Rewriting the code in "Machine Learning for Factor Investing" in Python

Value or Momentum? Comparing Random Forests, Support Vector Machines, and Multi-layer Perceptrons for Financial Time Series Prediction & Tactical Asset Allocation

众人的因子回测框架 stock factor test

Calculate technical factors for stocks in an efficient, maintainable and correct way

Web dashboard to visualize equity factor dynamics using solely publicly available data.

Data Science Project: Replication of "Forest Through the Trees: Building Cross-Sections of Stock Returns" - creation of assets to test validity of factor models with Python

In this study, I empirically and statistically investigate the credibility of common asset pricing beliefs using data from S&P 500® constituents from January 2010–December 2020.

VAR vs. LSTM: Multivariate Forecasting of Factor Returns

Bridging engineering expertise and investment savvy through hands-on tutorials, insightful financial analysis, and collaborative learning in Python and beyond.

Machine Learning for Factor Investing: Python Version

A project to estimate a stock's risk with a linear regression model in Python, using the Fama-French Carhart model and live data from Yahoo Finance.

Risk Premia Estimation (FamaMacbeth and Three-pass)

University Project: constructing portfolios by blending different types of factor portfolios (low-beta, value, and momentum). We investigate different techniques to weight our portfolio and calculating a combined score.

AQR Asset Management datasets in R

Computing Index Prices and Returns from prices/returns of financial assets

Python code for Swade et al. (2023) "Why Do Equally Weighted Portfolio Beat Value-Weighted Ones?" The Journal of Portfolio Management, 49 (5), 167–187.

Assignment3 is the application of factor investing

Analysis of an investment strategy known as Residual Momentum on the New York Stock Exchange (NYSE) is based on the premise that stock returns exhibit a certain "inertia", which gives rise to the phenomenon known as the "momentum effect".

Minimal PEAD (post-earnings announcement drift) backtest using Wharton Research Data Services (IBES + CRSP) — Python pipeline for research & plots.