Financial Data Science: Data Analytics & Machine Learning Fundamentals

Catalog description

This course equips students with the requisite SQL and Python programming and analytical skills needed to undertake advanced statistical learning procedures on financial datasets. The course begins with an introduction to structured query language (SQL) to ensure students can interact with relational databases commonly used to warehouse financial data. Students will learn how to retrieve, manipulate, and manage financial data from databases such as Wharton Research Data Services (WRDS), SEC Filings, Bloomberg, and Yahoo! Finance. Following the SQL modules, the course transitions into Python-based data preparation, covering extraction, transformation, and loading (ETL) processes, exploratory data analysis, and the generation of summary statistics. Students will develop hands-on experience in handling financial data from various sources and file formats, addressing the unique challenges associated with financial datasets. The course then introduces machine learning techniques relevant to financial modeling, specifically focusing on supervised learning techniques. Students will gain practical experience in model construction and evaluation. A special emphasis is placed on the interpretation of predictive modeling results, assessing model accuracy, and understanding the bias-variance tradeoff inherent in ML modeling. Students should expect to spend 5 to 7 hours per week outside of class meetings completing readings, coding assignments, and data analysis projects. By the end of the course, students will have acquired the SQL, Python programming, and statistical skills necessary to apply machine learning methods to complex financial datasets. Prereq: BAFI 355 .