When Machine Learning Meets Fashion – Celine Xu, H&M Group

Session Outline

In this talk, we introduce the conflicts between Fashion and Machine learning, summarise the limitation of current image recognition capabilities for fashion feature detection, and share ideas about how could industry better leverage machine learning in fashion industry.

Key Takeaways:

• Use machine learning to predict customer social belonging
• Focus on identifying multiple objects in the same picture and mapping the relationship between combinations and styles
• Customers can have multiple “fashion styles” – we should encourage them try different styles and support with professional guidance