Applying Machine Learning Methods to Predict Market Movements

Faculty Advisor: Former Quantitative Strategist, Morgan Stanley; PhD, Astrophysics, Columbia University

Research Program Introduction

Disclaimer: This program is purely for educational purposes. It is not to give financial advice on personal financial investments.

In today's dynamic financial landscape, understanding and predicting market movements is a crucial skill for investors, traders, and financial professionals. In this program, students will explore how a company’s financials can be used to create a machine learning model to predict stock prices. Students will learn about different metrics used to track a company’s financial health and learn how to create their own metrics. Students will also be introduced to a variety of machine learning models that can be used to create predictions of stock prices.

The goal is for students to gain familiarity with machine learning techniques as well as financial terms. By the end of the program, students will have a stronger ability to discuss and use machine learning techniques.

The final project for this program offers students flexibility based on their interests and skills. For students who are more interested in the financial aspects, the Faculty Advisor will provide a template machine learning code so students can focus on developing their own unique predictive metrics. Students who are more interested in machine learning modeling can develop their own algorithms for predicting stock prices. At the end of the program, each student will have a predictive model that can be written into a paper.

Options For Final Project:

• Students may compare different metrics and analyze which metrics do a better job of predicting prices.

• Students may build their own predictive model for a particular stock as their project.

• Students may compare several predictive models and examine which model is the most accurate in predicting prices.

Program Detail

• Cohort size: 3 to 5 students

• Workload: Around 4 to 5 hours per week (including class and homework time)

• Target students: 9 to 12th graders interested in Computer Science, Machine Learning, Mathematics, Data Science, Investment, Finance and/or Business

• Schedule: TBD. Meetings will take place for around one hour per week, with a weekly meeting day and time to be determined a few weeks prior to the class start date

• Required materials: Students should have Anaconda (python) installed on their computers and be able to open a Jupyter notebook