Research Article
Study of Stock Return Prediction Based on Big Data
@INPROCEEDINGS{10.4108/eai.9-12-2022.2327593, author={Shiqi Chen}, title={Study of Stock Return Prediction Based on Big Data}, proceedings={Proceedings of the 4th Management Science Informatization and Economic Innovation Development Conference, MSIEID 2022, December 9-11, 2022, Chongqing, China}, publisher={EAI}, proceedings_a={MSIEID}, year={2023}, month={3}, keywords={fundamentals; big data; stock return forecasting}, doi={10.4108/eai.9-12-2022.2327593} }- Shiqi Chen
Year: 2023
Study of Stock Return Prediction Based on Big Data
MSIEID
EAI
DOI: 10.4108/eai.9-12-2022.2327593
Abstract
The stock market is one of the most important components of the capital market, and thus identifying the reasons for changes in expected stock returns is key to building a well-functioning capital market. Based on Gordon's dividend growth model, this paper composes company fundamental indicators from five aspects: profitability, growth, corporate governance, potential value and safety, and obtains a company characteristics data set containing 115 indicators. Principal component analysis, Enigma Macbeth regression method, predictive portfolio method, composite principal component analysis and partial least squares method are applied to reduce the dimensionality of the above data set and construct a comprehensive quality index of company fundamentals respectively. The quality index QPLS constructed based on the partial least squares method is found to have the strongest and relatively stable predictive power through the uni variate portfolio analysis method. This paper confirms the importance of quantitative big data integration in stock market research and enriches the research on the frontier of "big data + asset pricing".