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

02/07/2022
by   Etienne David, et al.
0

Developing models and algorithms to draw causal inference for 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 the first fashion 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 behaviors of influencers. Secondly, to leverage such a complex and rich 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/07/2020

Knowledge Enhanced Neural Fashion Trend Forecasting

Fashion trend forecasting is a crucial task for both academia and indust...
research
05/07/2021

Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media

Fashion trend forecasting is of great research significance in providing...
research
10/14/2020

Graph Deep Factors for Forecasting

Deep probabilistic forecasting techniques have recently been proposed fo...
research
06/30/2021

Long Short-term Cognitive Networks

In this paper, we present a recurrent neural system named Long Short-ter...
research
02/15/2021

Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series

We propose a new model for networks of time series that influence each o...
research
04/08/2022

Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products

Estimating the preferences of consumers is of utmost importance for the ...
research
02/08/2021

Changepoint detection on a graph of time series

When analysing multiple time series that may be subject to changepoints,...

Please sign up or login with your details

Forgot password? Click here to reset