This hackathon presents a rich, unstructured text dataset consisting of approximately 1.56 lakh rows. The primary challenge is to classify these raw text descriptions into subcategories then into categories. While the names of the categories and subcategories are provided, participants are expected to explore the dataset to understand and define the meaning and context of each category. Participants are expected to ensure that the definitions of these categories and subcategories are aligned with Government of India rules and regulations.
Please download these datasets to create projects and only then proceed to fill the form.
Go through the datasets usage guidelines before accessing the datasets.