Abstract
Fund performance prediction aims to evaluate the performance of financial funds. It is of great interest to financial investors to achieve high returns while maintaining sustainable fund development. Existing studies primarily focus on analyzing the performance of individual fund managers using empirical analysis based on statistics, with limited attention given to leveraging social connections between managers and the latent characteristics of the fund learned from various financial market information for fund performance appraisal. In this paper, we propose to develop Hybrid Heterogeneous Graph Neural Networks for Fund Performance Prediction with Market Awareness. Specifically, we aim to build a heterogeneous fund information network to measure the social relationships between fund managers and the influence of funds on the investment relationship of stocks. Given the challenges of heterogeneous graph neural networks in dealing with relationship fusion of different types, we have designed a hybrid approach that combines heterogeneous graph embedding and tensor factorization to fuse two different sources of information over the heterogeneous fund information network. Furthermore, we incorporate a market-aware scheme, which combines static fund representation with dynamic market trends, to capture the dynamic factors of the market and enhance the accuracy of fund performance prediction. We conduct extensive experiments on real fund market datasets to confirm the effectiveness of our proposed framework, and the investment simulation shows that our approach can achieve higher returns compared to the baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Galagedera, D., Roshdi, I., Fukuyama, H., Zhu, J.: A new network DEA model for mutual fund performance appraisal: an application to US equity mutual funds. Omega 77, 168–179 (2018)
Middleton, K.L.W.: Becoming entrepreneurial: gaining legitimacy in the nascent phase. Int. J. Entrep. Behav. Res. (2013)
Qian, G., Wu, Y., Xu, M.: Multiple change-points detection by empirical Bayesian information criteria and Gibbs sampling induced stochastic search. Appl. Math. Model. 72, 202–216 (2019)
Schlichtkrull, M., Kipf, T., Bloem, P., Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: European Semantic Web Conference, pp. 593–607 (2018)
Wang, X., et al.: Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022–2032 (2019)
Yun, S., Jeong, M., Kim, R., Kang, J., Kim, H.: Graph transformer networks. Adv. Neural Inf. Process. Syst. 32 (2019)
Elton, E., Gruber, M., Blake, C.: Fundamental economic variables, expected returns, and bond fund performance. J. Financ. 50, 1229–1256 (1995)
Hochberg, Y., Ljungqvist, A., Lu, Y.: Whom you know matters: venture capital networks and investment performance. J. Financ. 62, 251–301 (2007)
Wang, X., Bo, D., Shi, C., Fan, S., Ye, Y., Philip, S.: A survey on heterogeneous graph embedding: methods, techniques, applications and sources. IEEE Trans. Big Data (2022)
Dong, Y., Chawla, N., Swami, A.: metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 135–144 (2017)
Hussein, R., Yang, D., Cudré-Mauroux, P.: Are meta-paths necessary? Revisiting heterogeneous graph embeddings. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 437–446 (2018)
Kiers, H.: Towards a standardized notation and terminology in multiway analysis. J. Chemomet. J. Chemomet. Soc. 14, 105–122 (2000)
Kolda, T., Bader, B.: Tensor decompositions and applications. SIAM Rev. 51, 455–500 (2009)
Nickel, M., Tresp, V., Kriegel, H.: A three-way model for collective learning on multi-relational data. ICML (2011)
Halpern, Y., Sontag, D.: Unsupervised learning of noisy-or Bayesian networks. In: Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence, pp. 272–281 (2013)
Sun, Y., Han, J.: Mining heterogeneous information networks: principles and methodologies. Synth. Lect. Data Mining Knowl. Discov. 3, 1–159 (2012)
Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)
Chen, C., Zhao, L., Bian, J., Xing, C., Liu, T.: Investment behaviors can tell what inside: exploring stock intrinsic properties for stock trend prediction. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2376–2384 (2019)
Liu, Q., Wu, H., Ye, Y., Zhao, H., Liu, C., Du, D.: Patent litigation prediction: a convolutional tensor factorization approach. In: IJCAI, pp. 5052–5059 (2018)
Deng, Y., Bao, F., Kong, Y., Ren, Z., Dai, Q.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Netw. Learn. Syst. 28, 653–664 (2016)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)
Brown, R.: Smoothing, Forecasting and Prediction of Discrete Time Series. Courier Corporation (2004)
Nelson, D., Pereira, A., De Oliveira, R.: Stock market’s price movement prediction with LSTM neural networks. In: 2017 International Joint Conference On Neural Networks (IJCNN), pp. 1419–1426 (2017)
Li, W., Bao, R., Harimoto, K., Chen, D., Xu, J., Su, Q.: Modeling the stock relation with graph network for overnight stock movement prediction. IJCAI 20, 4541–4547 (2020)
Pang, Y., et al.: Heterogeneous global graph neural networks for personalized session-based recommendation. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 775–783 (2022)
Zhang, L., et al.: Attentive heterogeneous graph embedding for job mobility prediction. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2192–2201 (2021)
Lin, J., Wang, F., Wei, L.: Alumni social networks and hedge fund performance: evidence from China. Int. Rev. Financ. Anal. 78, 101931 (2021)
Ye, J., Zhao, J., Ye, K., Xu, C.: Multi-graph convolutional network for relationship-driven stock movement prediction. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6702–6709 (2021)
Wang, C., et al.: Personalized and explainable employee training course recommendations: a Bayesian variational approach. ACM Trans. Inf. Syst. 40, 1–32 (2021)
Wang, C., Zhu, H., Zhu, C., Qin, C., Xiong, H.: SetRank: a setwise Bayesian approach for collaborative ranking from implicit feedback. In: AAAI, pp. 6127–6136 (2020)
Qin, C., et al.: Duerquiz: a personalized question recommender system for intelligent job interview. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2165–2173 (2019)
Qin, C., et al.: An enhanced neural network approach to person-job fit in talent recruitment. ACM Trans. Inf. Syst. 38, 1–33 (2020)
Acknowledgements
This work was supported by the Foshan HKUST Projects (FSUST21-FYTRI01A, FSUST21-FYTRI02A).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hao, S. et al. (2023). Hybrid Heterogeneous Graph Neural Networks for Fund Performance Prediction. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14118. Springer, Cham. https://doi.org/10.1007/978-3-031-40286-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-40286-9_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40285-2
Online ISBN: 978-3-031-40286-9
eBook Packages: Computer ScienceComputer Science (R0)