A Temporal Graph Network Approach for Personalized Portfolio Recommendations

DOI

10.2991/978-94-6463-598-0_54How to use a DOI?

Keywords

Stock recommendation; portfolio management; temporal graph networks; personalized financial advice; recommender systems

Abstract

In volatile financial markets, individual investors face challenges as traditional recommendation systems focus on individual stocks and rely mainly on historical data, overlooking social media sentiment, news, and expert opinions. This paper presents a framework using temporal graph networks (TGN) to capture evolving stock dynamics and investor preferences. By integrating user preferences-such as risk tolerance and investment goals-with alternative data, the model offers personalized portfolio recommendations. Evaluated on a large dataset of stock prices, transactions, and alternative data, the framework outperforms traditional methods in risk-adjusted returns, diversification, and alignment with investor goals.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ziyu Feng
PY  - 2024
DA  - 2024/12/19
TI  - A Temporal Graph Network Approach for Personalized Portfolio Recommendations
BT  - Proceedings of the 2024 3rd International Conference on Public Service, Economic Management and Sustainable Development (PESD 2024)
PB  - Atlantis Press
SP  - 520
EP  - 526
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-598-0_54
DO  - 10.2991/978-94-6463-598-0_54
ID  - Feng2024
ER  -