Analytics Competition hosted by the Analytics Club IITM in association with Techsoc IITM, as part of Pre Inter IIT Season
Company X has a catalog which consists of billions of products that belong to Hundreds of categories. Categories are used to help customer navigate through our website and classify products to product type groups. Hence, it is important to predict the node assignment at the time of listing of the product or when the browse node information is absent.
As part of this hackathon, you will use product metadata to classify products into categories. You will have access to product title, description, bullet points etc. and labels for ~40K products to train and test your submissions.
The Key Challenge of this competition lies in providing a low latency solution while maintaining a high classification accuracy.
The Final Kaggle Contest Leaderboard will hold a 60% weightage in the final standings. 20% of the weightage will be based on the time of execution of your code (this code should run only inference and not the whole pipeline, details will be shared near the competition deadline). The remaining 20% is a score that will be awarded for the Novelty of your solution. The novelty will be scored by the Analytics Club Core Team.
The metric used for this competition is Classification Accuracy.
Aryan Pandey. (2021). Deep Learning Hackathon. Kaggle. https://kaggle.com/competitions/techsoc-analytics-21-22