English

A News-based Machine Learning Model for Adaptive Asset Pricing

Statistical Finance 2021-06-15 v1 Machine Learning Methodology Machine Learning

Abstract

The paper proposes a new asset pricing model -- the News Embedding UMAP Selection (NEUS) model, to explain and predict the stock returns based on the financial news. Using a combination of various machine learning algorithms, we first derive a company embedding vector for each basis asset from the financial news. Then we obtain a collection of the basis assets based on their company embedding. After that for each stock, we select the basis assets to explain and predict the stock return with high-dimensional statistical methods. The new model is shown to have a significantly better fitting and prediction power than the Fama-French 5-factor model.

Keywords

Cite

@article{arxiv.2106.07103,
  title  = {A News-based Machine Learning Model for Adaptive Asset Pricing},
  author = {Liao Zhu and Haoxuan Wu and Martin T. Wells},
  journal= {arXiv preprint arXiv:2106.07103},
  year   = {2021}
}
R2 v1 2026-06-24T03:09:12.078Z