## 10k_filings_train.csv

This is the train set. You will train your model of choice on this data. You can split this train set into a train and validation for hyperparameter tuning. 

The column you want to predict is the `label` column. There are 9 unique sectors, so this is a multiclass classification problem. The company sectors were identified from the SEC website. While there are many more detailed sectors (under "industry" column), in this task you only have to predict the high-level sector group.

<strong> Only use the body of the 10K for features </strong>.

## 10k_filings_test_wo_labels.csv

Test set. The labels are omitted. Only submit your model's predicted sector for the test set.