English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

New fashion product sales forecasting is a challenging problem that involvesmany business dynamics and cannot be solved by classical forecastingapproaches. In this paper, we investigate the effectiveness of systematicallyprobing exogenous knowledge in the form of Google Trends time series andcombining it with multi-modal information related to a brand-new fashion item,in order to effectively forecast its sales despite the lack of past data. Inparticular, we propose a neural network-based approach, where an encoder learnsa representation of the exogenous time series, while the decoder forecasts thesales based on the Google Trends encoding and the available visual and metadatainformation. Our model works in a non-autoregressive manner, avoiding thecompounding effect of large first-step errors. As a second contribution, wepresent VISUELLE, a publicly available dataset for the task of new fashionproduct sales forecasting, containing multimodal information for 5577 real, newproducts sold between 2016-2019 from Nunalie, an Italian fast-fashion company.The dataset is equipped with images of products, metadata, related sales, andassociated Google Trends. We use VISUELLE to compare our approach againststate-of-the-art alternatives and several baselines, showing that our neuralnetwork-based approach is the most accurate in terms of both percentage andabsolute error. It is worth noting that the addition of exogenous knowledgeboosts the forecasting accuracy by 1.5% in terms of Weighted AbsolutePercentage Error (WAPE), revealing the importance of exploiting informativeexternal information. The code and dataset are both available athttps://github.com/HumaticsLAB/GTM-Transformer.

Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends