Machine Learning Algorithms for Financial Asset Price Forecasting
arXiv:2004.01504
Abstract
This research paper explores the performance of Machine Learning (ML) algorithms and techniques that can be used for financial asset price forecasting. The prediction and forecasting of asset prices and returns remains one of the most challenging and exciting problems for quantitative finance and practitioners alike. The massive increase in data generated and captured in recent years presents an opportunity to leverage Machine Learning algorithms. This study directly compares and contrasts state-of-the-art implementations of modern Machine Learning algorithms on high performance computing (HPC) infrastructures versus the traditional and highly popular Capital Asset Pricing Model (CAPM) on U.S equities data. The implemented Machine Learning models - trained on time series data for an entire stock universe (in addition to exogenous macroeconomic variables) significantly outperform the CAPM on out-of-sample (OOS) test data.
arXiv comment16 pages, 4 Figures
References in corpus (12)
- A Unified Approach to Interpreting Model Predictions
- Twitter mood predicts the stock market
- Recurrent Neural Network Regularization
- Evaluating time series forecasting models: An empirical study on performance estimation methods
- Deep and Confident Prediction for Time Series at Uber
- Hyperparameter Search in Machine Learning
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- Anticipating cryptocurrency prices using machine learning
- NGBoost: Natural Gradient Boosting for Probabilistic Prediction
- Deep Learning in Finance
- How to evaluate sentiment classifiers for Twitter time-ordered data?
- Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals