040

Title:

Latent Factor Model for Asset Pricing

Discipline: Business Data Science

Presenter:

Ajim Uddin

Abstract:

One of the fundamental question in asset pricing is ‘Why different assets earn different average returns?’ In this paper, we created an Autoencoder based asset pricing model to explain the return difference among the stocks in an index. The trained Autoencoder generates a set of latent factors that we used to implement a combined –‘communal’- factor that better explains a large portion of the return differences among the stocks in an index. After analyzing all the stocks in S&P-500, Russel-3000, and NASDAQ-100, we found that our proposed latent factor model can outperform many other factors models in predicting the next day's return. Particularly, the experiment results show that non-communal stocks earn 0.05% over communal stocks on average. However, the risk associated with this non-communal stock is also 0.8% higher than communal stocks. The experiments confirm that the superior performance comes from the compensation of high risk associated with these non-communal stocks. Investors will benefit from our latent factor model to identify these communal and non-communal stocks for earning a high return while diversifying their asset portfolio.

Author(s):

Ajim Uddin and Dantong Yu

Funding Acknowledgements:

nan