muBoost: An Effective Method for Solving Indic Multilingual Text Classification Problem

Text Classification is an integral part of many Natural Language Processing tasks such as sarcasm detection, sentiment analysis and many more such applications. Many e-commerce websites, social-media/entertainment platforms use such models to enhance user-experience to generate traffic and thus, revenue on their platforms. In this paper, we are presenting our solution to Multilingual Abusive Comment Identification Problem on Moj, an Indian video-sharing social networking service, powered by ShareChat. The problem dealt with detecting abusive comments, in 13 regional Indic languages such as Hindi, Telugu, Kannada etc., on the videos on Moj platform. Our solution utilizes the novel muBoost, an ensemble of CatBoost classifier models and Multilingual Representations for Indian Languages (MURIL) model, to produce SOTA performance on Indic text classification tasks. We were able to achieve a mean F1-score of 89.286 on the test data, an improvement over baseline MURIL model with a F1-score of 87.48.

Solving Fashion Recommendation -- The Farfetch Challenge

Recommendation engines are integral to the modern e-commerce experience, both for the seller and the end user. Accurate recommendations lead to higher revenue and better user experience. In this paper, we are presenting our solution to ECML PKDD Farfetch Fashion Recommendation Challenge.The goal of this challenge is to maximize the chances of a click when the users are presented with set of fashion items. We have approached this problem as a binary classification problem. Our winning solution utilizes Catboost as the classifier and Bayesian Optimization for hyper parameter tuning. Our baseline model achieved MRR of 0.5153 on the validation set. Bayesian optimization of hyper parameters improved the MRR to 0.5240 on the validation set. Our final submission on the test set achieved a MRR of 0.5257.