FA690 Machine Learning in Finance

Course Catalog Description


The application of Machine Learning (ML) and Artificial Intelligence (AI) to finance does not just focus around the knowledge of algorithms. While the understanding of the algorithms used is fundamental to the discipline, it is also necessary to understand the tradeoffs of each algorithm, how they scale when used in production, and how to explain the problem, solution, and field with people who are not technically proficient. Prerequisite: FE 542 or FE 590


Professor Email Office
Zachary Feinstein zfeinste@stevens.edu Babbio 628

More Information

Course Description

This course is designed for Master and Ph.D. graduate students and advanced undergraduates. The purpose is to learn to apply machine learning techniques to financial problems. Students are expected to have prior knowledge of machine learning and statistical learning as taught in a course such as FE 590. Basic understanding of the financial problems presented in this course will be covered in the class; background material from courses such as FE 542 or FE 620 may be useful. We will use R and Python throughout this course; a running knowledge of one or both of these languages is good to have. FE515 is a one credit course teaching R programming. FE520 is a one credit course teaching Python.

Relationship of Course to Rest of Curriculum : The course is one of the core courses for the Financial Analytics (FA) program.

Learning Goals : In this course, students will (generally):

  • Be able to apply machine learning techniques to financial problems
  • Be able to evaluate the performance of different methods to determine the best
  • method/hyperparameters
  • Learn how to interpret results of machine learning in a financial context

Outcomes : A student graduating this course will be expected to possess the following specific knowledge:

  1. The ability to apply machine learning to problems in portfolio optimization
  2. The ability to apply machine learning to text data and run sentiment analysis
  3. The ability to apply machine learning to determine credit risk and credit ratings

  4. Textbook(s) : Assorted chapters, articles, and papers will be posted to Canvas as appropriate in PDF format.
    Software : We will use R and/or Python throughout this course. Students will be expected to install and have the program running on their computers.
    Lecture Format : The lectures will be held on Wednesdays from 6:30 to 9:00PM Eastern time. I will broadcast and record the lectures using Zoom and post them on canvas. You are encouraged to ask questions either in class, using Canvas, or by email.
    Office Hours/Accessibility : Office hours will be held on Thursday from 9:00AM to 11:00AM (Eastern time) virtually on Zoom. Additional office hours can be scheduled by email (zfeinste@stevens.edu). Questions about course material can also be asked by email (zfeinste@stevens.edu) or in the Discussion Section of Canvas; I will respond within 24 hours except in extenuating circumstances.


Grading Policies

There will be no examinations in this course.

  • Quizzes and Short Assignments: 10%
  • Assignment 1: 25%
  • Assignment 2: 25%
  • Assignment 3: 25%
  • Presentation: 15%
  • Total Grade: 100%


To understand the course material and get a good grade, it is necessary (though not sufficient) to invest a substantial amount of time working on the assignments. There will be 3 major assignments during the semester focused on the primary financial topic areas. These will be posted on Canvas (approximately) at the start of the first section on that topic. Additional small assignments and quizzes will accompany certain lectures. These will also be posted on Canvas. All assignments will be due on the specific due date at the specified time. No late assignments, without prior approval, will be accepted.
You are encouraged to discuss your assignments. However, all written homework must be written by you. Copying solutions from other students in the class, former students, tutors, or any other source is strictly forbidden. Copying the solution of one or more problems from another source than your own brain is considered academic dishonesty/misconduct and will be dealt with according to the Stevens honor board policy. Please review the “Collaborating or Working in Groups” document posted on Canvas which details what is considered fair collaborating and what is considered academic misconduct.
Your solutions must be those that you fully understand and can produce again (and solve similar problems) without help. The ideal model to follow is: first work independently, then to discuss issues with your classmates, and then to prepare the final write-up individually. This is an applied course. Therefore, I expect any solution to a problem in this class will follow the steps below:

  1. Outline the steps and identify the mathematical techniques learned that pertain to the respective problem.
  2. If the problem needs a method, first identify and describe the methodology to be applied.
  3. Apply the methodology to the problem or data under study.
  4. Write a conclusion explaining if the application seems to support the method.
  5. Preliminary Grading Scheme:
    A: 93%-100%
    A-: 90%-93%
    B+: 87%-90%
    B: 83%-87%
    B-: 80%-83%
    C+: 77%-80%
    C: 70%-77%
    F: 0%-70%
    This grading scheme is subject to change based on student outcomes. It may be curved more leniently. It will not be made more difficult.

Lecture Outline

Date Topics Reading
9/6 Review of Machine Learning
9/13 ML for Portfolio Selection and Time Series (1)
9/20 ML for Portfolio Selection and Time Series (2)
9/27 ML for Portfolio Selection and Time Series (3)
10/4 ML for Portfolio Selection and Time Series (Presentations)
10/11 Columbus Day - No Class
10/18 ML for Text Analysis and Sentiment Analysis (1)
10/25 ML for Text Analysis and Sentiment Analysis (2)
11/1 ML for Text Analysis and Sentiment Analysis (3)
11/8 ML for Text Analysis and Sentiment Analysis (Presentations)
11/15 ML for Credit Risk and Ratings (1)
11/18 ML for Credit Risk and Ratings (3)
11/22 ML for Credit Risk and Ratings (2)
11/29 ML for Credit Risk and Ratings (3)
12/6 ML for Credit Risk and Ratings (Presentations)
12/13 Wrap-up/TBD

Please note that this schedule is a tentative plan for the semester. As we move through the semester the schedule outlined here is subject to change.

2020 Fall FE690 Machine Learning in Finance