mlsanityData to 7 Oct 2026

A News-based Machine Learning Model for Adaptive Asset Pricing

arXiv 2106.07103 ↗First posted 13 Jun 2021q-fin.ST cs.LG stat.MEcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 6 of its 31 references that are in the map. First posted on arXiv 13 Jun 2021.

Builds on

6 of 31 references.

References · 6

  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  2. 2014Distributed Representations of Sentences and Documentscited by 677
  3. 2016An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generationcited by 48
  4. 2021Form 10-Q Itemizationcited by 10
  5. 2018High-Dimensional Estimation, Basis Assets, and the Adaptive Multi-Factor Modelcited by 8
  6. 2020Time-Invariance Coefficients Tests with the Adaptive Multi-Factor Modelcited by 7

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 1; 2023: 1; 2024: 1.

7 papers.

  1. 2021Clustering Structure of Microstructure Measurescited by 3
  2. 2021The Adaptive Multi-Factor Model and the Financial Marketcited by 3
  3. 2021An Efficient Group-based Search Engine Marketing System for E-Commercecited by 2
  4. 2022Deep Learning Based Page Creation for Improving E-Commerce Organic Search Trafficcited by 2
  5. 2023Finding Lookalike Customers for E-Commerce Marketingcited by 1
  6. 2021Two ways towards combining Sequential Neural Network and Statistical Methods to Improve the Prediction of Time Seriescited by 0
  7. 2024Integrating Natural Language Processing Techniques of Text Mining Into Financial System: Applications and Limitationscited by 0