Session
Management, Business and Economics
Description
The financial market and stock market have experienced great changes during the past decades, which lead to lots of excellent
new methods about how to calculate and predict the return of the mar- ket and stocks.
Currently, a common practice of stock investors is to implement the Capital Asset Pricing Model (CAPM) and calculate excess returns with the difference between the real value and the theoretical value of stocks. Among Capital Asset Pricing Models, the Fama-French factors model is used frequently. In this paper, we applied several machine learning algorithms in the stock market to find out whether they are useful in predicting the stock price and what are the possible reasons behind the results. With proper data, the result can also predict the return of the market with excess return in Fama-French three factors model. The machine learning algorithms were used to predict the price of S&P500, using data of S&P500 constituents. It is chosen because S&P500 data is a standard of the return of the market, and the data of its constituents are highly related to the excess return α. Then the machine learning algorithms were proposed to identify the relationship between the excess return of the last day and the return of the market of the next day. This research showed that some machine learning algorithms can do the prediction well with proper models and parameters. Besides, the return of the market can be predicted with proper data.
Keywords:
Machine learning, Stock market, Return of market, S&P500
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-47-5
Location
UBT Kampus, Lipjan
Start Date
30-10-2021 12:00 AM
End Date
30-10-2021 12:00 AM
DOI
10.33107/ubt-ic.2021.529
Recommended Citation
You, Ran, "The machine learning algorithms to the market return" (2021). UBT International Conference. 553.
https://knowledgecenter.ubt-uni.net/conference/2021UBTIC/all-events/553
Included in
The machine learning algorithms to the market return
UBT Kampus, Lipjan
The financial market and stock market have experienced great changes during the past decades, which lead to lots of excellent
new methods about how to calculate and predict the return of the mar- ket and stocks.
Currently, a common practice of stock investors is to implement the Capital Asset Pricing Model (CAPM) and calculate excess returns with the difference between the real value and the theoretical value of stocks. Among Capital Asset Pricing Models, the Fama-French factors model is used frequently. In this paper, we applied several machine learning algorithms in the stock market to find out whether they are useful in predicting the stock price and what are the possible reasons behind the results. With proper data, the result can also predict the return of the market with excess return in Fama-French three factors model. The machine learning algorithms were used to predict the price of S&P500, using data of S&P500 constituents. It is chosen because S&P500 data is a standard of the return of the market, and the data of its constituents are highly related to the excess return α. Then the machine learning algorithms were proposed to identify the relationship between the excess return of the last day and the return of the market of the next day. This research showed that some machine learning algorithms can do the prediction well with proper models and parameters. Besides, the return of the market can be predicted with proper data.