README.md

---
title: Busy Module XGBoost
emoji: 🎯
colorFrom: purple
colorTo: blue
sdk: docker
app_port: 7860
pinned: false
---

# Busy Detector — XGBoost Inference

Binary classifier predicting busy probability from 26 features (17 voice + 9 text).

## API

**POST** `/predict`
```json
{
  "inputs": {
    "audio_features": { "v1_snr": 15.0, "v2_noise_traffic": 0.0, ... },
    "text_features":  { "t1_explicit_busy": 0.0, ... }
  }
}
```

**Response:**
```json
{
  "busy_score": 0.32,
  "confidence": 0.65,
  "recommendation": "CHECK_IN",
  "ml_probability": 0.28,
  "evidence_details": ["ML Baseline (-0.5)"]
}
```