Research Article
Application of Computer Science in Risk Management of Financial Investment
@INPROCEEDINGS{10.4108/eai.28-10-2022.2328463, author={Andy Ruichen Lu and Yuhan Pan and Yu Yang and Zhiyi Ying}, title={Application of Computer Science in Risk Management of Financial Investment}, proceedings={Proceedings of the International Conference on Financial Innovation, FinTech and Information Technology, FFIT 2022, October 28-30, 2022, Shenzhen, China}, publisher={EAI}, proceedings_a={FFIT}, year={2023}, month={4}, keywords={python fama-french model linear regression model decision tree regressor model portfolio optimization with monte carlo simulations}, doi={10.4108/eai.28-10-2022.2328463} }- Andy Ruichen Lu
Yuhan Pan
Yu Yang
Zhiyi Ying
Year: 2023
Application of Computer Science in Risk Management of Financial Investment
FFIT
EAI
DOI: 10.4108/eai.28-10-2022.2328463
Abstract
Forecasting for the stock market is a popular domain that many researchers have focused on in recent years. However, accurate prediction for different types of stocks is still challenging. In this research, by using the computing power of a programming tool called Python, financial mathematical models were transferred into a computer model, and this study innovatively realized the use of computers to complete the preliminary stock market forecast, to make the forecast and asset distribution more accurate, which is very helpful for practitioners in the stock market. Investment in the field has played an important role in avoiding risks. This study obtained data from Yahoo Finance and made relevant predictions using mainly Fama-French model, Linear Regression model, Decision Tree Regressor model and Portfolio Optimization with Monte Carlo Simulations experiment. The result indicated that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the multi-factor model, Linear Regression model and Decision Tree Regressor model are all less than 1, which means the prediction effect of the experiment is satisfactory. This demonstrates the feasibility of emerging computer algorithms to replace traditional methods.
