Deep Learning for Forecasting Stock Returns in the Cross-Section

Abe, Masaya; Nakayama, Hideki

doi:10.1007/978-3-319-93034-3_22

Cited by 85 publications

(45 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their Simulation outcome demonstrated the attractiveness of their proposed ensemble method compared with auto-regressive integrated moving average, generalised autoregressive conditional heteroscedasticity. Likewise, Abe et al [34] applied a deep neural network technique to predict stock price and reported that deep technique is more accurate than shallow neural networks.…”

Section: Related Work Evaluationmentioning

confidence: 99%

A comprehensive evaluation of ensemble learning for stock-market prediction

2020

View full text Add to dashboard Cite

show abstract

Section: Related Work Evaluationmentioning

confidence: 99%

A comprehensive evaluation of ensemble learning for stock-market prediction

2020

View full text Add to dashboard Cite

show abstract

“…The hyper-parameters for neural networks are chosen to define one rather shallow (NN1) and one deeper (NN3) network. The structures are comparable to those of Abe and Nakayama (2018) and the orders of magnitude are also similar to those of Gu et al (2018).…”

Section: Boosted Treesmentioning

confidence: 57%

Machine Learning in Systematic Equity Allocation: A Model Comparison

Guida¹,

Coqueret²

2018

Wilmott

View full text Add to dashboard Cite

Recent criticisms suggest that Machine Learning-based approaches only suit predicting very short-term price movements. Tony Guida and Guillaume Coqueret apply well-known ML algorithms to systematic equity investment, presenting a methodology which shows a critical stage of feature and label engineering, a step that helps uncover hidden structures in the equity market space. Only then, the authors argue, can a modern quantitative approach make accurate long-term predictions. Machine Learning 26wilmott magazine

show abstract

“…The past few years have witnessed a surging number of the applications of deep neural networks (DNNs) for forecasting financial markets. Abe and Nakayama [23] used DNNs to predict one-month-ahead cross-section stock return. Various DNN structures, with differing numbers of layers and differing numbers of neurons in each layer, were investigated.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

An Enriched Time-Series Forecasting Framework for Long-Short Portfolio Strategy

et al. 2020

View full text Add to dashboard Cite

Stock return forecasting typically requires a large number of factors and these factors usually exhibit nonlinear relations with each other. Conventional methods of stock return forecasting mainly fall into two categories: Technical Analysis and Fundamental Analysis. Technical Analysis focuses on time-series data, while Fundamental Analysis explores low-frequency fundamental variables. Although there are substantial works on either time-series analysis or fundamental analysis, few studies have enriched the time-series forecasting with fundamental variables, as the features are characterized by different frequencies, scales and types. In this paper, we propose a Long Short-Term Memory and Deep Neural Network (LSTM-DNN) hybrid model to integrate the fundamental information into time-series forecasting tasks. We demonstrate how investors can benefit from the superior performance of LSTM-DNN by constructing a long-short portfolio that takes long positions in stocks with the highest forecasting returns and short positions in stocks that are expected to decline. Extensive experimental results on real data show that our novel framework could improve the profitability of long-short portfolio strategies compared to the state-of-the-art approaches. We also find evidence indicating that the outperformance of LSTM-DNN model comes from its enhanced ability to extract information from the nonlinear relations among various features, rather than bearing more market risks. Besides the novel framework, we propose a cross-section normalization method, which benefits the framework by providing enriched cross-section signals. INDEX TERMS Hybrid deep neural networks, long-short portfolio strategy, security returns forecasting.

show abstract

Deep Learning for Forecasting Stock Returns in the Cross-Section

Cited by 85 publications

References 15 publications

A comprehensive evaluation of ensemble learning for stock-market prediction

A comprehensive evaluation of ensemble learning for stock-market prediction

Machine Learning in Systematic Equity Allocation: A Model Comparison

An Enriched Time-Series Forecasting Framework for Long-Short Portfolio Strategy

Contact Info

Product

Resources

About