Dif4FF: Leveraging Multimodal Diffusion Models and Graph Neural Networks for Accurate New Fashion Product Performance Forecasting

TL;DR

Dif4FF introduces a two-stage forecasting system combining diffusion models and graph neural networks to accurately predict sales of new fashion products, addressing domain shift issues and outperforming existing methods.

Contribution

The paper presents a novel pipeline that integrates multimodal diffusion models with GCNs for improved new fashion product sales forecasting, a significant advancement over prior deterministic models.

Findings

Achieved state-of-the-art results on VISUELLE dataset.

Demonstrated robustness in predicting sales of unseen fashion items.

Outperformed existing models in accuracy and efficiency.

Abstract

In the fast-fashion industry, overproduction and unsold inventory create significant environmental problems. Precise sales forecasts for unreleased items could drastically improve the efficiency and profits of industries. However, predicting the success of entirely new styles is difficult due to the absence of past data and ever-changing trends. Specifically, currently used deterministic models struggle with domain shifts when encountering items outside their training data. The recently proposed diffusion models address this issue using a continuous-time diffusion process. Specifically, these models enable us to predict the sales of new items, mitigating the domain shift challenges encountered by deterministic models. As a result, this paper proposes Dif4FF, a novel two-stage pipeline for New Fashion Product Performance Forecasting (NFPPF) that leverages the power of diffusion models conditioned on multimodal data related to specific clothes. Dif4FF first utilizes a multimodal score-based diffusion model to forecast multiple sales trajectories for various garments over time. The forecasts are refined using a powerful Graph Convolutional Network (GCN) architecture. By leveraging the GCN's capability to capture long-range dependencies within both the temporal and spatial data and seeking the optimal solution between these two dimensions, Dif4FF offers the most accurate and efficient forecasting system available in the literature for predicting the sales of new items. We tested Dif4FF on VISUELLE, the de facto standard for NFPPF, achieving new state-of-the-art results.