Hi, I'm Rohit 馃憢 I'm a data scientist.
馃捇 I build Big Data solutions for PocketFm using machine learning, causal inference and optimization models. 馃敪 I'm currently building Recommendation systems, content moderation systems and other goofy stuff. 馃槄 Fun fact: After completing my Bachelor's, I went to Ireland to pursue Masters in Structural Engineering. My thesis involved implementation of AI and during that time I fell in love with Machine Learning so much, that I decided to pursue a career in it.
I'm best reached via [email : work.rmehra@gmail.com]. I'm always open to interesting conversations and collaboration.
I am available for mentoring, interview preparation and upskilling.
Feb 9, 2024 路 3 min read 路 Popular items are recommended even more frequently than their popularity would warrant The long-tail phenomenon is common in RS data: in most cases, a small fraction of popular items account for most user interactions When trained on such long-tail...
Join discussion
Sep 7, 2023 路 2 min read 路 In the world of recommendation systems, the quest for simplicity often leads to remarkable breakthroughs. The "Embarrassingly Shallow Autoencoders for Sparse Data," or EASE, is one such breakthrough that combines simplicity with state-of-the-art perf...
Join discussion
Dec 27, 2022 路 4 min read 路 Explicit v.s. Implicit ratings Two ways to gather user preference data to recommend items, Ask for explicit ratings from a user, on a rating scale (such as rating a movie from one to five stars). The drawback is it puts the responsibility of data co...
Join discussion