Optimization of Deep Learning Models for Dynamic Market Behavior Prediction

TL;DR

This paper introduces a hybrid deep learning model for multi-horizon demand forecasting in retail, demonstrating improved accuracy and robustness over existing methods using strict evaluation protocols.

Contribution

The paper presents a novel hybrid sequence model combining temporal convolutions, gated recurrent units, and self-attention for retail demand prediction, with comprehensive benchmarking and reproducibility.

Findings

Consistent accuracy improvements over ARIMA, Prophet, LSTM, GRU, LightGBM, and Transformer models.

Enhanced robustness during peak and holiday periods.

Statistically significant performance gains validated by ablation studies.

Abstract

The advent of financial technology has witnessed a surge in the utilization of deep learning models to anticipate consumer conduct, a trend that has demonstrated considerable potential in enhancing lending strategies and bolstering market efficiency. We study multi-horizon demand forecasting on e-commerce transactions using the UCI Online Retail II dataset. Unlike prior versions of this manuscript that mixed financial-loan narratives with retail data, we focus exclusively on retail market behavior and define a clear prediction target: per SKU daily demand (or revenue) for horizons H=1,7,14. We present a hybrid sequence model that combines multi-scale temporal convolutions, a gated recurrent module, and time-aware self-attention. The model is trained with standard regression losses and evaluated under MAE, RMSE, sMAPE, MASE, and Theil's U_2 with strict time-based splits to prevent leakage. We benchmark against ARIMA/Prophet, LSTM/GRU, LightGBM, and state-of-the-art Transformer forecasters (TFT, Informer, Autoformer, N-BEATS). Results show consistent accuracy gains and improved robustness on peak/holiday periods. We further provide ablations and statistical significance tests to ensure the reliability of improvements, and we release implementation details to facilitate reproducibility.