Stock Return Prediction Using Machine Learning Classifiers

DOI

10.2991/aebmr.k.220603.218How to use a DOI?

Keywords

Stock return prediction; machine learning; sentiment analysis; random forest; decision trees; KNN

Abstract

Machine learning is one of the major tools that could extract patterns from big data. The bigger the size of the data, the better the machine will learn. From the technical perspective, machine learning makes better predictions. In this paper, the major objective is to predict annual average stock returns using machine learning methods. To build the model, fundamental and financial data about each firm are used. Furthermore, news of each firm is webscrabbed and categorized as either positive or negative news using sentiment analysis methods. The conclusion is that adding sentiment analysis decreases the accuracy of the entire model. This result indicates that with influential incidents like COVID-19[1], models have more significant scores than usual (when considering only SP500 components). In 2018, adding sentiment variables decreased the model accuracy by 3% on average.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Shenghan Zhao
PY  - 2022
DA  - 2022/07/01
TI  - Stock Return Prediction Using Machine Learning Classifiers
BT  - Proceedings of the 2022 2nd International Conference on Enterprise Management and Economic Development (ICEMED 2022)
PB  - Atlantis Press
SP  - 1347
EP  - 1351
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220603.218
DO  - 10.2991/aebmr.k.220603.218
ID  - Zhao2022
ER  -