Real-time Forecasting of Time Series in Financial Markets Using Sequentially Trained Many-to-one LSTMs

TL;DR

This paper introduces a sequentially trained many-to-one LSTM approach for real-time financial time series forecasting, demonstrating improved accuracy over traditional models across stock, cryptocurrency, and commodity markets.

Contribution

The paper proposes a novel training procedure for LSTMs that maintains higher accuracy in real-time predictions by sequentially updating the model with previous predictions.

Findings

Outperforms extended Kalman filter, AR, and ARIMA models in accuracy

Maintains superior accuracy as testing progresses

Effective across diverse financial markets

Abstract

Financial markets are highly complex and volatile; thus, learning about such markets for the sake of making predictions is vital to make early alerts about crashes and subsequent recoveries. People have been using learning tools from diverse fields such as financial mathematics and machine learning in the attempt of making trustworthy predictions on such markets. However, the accuracy of such techniques had not been adequate until artificial neural network (ANN) frameworks were developed. Moreover, making accurate real-time predictions of financial time series is highly subjective to the ANN architecture in use and the procedure of training it. Long short-term memory (LSTM) is a member of the recurrent neural network family which has been widely utilized for time series predictions. Especially, we train two LSTMs with a known length, say $T$ time steps, of previous data and predict only one time step ahead. At each iteration, while one LSTM is employed to find the best number of epochs, the second LSTM is trained only for the best number of epochs to make predictions. We treat the current prediction as in the training set for the next prediction and train the same LSTM. While classic ways of training result in more error when the predictions are made further away in the test period, our approach is capable of maintaining a superior accuracy as training increases when it proceeds through the testing period. The forecasting accuracy of our approach is validated using three time series from each of the three diverse financial markets: stock, cryptocurrency, and commodity. The results are compared with those of an extended Kalman filter, an autoregressive model, and an autoregressive integrated moving average model.