Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks

By L. Takeuchi. 2013

Subfields: Economics & Operations Research

How researchers see this paper

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

In Economics & Operations Research

Citations in the corpus

Deep Learning for Financial Applications : A Survey (2020, methodology): “[127] classified the stocks in two classes, low momentum and high momentum depending on their expected return.”
Statistical Arbitrage in Cryptocurrency Markets (2019, methodology): “With this approach, we follow the logic of Takeuchi and Lee (2013) and transfer it to minute-binned data with the aim of forecasting the return of the next two hours or 120 min, while using information of the returns of the last 24 h.”
Decision support from financial disclosures with deep neural networks and transfer learning (2017, methodology): “Here previous research utilizes an autoencoder composed of stacked restricted Boltzmann machines in order to predict future stock prices based on historic time series [33].”
Using deep learning to detect price change indications in financial markets (2017, methodology): “Similarly in [2], a Restricted Boltzmann Machine (RBM) is used to encode monthly closing prices of stocks and then it is fine-tuned to predict the direction the price of each stock will move (above or below the median change).”
Stock prediction using deep learning (2016, methodology): “A paper which uses autoencoders to extract features from the input variables has been proposed for stock trading strategies [27].”
An innovative neural network approach for stock market prediction (2018, methodology): “…Deep Belief Networks-Multi-layer Perceptron (DBN-MLP) via particle swarm optimization (PSO) to predict the chaotic time series [16]; Takeuchi chose the earnings of t-13 to t-2 months and previous 20 days as input, using multiple RBM models to classify US stocks with over 53% of accuracy [17].”
Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks (2017, methodology): “Given some input features machine learning models can be used to predict the behaviour of various aspects of financial markets [1], [2], [3], [4].”
News-based trading strategies (2016, methodology): “A recent research paper [30] utilizes deep learning to train an autoen-coder of stacked restricted Boltzmann machines (RBM) to extract features from stock movements.”
Stock Market Embedding and Prediction: A Deep Learning Method (2018, methodology): “Takeuchi & Lee (2013) [19] also use a 5-layer Autoencoder of the stacked Boltzmann machine to enhance Momentum trading strategies that generate 45.93% annualized return.”
Cloning Strategies from Trading Records using Agent-based Reinforcement Learning Algorithm (2018, methodology): “[6] applied autoencoder to extract features from the history stock price.”
Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500 (2017, background): “In other words, we follow Takeuchi and Lee (2013) and ﬁrst focus on the returns of the ﬁrst 20 days, approximately corresponding to one trading month.”