Customer-Targeted E-Commerce Recommendation System with Attention-Based Multi-Scale Feature Fusion

Abstract

Customer-Targeted E-Commerce Recommendation System presents a fundamental challenge in Recommendation Systems, E-Commerce. Existing approaches, including CollabFilter, SVD++, and NMF, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing EComRec, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on Amazon Electronics using stratified 10-fold crossvalidation. Our method achieves a mean map@10 of 88.2% on the primary benchmark, surpassing the nearest baseline by 7.7 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 20.1% reduction in computational cost relative to comparable hybrid architectures and convergence within 85 epochs on all benchmark datasets.