Work

Research on multi-factor quantitative investment strategy of SVM model based on machine learning

Year: 2023

Type: conference-paper

Abstract: In order to cope with the impact of the epidemic on the global economy and the challenges to the investment industries, this paper based on the characteristics of quantitative investment, which is not affected by emotions and can process information quickly, takes the constituent stocks of CSI 300 index as the research object, constructs fundamental factors related to financial management, searches the hyperparameter space of the support vector machine algorithm, finds the optimal decision surface, constructs a stock selection model and excess investment portfolio, and evaluates the investment portfolio through simulated trading. The results show that the total return in the backtesting period reaches 41.25%, and the return of CSI 300 index is 21.15%. The method shows some value in training data, and also attenuates personal cognitive bias in actual trading, which is more suitable for adaptive dynamic trading in unstable markets, and also provides new ideas for the innovation of quantitative investment financial factor tools and the application of machine learning methods in the field of finance.

Source: International Conference on Artificial Intelligence and Computer Engineering (ICAICE)

DOI: 10.1145/3652628.3652737

Authors: Ting Liu, Chunyuan Li

Institution: Shanghai University

Language: English

Topic: Stock Market Forecasting Methods

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: bronze

Funders: Universitas Brawijaya, National Office for Philosophy and Social Sciences

Awards: G2263615717, G2869654641