Banking sentiment — educational fine-tuning demo

DistilBERT adapted to synthetic English banking feedback. Labels: 0 NEGATIVE, 1 POSITIVE.

Data and evaluation

480 templated rows from 40 manually written synthetic scenarios. Scenario-disjoint, stratified 60/20/20 split; 288 training, 96 validation and 96 test rows. Only 8 independent scenarios in the test set. No real customer data was used. The best epoch was selected using validation accuracy.

Metric	Value
Baseline test accuracy	0.8854
Fine-tuned test accuracy	1.0000
Best validation accuracy	1.0000

Limitations

Educational demonstration, not validated for production, lending, compliance or customer decisions. Limited English examples, binary sentiment only; no neutral class. Template repetition makes evaluation optimistic relative to real feedback. Performance on real banking feedback and other languages is unknown.

Training

transformers 4.57.1; learning rate 2e-5; 4 epochs; batch size 8; seed 42. Base model: https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english

Loading…

Jagdish11/banking-sentiment-distilbert-demo

Banking sentiment — educational fine-tuning demo

Data and evaluation

Limitations

Training

Banking sentiment — educational fine-tuning demo

Data and evaluation

Limitations

Training