Multiclass Sentiment Prediction for Stock Trading
Statistical Finance
2022-10-04 v1 Machine Learning
Abstract
Python was used to download and format NewsAPI article data relating to 400 publicly traded, low cap. Biotech companies. Crowd-sourcing was used to label a subset of this data to then train and evaluate a variety of models to classify the public sentiment of each company. The best performing models were then used to show that trading entirely off public sentiment could provide market beating returns.
Keywords
Cite
@article{arxiv.2210.00870,
title = {Multiclass Sentiment Prediction for Stock Trading},
author = {Marshall R. McCraw},
journal= {arXiv preprint arXiv:2210.00870},
year = {2022}
}
Comments
5 pages, 11 figures, written for course credit in the spring semester of 2020