Deep Learning based Forecasting: a case study from the online fashion industry

TL;DR

This paper presents a deep learning forecasting approach tailored for the online fashion industry, addressing unique challenges like high data volume, catalog turnover, and inventory constraints, with empirical validation of its effectiveness.

Contribution

It introduces a specialized deep learning model that accounts for inventory constraints and price-demand relationships in fashion demand forecasting.

Findings

The approach improves forecast accuracy over standard models.

Empirical results demonstrate effectiveness in real industry data.

Addresses catalog turnover and inventory issues explicitly.

Abstract

Demand forecasting in the online fashion industry is particularly amendable to global, data-driven forecasting models because of the industry's set of particular challenges. These include the volume of data, the irregularity, the high amount of turn-over in the catalog and the fixed inventory assumption. While standard deep learning forecasting approaches cater for many of these, the fixed inventory assumption requires a special treatment via controlling the relationship between price and demand closely. In this case study, we describe the data and our modelling approach for this forecasting problem in detail and present empirical results that highlight the effectiveness of our approach.