[3Yin2] Interactive session 1

[3Yin2-43] Enhanced Quintile Portfolio for Multifactor Model with Deep Learning

〇Masaya Abe¹, Kei Nakagawa¹ (1.Nomura Asset Management Co., Ltd.)

Keywords:Finance, Deep learning, Stock prediction, Multifactor model, Portfolio

Stock return predictability is an important research theme as it reflects our economic and social organization, and significant efforts are made to explain the dynamism therein. Although machine learning methods are increasingly popular and effective in stock return prediction in the cross-section, still most of the previous studies rely on a simple quintile portfolio. In this paper, we apply deep learning for stock return prediction in the cross-section and propose a more sophisticated portfolio construction framework called Enhanced Quintile Portfolios. These portfolios are inspired by Pure Quintile Portfolio that overcome the main drawbacks of simple quintile portfolios based on a single sort. The formulation of Enhanced Quintile Portfolio is a quadratic programming problem that considers the trade-off between portfolio alpha and stock diversification, while maintaining the characteristics of a simple quintile portfolio. The experimental comparison shows that the proposed approach outperforms a simple quintile portfolio.