Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain

TL;DR

This paper introduces a Multi-Task Temporal Fusion Transformer that jointly forecasts sales and inventory in Amazon's e-commerce supply chain, leveraging diverse data sources for improved accuracy and operational decision-making.

Contribution

It presents a novel deep learning framework that simultaneously predicts sales and inventory metrics, capturing complex temporal and cross-task dependencies in large-scale e-commerce data.

Findings

Outperforms baseline models like LSTM and GRU in accuracy.

Reduces sales RMSE by 6.2% compared to single-task TFT.

Enhances inventory forecasting with a 6.4% reduction in RMSE.

Abstract

Efficient inventory management and accurate sales forecasting are critical challenges in large-scale e-commerce platforms such as Amazon, where stockouts and overstocking can lead to substantial financial losses and operational inefficiencies. Traditional single-task forecasting models, which focus solely on sales or inventory, often fail to capture the complex temporal dependencies and cross-task interactions that characterize real-world supply chain dynamics. To address this limitation, this study proposes a Multi-Task Temporal Fusion Transformer (TFT-MTL) framework designed for joint sales and inventory forecasting within the Amazon e-commerce ecosystem. The model integrates heterogeneous data sources, including historical sales records, warehouse inventory levels, pricing, promotions, and event-driven factors such as holidays and Prime Day campaigns, through a unified deep learning architecture. A shared encoder captures long-term temporal patterns, while task-specific decoder heads predict sales volume, inventory turnover, and stockout probability simultaneously. Experiments on large-scale real-world datasets demonstrate that the proposed TFT-MTL model significantly outperforms baseline methods such as LSTM, GRU, and single-task TFT. Compared with the single-task TFT model, the proposed approach achieves a 6.2% reduction in Sales RMSE, a 12.7% decrease in Sales MAPE, a 6.4% reduction in Inventory RMSE, and a 12.4% decrease in Inventory MAPE. These results confirm the model's ability to effectively capture multi-dimensional dependencies across supply chain variables. The proposed framework provides an interpretable, data-driven decision support tool for optimizing Amazon's inventory scheduling and demand planning strategies.