Context-Aware Fintech User Feedback Classification

Context-Aware Fintech User Feedback Classification & Urgency Detection

Most feedback tools stop at sentiment; positive or negative. This project goes further by building a decision-driven NLP system that classifies fintech user feedback by issue type and detects operational urgency, enabling smarter triage and escalation.

What was built:

Two machine learning models trained on manually collected and annotated app store reviews from real fintech platforms like Revolut, Wise, and Monzo:

Issue Classifier: categorizes feedback into 9 classes including transaction issues, account security, KYC, refunds, app performance, and fraud

Urgency Detector: binary classifier that flags high-risk feedback requiring immediate attention, optimized for recall to minimize missed critical cases