6, 7%: Indicator Evaluation
Project 7, 10%: Qlearning Robot
Project 8, 20%: Strategy Evaluation

Exams: 25%

There are two exams, each worth 12.5% of your average.

Exams will be delivered via Canvas and Honorlock. Any material in the lecture videos or the non-optional items listed under Readings/Videos until the exam week is eligible for inclusion on the exams.

Course Content Quizzes: 2%

There will be approximately 10 quizzes covering the lecture material, course materials, and project requirements. Quizzes consist of a small number of multiple-choice/short-answer questions. They are administered on Canvas and will be like the Multiple-Choice Questions (MCQs) you will see on the exams. Please refrain from posting or discussing the question(s) on Ed Discussion, Slack, or other communications channels. Quizzes are released on Mondays and are due the following Sunday at 11:59 pm AOE. Late quiz submissions are not accepted.

Course Surveys: 2%

Course Surveys are 2% of your average. All course survey activities will be shared as part of the Surveys section of assignments in Canvas. Complete all these by the due dates shown in Canvas to fulfill your credit.

Extra Credit (Optional): 2%

This is optional and will not count against your grade, whether you attempt it or not.

Extra Credit Project

Course Policies

The following policies are binding for this course.

Official Course Communication

You are responsible for knowing the following information:

Anything posted to this syllabus (including the pages linked here, the general course landing page).
Anything emailed directly to you by the teaching team (including announcements via Ed Discussion) 24 hours after receiving such an email.

Because Ed Discussion announcements are emailed to you, you need only check your Georgia Tech email once every 24 hours to remain up-to-date on new information during the semester. Georgia Tech generally recommends students check their Georgia Tech email once every 24 hours. So, if an announcement or message is time-sensitive, you will not be responsible for the contents of the announcement until 24 hours after it has been sent.

We generally prefer to handle class-wide communication via Ed Discussion, but the Assignment Follow-Up form is utilized for individual grade-specific communication. Slack is a fantastic tool but is not officially monitored: stick to Ed Discussion for official questions and answers.

Note that this means you won’t be responsible for knowing information communicated in several other methods we’ll be using. You aren’t responsible for knowing anything posted to Ed Discussion that isn’t linked to an official announcement. You aren’t accountable for anything said in Slack or other third-party sites we sometimes use to communicate with students. You don’t need to worry about missing critical information if you keep up with your email and understand this website’s documents. This also applies in reverse: we do not monitor our Canvas message boxes. Please create a private Ed Discussion post if you need to contact the course staff.

Code Submission

All coding assignments are submitted via Gradescope. Note that Gradescope does not grade your assignment live; instead, it pre-validates that it will run against our batch autograder that we will run after the deadline. There will be no credit for coding assignments that do not pass this pre-validation.

Office Hours

Most of our Teaching Assistants will hold weekly office hours using Hangouts, Webex, or another teleconferencing tool. Office hours are not recorded and are intended for more individually-focused help and conversations. Anything that comes up during office hours relevant to the entire class will be shared via Ed Discussion.

An office hours schedule will be made available via Ed Discussion early in the semester.

Late Work

Late work will not be accepted without approved emergency extensions prior to the due date. All assignments are due and must be acknowledged by the server (e.g., Gradescope, Canvas) by the due date and time in Canvas. We have made the descriptions of all assignments available on the first day of class. If there are expected interruptions (business trips, family vacations, etc.), you can complete the work ahead of time. Code must be submitted to Gradescope SUBMISSION, and your last submission will be used unless you activate a previous submission. Reports are submitted to Canvas, and your last submission will be used.

Suppose you have an emergency and absolutely cannot submit an assignment by the posted deadlines. In that case, we ask you to make a private Ed Discussion post to ALL instructors with information about your extension request for a justifiable excuse. Justifiable excuses here would involve any major unforeseen disruption to your classwork, such as injuries, deaths, and births, all for either you or your family. Note that for foreseen but unavoidable conflicts, like weddings, business trips, job interviews, conferences, and assignments in other courses, you should complete your work in advance. Requests may be subject to the Dean of Students approval.

Assignment Follow-Up

The Assignment Follow-Up page outlines the full details and directions for requesting clarification or regrade on your assignment. Ensure that you have reviewed it and adhere to the guidelines when presenting a request.

Academic Honesty

All students in the class are expected to know and abide by the Georgia Tech Academic Honor Code. Specifically for us, the following academic honesty policies are binding for this class:

In written essays, all sources are expected to be cited according to APA style, both in-line with quotation marks and at the end of the document. You should consult the Purdue OWL Research and Citation Resources for proper citation practices, especially the following pages: Quoting, Paraphrasing, and Summarizing, Paraphrasing, Avoiding Plagiarism Overview, Is It Plagiarism?, and Safe Practices. You should also consult our dedicated pages on how to use citations and avoid plagiarism.
Any non-original figures must similarly be cited. If you borrow an existing figure and modify it, you must still cite the original figure. It must be obvious what portion of your submission is your creation.
In written essays, you may not copy any content from any current or previous student in this class, regardless of whether you cite it or not.
You may not copy any code from any other source, including but not limited to repositories on the internet and former students in the class. Every line of code you submit should be your work. Any code copying will result in an automatic 0 on the project and a report to the Office of Student Integrity.
During exams, you are prohibited from consulting outside material, interacting directly with any other person (except for the teaching staff) on the exam topic, or any other behaviors that could be used to gain an unfair advantage.

Note, however, when seeking help from the TAs via office hours or the course forum, you may assume that a TA will not share too much information. For example, if a TA gives you a line of code, you may use it.

These policies, including the rules on all pages linked in this section, are binding for the class. Any violations of this policy will be subject to the institute’s Academic Integrity procedures, which may include a 0 grade on assignments found to contain violations, additional grade penalties, and academic probation or dismissal.

Note that if you are accused of academic misconduct, you are not permitted to withdraw from the class until the accusation is resolved; if you are found to have participated in the misconduct, you will not be allowed to withdraw for the semester. If you do so anyway, you will be forcibly re-enrolled without any opportunity to make up work you may have missed while illegally withdrawn.

Feedback

Every semester, we make changes and tweaks to the course formula. As a result, every semester, we try some new things which may not work. We ask for your patience and support as we figure things out, and in return, we promise that we, too, will be fair and understanding, especially with anything that might impact your grade or performance in the class. Second, we want to consistently get feedback on improving and expanding the course for future iterations. You can take advantage of the feedback box on Ed Discussion (especially if you want to gather input from others in the class), give us feedback on the surveys, or contact us directly via private Ed Discussion messages.