International Conference on Computer and Knowledge Engineering

Home / 15th International Conference on Computer and Knowledge Engineering

A Synergistic Hybrid Architecture with Residual Attention and Mixture-of-Experts for Robust Hour-Ahead Forex Forecasting

Authors :

Alireza Abbaszadeh¹ Seyyed Abed Hosseini² Mohammad Reza Akbarzadeh Totonchi³

1- Department of Computer Engineering, Ma.C., Islamic Azad University, Mashhad, Iran. 2- Department of Electrical Engineering, Ma.C., Islamic Azad University, Mashhad, Iran. 3- Department of Electrical Engineering, Center of Excellence on Soft Computing and Intelligent Information Processing, Ferdowsi University of Mashhad, Mashhad, Iran

Keywords :

Deep Learning،Attention Mechanism،Residual Networks،Mixture of Experts (MoE).،Foreign Exchange Forecasting

Abstract :

Forecasting highly volatile exchange rates like EUR/USD is a critical challenge where traditional models fail to capture the associated complex and volatile nonlinear dynamics of these rates. While the modern deep learning architectures have shown considerable promise in the past few years, they also present significant variation, and achieving optimal synergy among their advanced components, such as attention and mixture-of-experts, remains an open research question. This paper introduces a novel, synergistic hybrid architecture engineered to address this gap. Our model (V8) strategically integrates a Residual Block with Multi-Head Attention (RB-MHA) for robust feature extraction, a Bidirectional LSTM for temporal modeling, and a Mixture-of-Experts (MoE) module for adaptive prediction under varying market conditions. Evaluated on over 15 years of hourly EUR/USD data using a rigorous, leak-free methodology, our model sets a new state-of-the-art performance with a Root Mean Squared Error (RMSE) of 0.001863 and an R^2 of 0.985467 on the unseen test set. This result constitutes a 44.1% reduction in RMSE over a strong deep learning baseline (V1), demonstrating the significant impact of our synergistic design and establishing a new benchmark for hour-ahead forex forecasting.

Papers List

List of archived papers

HV-RCE: Reducing Network Bandwidth Usage for Video Transmission via HEVC/VVC Features in Resource-Constrained Environments

Yaghoub Saberi - Mohammadreza Forghani - Sharifeh Sadat Mirkhalaf

Farsi Optical Character Recognition Using a Transformer-based Model

Fatemeh Asadi Zeydabadi - Elham Shabaninia - Hossein Nezamabadi-pour - Melika Shojaee

Parallel Local Feature Selection For High-dimensional Data

Zhaleh Manbari - Chiman Salavati - Fardin AkhlaghianTab - Barzan Saeedpoor - Himan Delbina - Mahmud Abdulla Mohammad

Bridging Knowledge and Language Models in Healthcare: A RAG Survey

Seyedali Hasanzadeh - Fahimeh Ghasemian - Elham Shabaninia

Lightweight Local Transformer for COVID-19 Detection Using Chest CT Scans

Hojat Asgarian Dehkordi - Hossein Kashiani - Amir Abbas Hamidi Imani - Shahriar Baradaran Shokouhi

Balanced Learning with Optimized Extra Trees Classifier for Reliable Lithology Identification in Imbalanced Well Log Data

Ali Daneshpour - Behnam Yousefimehr - Mehdi Ghatee

Towards Transparent and Accurate Story Point Estimation via Interpretable BERT-based Modeling

Seyed Emad Baradaran Hosseini - Maryam Khodabakhsh - Alireza Tajary - Seyedehfatemeh Karimi

Efficient Object Detection using Deep Reinforcement Learning and Capsule Networks

Sobhan Siamak - Eghbal Mansoori

Practical Implementation of Real-Time Waste Detection and Recycling based on Deep Learning for Delta Parallel Robot

Hasan Jalali - Shaya Garjani - Ahmad Kalhor - Mehdi Tale Masouleh - Parisa Yousefi

Graph Representation Learning Towards Patents Network Analysis

Mohammad Heydari - Babak Teimourpour