Со-основатель мобильного маркетплейса Lalafo
Yuriy was involved in online marketplaces business since 2008.
He managed large scale marketing campaigns for Slando in Russia, Ukraine and Kazakhstan as the Head of Marketing. In Slando Yuriy was implementing machine learning tools for marketing analysis.
Slando became part of world’s third biggest classified site Avito after a $570 million deal with Naspers; grew to the strong market leader and largest Ukrainian website in Ukraine; and became market leader and 3rd biggest website in Kazakhstan.
By the beginning of 2013 Slando traffic has grown to almost 1 billion page views monthly, reaching 27 million unique visitors across Russia, Ukraine and Kazakhstan.
After several years in Slando Yuriy co-founded Lalafo, a global C2C mobile marketplace for frictionless trade.
Lalafo is active in Asia and Europe with 3mln MAU & 700k new items per month. Unlike classic marketplaces, Lalafo is built with focus on AI as a main driver of frictionless trade.
Тема доповіді: Frictionless C2C trade with AI: is it possible to sell & buy stuff in 1 second?
- Currently it’s a huge hustle to sell or buy used stuff online. People experience many barriers like I don’t know what to sell, don’t believe anyone needs it, complexity of describing item, fraud, many items are already sold, meeting each other or delivery, accepting payments etc. It results in a fact that only 1.5% of internet population sell smth online on a monthly basis.
- At Lalafo we believe it’s possible to remove all mentioned barriers with the help of machine learning and AI. Our ideal world is where everyone trades online.
- We implement computer vision and NLP models for product description to provide a description which is much better than could be made by a human.
- We build complex algorithms for buyer and seller matching, recommend prices and train bot to help you sell faster or even sell for you. We use ML for fraud detection and even Lalafo TV advertising is measured by a ML model.
- I will describe how we do it from business side: how we structure team; how we define and evaluate machine learning projects; what challenges we face and why AI will change the way people trade.