Guest
Pawel Jankiewicz and Konstantin Lopuhin share their winner’s solution of Kaggle Mercari Price Suggestion Challenge. In this competition, Kagglers were challenged to build an algorithm that automatically suggests the right product prices based on user-inputted text descriptions of their products, including details like product category name, brand name, and item condition. From this video you will learn: - Code competition tricks - Why to use MLP (and sparse MLP) - Cheap feature binarization - Optimization: one model per core - Didn’t work ideas and other teams solution Slides: Github: Yandex hosts biweekly training sessions on machine learning. These meetings offer an opportunity for the participants of data analysis contests to meet, talk, and exchange experience. Each of these events is made up of a practical session and a report. The problems are taken from Kaggle and similar platforms. The reports are given by successful participants of recent contests, who share their strategies and talk about the techniques used by their competitors.
