Time Series Forecasting Using LSTM Networks: A Symbolic Approach

TL;DR

This paper introduces a symbolic representation combined with LSTM networks to improve time series forecasting, reducing sensitivity to hyperparameters and enabling faster training while maintaining accuracy.

Contribution

It proposes a novel symbolic approach integrated with LSTM networks to address limitations of traditional methods in time series forecasting.

Findings

Symbolic representation reduces hyperparameter sensitivity.

Faster training without loss of forecast accuracy.

Improved robustness of LSTM models with symbolic data.

Abstract

Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural network with a dimension-reducing symbolic representation is proposed and applied for the purpose of time series forecasting. It is shown that the symbolic representation can help to alleviate some of the aforementioned problems and, in addition, might allow for faster training without sacrificing the forecast performance.