RESI Baseline Model (SN46)
XGBoost-based real estate price prediction model for Bittensor Subnet 46 (RESI).
Model Details
- Input: 79 float32 features (51 numeric + 28 boolean)
- Output: 1 float32 predicted sale price (USD)
- Format: ONNX (opset 15)
- Size: ~6.9 MB
- Training: 200K synthetic US residential property samples
- Test MAPE: 12.63%
License
MIT
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support