ArXiv is a public service repository and open-source archive for scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics.
In this data challenge, you are given a dataset that contains abstracts and categories columns that are collected from the arXiv portal. There are altogether 157 subject categories. For this competition, you have been provided with dataset having 23 classes. You will have to classify the data into those classes.

**Your task is to build a model to predict the category given paper abstract and title.**

Note that the provided dataset is very imbalanced posing a different challenge and providing a great opportunity to flex your NLP muscles and solve an exciting problem!
Please refer to [this file ]
(https://drive.google.com/file/d/1u8J2hLaNE3cckJmEOM1oEsD11MfC1555/view?usp=share_link)
to check the distribution of classes.