FUND-RELATED GRAPH REPRESENTATION FOR MARGINAL EFFECTIVENESS IN MULTI-FACTORS QUANTITATIVE STRATEGY
Research on constructing fund-related graphs for multi-factor quantitative strategies to improve stock prediction accuracy.
What it examines
This paper explores constructing new factors from relational graph data in quantitative trading. It focuses on capital flow similarity graphs and their integration into multi-factor models using XGBoost, aiming to enhance stock prediction and portfolio returns in the A-share market.
What it concludes
The research highlights the effectiveness of fund-related graph factors in improving quantitative strategies. Potential applications include enhanced stock selection and portfolio management. Future research could explore additional relational data types and further refine graph construction methods.
Evidence objects
The research highlights the effectiveness of fund-related graph factors in improving quantitative strategies. Potential applications include enhanced stock selection and portfolio management. Future research could explore additional relational data types and further refine graph construction methods.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Under review as a conference paper at ICLR 2024 FUND -RELATED GRAPH REPRESENTATION FOR MARGINAL EFFECTIVENESS IN MULTI -FACTORS QUANTITATIVE STRATEGY Anonymous authors Paper under double-blind review ABSTRACT With increasing research attention in the quantitative trading community on multi- factors machine learning strategies, how to obtain higher-dimensional and effec- tive features from finance market has become an important research topic in both academia and industry area. In general, the effectiveness of new data, new fac- tors, and new information depends not only on the strength of their individual effects but also on the marginal increment they bring relative to existing factors. In this paper, our research focuses on how to construct new factors from the re- lational graph data. We construct six capital flow similarity graphs from the fre- quency of joint occurrences of the inflows or outflows of the net fund between stocks within the same period. Moreover, three composite mul
Source row: 949 · abstract type: unknown