Wavelet Denoising and Attention-based RNN-ARIMA Model to Predict Forex Price

TL;DR

This paper introduces a hybrid model combining wavelet denoising, attention-based RNN, and ARIMA to improve forex price prediction accuracy, effectively capturing both linear and nonlinear market dynamics.

Contribution

The novel integration of wavelet denoising with attention-based RNN and ARIMA models enhances forex forecasting by addressing noise and complex market patterns.

Findings

Hybrid model achieves RMSE of 1.65 on USD/JPY data

Directional accuracy of approximately 76%

Outperforms baseline forecasting methods

Abstract

Every change of trend in the forex market presents a great opportunity as well as a risk for investors. Accurate forecasting of forex prices is a crucial element in any effective hedging or speculation strategy. However, the complex nature of the forex market makes the predicting problem challenging, which has prompted extensive research from various academic disciplines. In this paper, a novel approach that integrates the wavelet denoising, Attention-based Recurrent Neural Network (ARNN), and Autoregressive Integrated Moving Average (ARIMA) are proposed. Wavelet transform removes the noise from the time series to stabilize the data structure. ARNN model captures the robust and non-linear relationships in the sequence and ARIMA can well fit the linear correlation of the sequential information. By hybridization of the three models, the methodology is capable of modelling dynamic systems such as the forex market. Our experiments on USD/JPY five-minute data outperforms the baseline methods. Root-Mean-Squared-Error (RMSE) of the hybrid approach was found to be 1.65 with a directional accuracy of ~76%.