Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Stock Recommendations for Individual Investors: A Temporal Graph Network Approach with Mean-Variance Efficient Sampling

Youngbin Lee, Yejin Kim, Javier Sanz-Cruzado, Richard McCreadie, Yongjae Lee

TL;DR

The paper tackles personalized stock recommendations for individual investors by balancing user preferences with portfolio diversification in a temporally evolving market. It introduces PfoTGNRec, a Portfolio Temporal Graph Network Recommender that learns dynamic embeddings via a temporal graph network and uses mean-variance efficient sampling to guide diversification, optimized with Bayesian Personalized Ranking. Empirical results on real investor data show that PfoTGNRec offers competitive recommendation accuracy while achieving improved portfolio performance compared to strong baselines, highlighting the value of jointly modeling dynamics and diversification. The work contributes a holistic framework for personalized, temporally-aware stock recommendations and provides code and data to enable reproducibility and further research.

Abstract

Recommender systems can be helpful for individuals to make well-informed decisions in complex financial markets. While many studies have focused on predicting stock prices, even advanced models fall short of accurately forecasting them. Additionally, previous studies indicate that individual investors often disregard established investment theories, favoring their personal preferences instead. This presents a challenge for stock recommendation systems, which must not only provide strong investment performance but also respect these individual preferences. To create effective stock recommender systems, three critical elements must be incorporated: 1) individual preferences, 2) portfolio diversification, and 3) the temporal dynamics of the first two. In response, we propose a new model, Portfolio Temporal Graph Network Recommender PfoTGNRec, which can handle time-varying collaborative signals and incorporates diversification-enhancing sampling. On real-world individual trading data, our approach demonstrates superior performance compared to state-of-the-art baselines, including cutting-edge dynamic embedding models and existing stock recommendation models. Indeed, we show that PfoTGNRec is an effective solution that can balance customer preferences with the need to suggest portfolios with high Return-on-Investment. The source code and data are available at https://github.com/youngandbin/PfoTGNRec.

Stock Recommendations for Individual Investors: A Temporal Graph Network Approach with Mean-Variance Efficient Sampling

TL;DR

The paper tackles personalized stock recommendations for individual investors by balancing user preferences with portfolio diversification in a temporally evolving market. It introduces PfoTGNRec, a Portfolio Temporal Graph Network Recommender that learns dynamic embeddings via a temporal graph network and uses mean-variance efficient sampling to guide diversification, optimized with Bayesian Personalized Ranking. Empirical results on real investor data show that PfoTGNRec offers competitive recommendation accuracy while achieving improved portfolio performance compared to strong baselines, highlighting the value of jointly modeling dynamics and diversification. The work contributes a holistic framework for personalized, temporally-aware stock recommendations and provides code and data to enable reproducibility and further research.

Abstract

Recommender systems can be helpful for individuals to make well-informed decisions in complex financial markets. While many studies have focused on predicting stock prices, even advanced models fall short of accurately forecasting them. Additionally, previous studies indicate that individual investors often disregard established investment theories, favoring their personal preferences instead. This presents a challenge for stock recommendation systems, which must not only provide strong investment performance but also respect these individual preferences. To create effective stock recommender systems, three critical elements must be incorporated: 1) individual preferences, 2) portfolio diversification, and 3) the temporal dynamics of the first two. In response, we propose a new model, Portfolio Temporal Graph Network Recommender PfoTGNRec, which can handle time-varying collaborative signals and incorporates diversification-enhancing sampling. On real-world individual trading data, our approach demonstrates superior performance compared to state-of-the-art baselines, including cutting-edge dynamic embedding models and existing stock recommendation models. Indeed, we show that PfoTGNRec is an effective solution that can balance customer preferences with the need to suggest portfolios with high Return-on-Investment. The source code and data are available at https://github.com/youngandbin/PfoTGNRec.
Paper Structure (23 sections, 9 equations, 4 figures, 2 tables)

This paper contains 23 sections, 9 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Stock Recommendations
  4. Dynamic Graph Learning
  5. Preliminaries
  6. Method
  7. Dynamic Embedding Learning
  8. Memory embedding
  9. Graph embedding
  10. Mean-Variance Efficient Sampling
  11. BPR Loss
  12. Experiment
  13. Experimental Settings
  14. Dataset
  15. Baseline
  16. ...and 8 more sections

Figures (4)

  • Figure 1: The importance of temporal aspects in stock recommender systems. (A) Various features of stocks would be different based on the timing of recommendations. (B) Contrasting behaviors between user A, who engages in short-term trading, and user B, who holds stocks for a long period.
  • Figure 2: Model architecture of our proposed PfoTGNRec.
  • Figure 3: Visualization of Comparison of Both Recommendation and Portfolio Performance
  • Figure 4: Hyperparameter study of the PfoTGNRec