Previous proposalLessons from Elasticsearch in production
Data sciences (is) in fashion @ Myntra
Ever dreamt that you can walk into a store which has been designed just for you? A store where the shelves have been stacked keeping in mind your fashion preferences only. A sales rep who understands what you wear and what’s missing in your wardrobe. Myntra is fast transforming itself into such a hyper-personalized (1:1) store and this transformation is being powered solely through analytics over big data. This talk discusses the challenges of delivering personalization at Internet scale. We present an overview of the machine learning techniques and big data technologies used to develop the system.
Fashion is a hard category to sell online given most of the purchases happen on impulse. It fundamentally differs from selling categories like mobiles which are more driven through reviews and ratings. Data sciences help bring a differentiating angle to selling fashion and can be applied in a variety of fashion e-tailing problems ranging from product rankings (the extreme form of which is personalised store for every user), store organisation and navigation, better customer engagement, better offer creation, better merchandising decisions, etc. We @ Myntra are working towards these specific problems and would love to talk about the approaches that have worked for us.
We are personalising the customer experience in multiple ways
- by personalising customer communications through various channels - by personalising the website to tailor to customers' preferences - by creating unique customer specific offers
We would as well be talking about the data platform which powers all these efforts.
Divya Alok, Devashish, Debdoot
Data scientists working at myntra. We look at tons of data and actively look towards creating data products used by our customers - external and internal.