PinnedSubir VermaMulti-objective Ranking in Large-Scale E-commerce Recommender SystemsMotivationJan 102Jan 102
PinnedSubir VermaTransformer-based Sequential Denoising Auto-Encoder: Job2VecUsing TSDAE to convert Job descriptions into Vector for Job SearchApr 17, 20222Apr 17, 20222
PinnedSubir VermaSemantic Search with S-BERT is all you needBuilding In-house Semantic Search Engine from Scratch — Fast and AccurateJun 5, 202114Jun 5, 202114
Subir VermaRetrieval-Augmented Generation — Deep DiveLet’s try to break down RAG architecture and understand components and intuition behind why they workJan 30Jan 30
Subir VermaEvent-Driven Microservices in Data ScienceEvent-driven microservices communicate with each other via event messages. When business events occur, producers publish them with…Mar 25, 2022Mar 25, 2022
Subir VermaPersonalization and Recommendation with Contextual Bandits 🤖Simulate a content personalization scenario with Vowpal Wabbit using contextual bandits to make choices between actions in a given context.Dec 1, 20212Dec 1, 20212
Subir VermaBehavior Sequence Transformer** Paper Study of Alibaba’s SOTA RecSys **Oct 18, 2021Oct 18, 2021
Subir VermaSearch, Rank, and RecommendationsEasy way to re-rank search results and personalized recommendations.Jul 5, 20211Jul 5, 20211
Subir VermaAdversarial Validation: Battling OverfittingAdversarial validation is an extremely useful method and allows you to quickly check the similarity between features in train and test.Jun 23, 2020Jun 23, 2020
Subir VermaSmart Text Pre-ProcessingOut of the box NLP Libraries for text cleaningJun 11, 2020Jun 11, 2020