Consumer Complaint Classifier

Fine-tuned DistilBERT model that classifies consumer financial complaint narratives into 5 categories: credit_card, credit_reporting, debt_collection, mortgages_and_loans, retail_banking.

Trained on a 56,000-row stratified sample of the CFPB consumer complaints dataset. Achieves Macro F1 = 0.84 on the held-out test set.

Downloads last month
25
Safetensors
Model size
67M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support