Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500

By Christopher Krauss, Xuan Anh Do, Nicolas Huck. 2017

670 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Management Science and Operations Research, Model Architectures

How researchers see this paper

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

In Economics and Econometrics

1. Omer Berat Sezer
2. A. Ozbayoglu
3. M. Ugur Gudelek
4. Mathias Kraus
5. Sami ben Jabeur
6. Jean-Laurent Viviani
7. Sima Siami‐Namini
8. Salma Mefteh-Wali

In Finance

1. M. Ugur Gudelek
2. A. Ozbayoglu
3. Omer Berat Sezer
4. Longbing Cao
5. Mathias Kraus
6. Sami ben Jabeur
7. Jean-Laurent Viviani
8. Sima Siami‐Namini

In Management Science and Operations Research

1. M. Ugur Gudelek
2. Omer Berat Sezer
3. A. Ozbayoglu
4. Longbing Cao
5. Sami ben Jabeur
6. Salma Mefteh-Wali
7. Jean-Laurent Viviani
8. Mathias Kraus

In Model Architectures

1. M. Ugur Gudelek
2. A. Ozbayoglu
3. Omer Berat Sezer
4. Mathias Kraus
5. Sami ben Jabeur
6. Jean-Laurent Viviani
7. Sima Siami‐Namini
8. Salma Mefteh-Wali

Citations in the corpus

• Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, methodology): “The authors of [89] used price data and DNN, Gradient Boosted Trees (GBT), Random Forest (RF) methods for the prediction of the stocks in the Standard’s & Poor’s 500 Index (S&P500).”
• Deep Learning for Financial Applications : A Survey (2020, methodology): “[50] Stocks in the S&P500 1990-2015 Price data DNN, GBT, RF Mean return, MDD, Calmar ratio H2O”
• Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks (2019, methodology): “With the introduction of deep learning models, methods such as recurrent neural network (RNN) [15], convolutional neural network (CNN) [4], and long short term memory (LSTM) [9] have started appearing on implementations that are used for analyzing financial data.”
• Deep Learning for Forecasting Stock Returns in the Cross-Section (2018, background): “Krauss et al. [11] used three different machine learning models, deep neural networks, gradient-boosted trees and random forests to predict one-day-ahead stock returns for the S&P500 constituents.”
• Using deep Q-learning to understand the tax evasion behavior of risk-averse firms (2018, background): “, 2014), analysis of financial trading (Krauss et al., 2017), social networks (Perozzi et al.”
• Deep learning in business analytics and operations research: Models, applications and managerial implications (2018, background): “In regression tasks, neural networks output a continuous probability distribution, for which one frequently draws upon the KullbackLeibler divergence (Kullback & Leibler, 1951) or the Jensen-Shannon divergence (Lin, 1991).”
• The Performance of LSTM and BiLSTM in Forecasting Time Series (2019, background): “Krauss et al. [19] used various forms of forecasting models such as deep learning, gradient-boosted trees, and random forests to model S&P 500 constitutes.”
• A Comparison of ARIMA and LSTM in Forecasting Time Series (2018, background): “For instance, Krauss et al. [15] use various forms of forecasting models such as deep learning, gradient-boosted trees, and random forests to model S&P 500 constitutes.”