Deep Learning for Forecasting Stock Returns in the Cross-Section

By Masaya Abe, Hideki Nakayama. 2018

100 citations recorded by the source corpus.

Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper implements deep learning to predict one-month-ahead stock returns in the cross-section in the Japanese stock market and investigates the performance of the method. Our results show that deep neural networks generally outperform shallow neural networks, and the best networks also outperform representative machine learning models. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section.

Subfields: Finance, Management Science and Operations Research, Economics & Operations Research, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

1. M. Ugur Gudelek
2. A. Ozbayoglu
3. Omer Berat Sezer
4. Longbing Cao
5. Ze Hu
6. Matloob Khushi
7. Yiqi Zhao
8. Weiwei Jiang

In Management Science and Operations Research

1. M. Ugur Gudelek
2. Omer Berat Sezer
3. A. Ozbayoglu
4. Longbing Cao
5. Ze Hu
6. Matloob Khushi
7. Yiqi Zhao
8. Weiwei Jiang

In Economics & Operations Research

1. A. Ozbayoglu
2. M. Ugur Gudelek
3. Ze Hu
4. Longbing Cao
5. Omer Berat Sezer
6. Matloob Khushi
7. Yiqi Zhao

In Time-Series & Forecasting

1. M. Ugur Gudelek
2. Longbing Cao
3. Omer Berat Sezer
4. A. Ozbayoglu
5. Ze Hu
6. Matloob Khushi
7. Yiqi Zhao
8. Weiwei Jiang

Citations in the corpus

• Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, methodology): “In [96], DNN model and 25 fundamental features were used for the prediction of the Japan Index constituents.”
• A Survey of Forex and Stock Price Prediction Using Deep Learning (2021, methodology): “paper [33] used the LSTM-based model; papers [70,71] used the DNN-based model; papers [78,79] used the reinforcement learning based model; and papers [84,87–91] used other deep learning methods.”
• AI in Finance: Challenges, Techniques, and Opportunities (2021, methodology): “The direct applications of DNNs consist of CNNs to model multi-market/sector/factor correlations and dependencies by embedding each factor as an input, RNNs like LSTM and bidirectional RNN to sequentially model multi-market/sector/factor time series, deep transfer learning to model cross-sectional i”