---
license: mit
tags:
- fintech
- reconciliation
- classification
---

# FinTech Reconciliation Break Classifier (Pair-Level)

This repository contains a trained model that predicts whether a bank↔broker reconciliation **pair** is a **TRUE_BREAK (1)** or **FALSE_BREAK (0)**.

## Features Used
['large_amt_mismatch', 'amt_diff', 'amt_pct', 'amt_diff_abs', 'amt_ratio', 'settlement_gap_days', 'is_weekend', 'is_settlement_weekend']

## Best Run (selected by PR-AUC)
- Experiment: exp_001_baseline
- PR-AUC: 1.000
- ROC-AUC: 1.000
- F1: 0.998

## Files
- `model.joblib` : trained sklearn pipeline
- `features.json`: selected feature list
- `config.json`  : training metadata + best metrics
- `predict.py`   : minimal inference helper