HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time series

TL;DR

This paper introduces HERMES, a hybrid model for nonstationary fashion time series forecasting that integrates external signals and seasonal components, achieving state-of-the-art results on new and existing datasets.

Contribution

The paper provides a new fashion time series dataset with external influencer signals and proposes a hybrid forecasting model combining parametric, seasonal, and neural components.

Findings

State-of-the-art forecasting accuracy on fashion data

Effective integration of external influencer signals

Improved performance on M4 weekly dataset

Abstract

Developing models and algorithms to predict nonstationary time series is a long standing statistical problem. It is crucial for many applications, in particular for fashion or retail industries, to make optimal inventory decisions and avoid massive wastes. By tracking thousands of fashion trends on social media with state-of-the-art computer vision approaches, we propose a new model for fashion time series forecasting. Our contribution is twofold. We first provide publicly a dataset gathering 10000 weekly fashion time series. As influence dynamics are the key of emerging trend detection, we associate with each time series an external weak signal representing behaviours of influencers. Secondly, to leverage such a dataset, we propose a new hybrid forecasting model. Our approach combines per-time-series parametric models with seasonal components and a global recurrent neural network to include sporadic external signals. This hybrid model provides state-of-the-art results on the proposed fashion dataset, on the weekly time series of the M4 competition, and illustrates the benefit of the contribution of external weak signals.