Bump sdk_version to 5.49.1 (fix Python 3.13 pydub incompatibility)

requirements.txt

@@ -1,7 +1,27 @@
-gradio>=4.0
-matplotlib>=3.8
-numpy>=1.26,<3
-pandas>=2.1
-scikit-learn>=1.3
-scipy>=1.11
-xgboost>=2.0
+---
+title: AAPL Triple-Barrier Direction Classifier
+emoji: 📊
+colorFrom: blue
+colorTo: gray
+sdk: gradio
+sdk_version: "5.49.1"
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# AAPL Triple-Barrier Direction Classifier (educational)
+
+Reference-backed financial-ML demo. XGBoost classifier trained on
+fractionally-differenced features and triple-barrier labels (López de Prado,
+*Advances in Financial Machine Learning*, Ch.3 + Ch.5).
+
+**This is an educational portfolio artifact, not a trading signal.**
+Test-set accuracy ~38% on a 3-class label set (random = 33%, p<0.05 in 3 of 5
+purged folds). Directional accuracy *when the model picks a side* is ~36% —
+worse than coin-flip. Do not trade real money on this.
+
+![Gradio interface](app_screenshot.png)
+
+Full source, technical writeup, and lessons-learned:
+[github.com/moccaram/DataSynth](https://github.com/moccaram/DataSynth).