Asset pricing with contrastive adversarial variational Bayes

Liu, Ruirui, Huang, Huichou and Ruf, Johannes ORCID: 0000-0003-3616-2194 (2025) Asset pricing with contrastive adversarial variational Bayes. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Proceedings of the International Joint Conference on Artificial Intelligence,34. International Joint Conferences on Artificial Intelligence.

Text (ijcai25_5007_main) - Accepted Version Pending embargo until 1 January 2100. Download (511kB)

Abstract

Machine learning techniques have gained consider able attention in the field of empirical asset pricing. Conditioning on a broad set of firm characteristics, one of the most popular no-arbitrage workhorses is a nonlinear conditional asset pricing model that consists of two modules within a neural network structure, i.e., factor and beta estimates, for which we propose a novel contrastive adversarial variational Bayes (CAVB) framework. To exploit the factor structure, we employ adversarial variational Bayes that transforms the maximum likelihood problem into a zero-sum game between a variational autoencoder (VAE) and a generative adversarial network (GAN), where an auxiliary discriminative network brings in arbitrary expressiveness to the inference model. To tackle the problem of learning indistinguishable feature representations in the beta network, we introduce a contrastive loss to learn distinctive hidden features of the factor loadings in correspondence to conditional quantiles of return distributions. CAVB establishes a robust relation between the cross-section of asset returns and the common latent factors with nonlinear factor loadings. Extensive experiments show that CAVB not only significantly outperforms prominent models in the existing literature in terms of out-of-sample total and predictive R2s, but also delivers superior Sharpe ratios after transaction costs for both long-only and long-short portfolios.

Item Type:	Book Section
Additional Information:	© 2025 International Joint Conferences on Artificial Intelligence
Divisions:	Data Science Institute Mathematics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited:	23 May 2025 07:39
Last Modified:	02 Jun 2025 23:19
URI:	http://eprints.lse.ac.uk/id/eprint/128164

Actions (login required)

View Item