EMP: Enhanced Multi-modal Prediction for fashion sales using Fourier Mapping and ERP-based contrastive learning
Sanguk Park, Byungyoon Park, Seohyun Lee, Subin Shin, Wooju Kim · 2026
Read EMP: Enhanced Multi-modal Prediction for fashion sales using Fourier Mapping and ERP-based contrastive learning by Sanguk Park, Byungyoon Park, Seohyun Lee, Subin Shin, Wooju Kim (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13271468.txt.
Description
Sanguk Park is lead author of a 2026 journal article presenting EMP, a model for predicting sales of brand-new fashion products, which have no sales history to learn from. The model combines product images and text with the sales patterns of similar older items, rather than relying on outside data services.
The first stage finds reference items using a distance measure built for wiggly real-valued time series, creating a meaningful comparison space. The second stage, a transformer model, forecasts twelve weeks of sales using a Fourier mapping that keeps the true size of sales values readable. The authors argue this preserves both slow trends and sharp weekly swings better than standard scaling.
Catalog record
| CREATOR | Sanguk Park, Byungyoon Park, Seohyun Lee, Subin Shin, Wooju Kim |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78770 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |