Abhay is a Senior Machine Learning Engineer at Instacart and works on large scale machine learning problems which help Instacart in improving the quality of their service. As a data science professional for the past 6 years, he's worked on various ML problems in banking, insurance, fintech, marketing, and logistics domains. He got his Masters in Data Science from Columbia University and went to IIT Madras, Chennai for an undergraduate degree in Electrical Engg. In order to provide the best quality of service to our customers, knowing which items are available in which partner stores is of utmost importance to Instacart. Every time a customer's personal shopper scans an item into their cart or marks an item as “not found”, we get information that helps us make granular predictions of an item’s in-store availability. This helps us set accurate expectations for out-of-stock items and recommend appropriate replacements for items likely to be out-of-stock. In this talk, we'll discuss how we trained the availability model, how the model was productionized to score over 250 million items every half an hour and how we actually use the predictions to improve our key metrics throughout the product. We've already talked about the first question in this blog post (
0 Comments