Long Short-Term Memory Neural Network for Financial Time Series
Ensemble of LSTM neural networks predicts stock price movements, outperforming traditional methods on Stockholm OMX30 index.
What it examines
This paper presents an ensemble of independent and parallel LSTM neural networks to predict stock price movements, focusing on the Stockholm OMX30 index. The study aims to demonstrate the advantages of LSTM-based approaches over traditional methods and other machine learning models in financial time series analysis.
What it concludes
The study concludes that LSTM-based portfolios offer higher returns and lower volatility compared to traditional methods. Potential applications include improved trading strategies and risk management. Future research could explore learning rate decay, systematic retraining, and weighted trading strategies to enhance performance further.
Evidence objects
The study concludes that LSTM-based portfolios offer higher returns and lower volatility compared to traditional methods. Potential applications include improved trading strategies and risk management. Future research could explore learning rate decay, systematic retraining, and weighted trading strategies to enhance performance further.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: Performance forecasting is an age-old problem in economics and finance. Recently, developments in machine learning and neural networks have given rise to non-linear time series models that provide modern and promising alternatives to traditional methods of analysis. In this paper, we present an ensemble of independent and parallel long short-term memory (LSTM) neural networks for the prediction of… ▽ More Performance forecasting is an age-old problem in economics and finance. Recently, developments in machine learning and neural networks have given rise to non-linear time series models that provide modern and promising alternatives to traditional methods of analysis. In this paper, we present an ensemble of independent and parallel long short-term memory (LSTM) neural networks for the prediction of stock price movement. LSTMs have been shown to be especially suited for time series data due to their ability to incorporate past information, while neural network ensembles have been found to reduce variability in results and improve generalization. A binary classification problem based on the median of returns is used, and the ensemble's forecast depends on a threshold value, which is the minimum number of LSTMs required to agree upon the result. The model is applied to the constituents of the smaller, less efficient Stockholm OMX30 instead of other major market indices such as the DJIA and S&P500 commonly found in literature. With a straightforward trading strategy, comparisons with a randomly chosen portfolio and a portfolio containing all the stocks in the index show that the portfolio resulting from the LSTM ensemble provides better average daily returns and higher cumulative returns over time. Moreover, the LSTM portfolio also exhibits less volatility, leading to higher risk-return ratios. △ Less
Source row: 1238 · abstract type: unknown