# Fashion Outfit Generation for E-commerce

arXiv: https://arxiv.org/abs/1904.00741 · HTML: https://mlsanity.com/paper/1904.00741/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2019.

## Built on by (most cited first, 6 of 6)

- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model](https://mlsanity.com/paper/2504.17826/) (2025)
- [fAshIon after fashion: A Report of AI in Fashion](https://mlsanity.com/paper/2105.03050/) (2021)
- [Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs](https://mlsanity.com/paper/2402.05941/) (2024)
- [Recommendation of Compatible Outfits Conditioned on Style](https://mlsanity.com/paper/2203.16161/) (2022)
- [An Application to Generate Style Guided Compatible Outfit](https://mlsanity.com/paper/2205.00663/) (2022)

## Abstract (arXiv)

Combining items of clothing into an outfit is a major task in fashion retail. Recommending sets of items that are compatible with a particular seed item is useful for providing users with guidance and inspiration, but is currently a manual process that requires expert stylists and is therefore not scalable or easy to personalise. We use a multilayer neural network fed by visual and textual features to learn embeddings of items in a latent style space such that compatible items of different types are embedded close to one another. We train our model using the ASOS outfits dataset, which consists of a large number of outfits created by professional stylists and which we release to the research community. Our model shows strong performance in an offline outfit compatibility prediction task. We use our model to generate outfits and for the first time in this field perform an AB test, comparing our generated outfits to those produced by a baseline model which matches appropriate product types but uses no information on style. Users approved of outfits generated by our model 21% and 34% more frequently than those generated by the baseline model for womenswear and menswear respectively.