← Back to all models
AVM model details: New York, New York, United States
Performance metrics for AVMs in this location.
Model type
Select the type of valuation model you want to view.
List price estimation model
Estimates list prices in this location from historical data and market trends.
Key performance metrics
| Median Absolute Percentage Error (M. MAPE) | 12.3% | Half of our predictions are within this percentage of the actual value |
| Testing R² Score | 0.840 | How much of the price variation our model explains |
| Root Mean Square Error | $1,283,436 | Average prediction error in the local currency |
| Mean Absolute Error | $337,193 | Average absolute difference between predicted and actual |
Accuracy distribution
Percentage of predictions within various error ranges
| Within 5% | 22.6% |
| Within 10% | 42.4% |
| Within 15% | 58.2% |
| Within 20% | 69.6% |
Prediction bias analysis
Does the model tend to overestimate or underestimate?
| Mean Bias | -$74,061 | Average prediction bias (+ means overestimate) |
| Median Bias | -$10,003 | Typical prediction bias |
| Over-prediction Rate | 47.0% | Percentage of predictions that are above the actual value |
| Under-prediction Rate | 53.0% | Percentage of predictions that are below actual value |
Error distribution percentiles
The absolute error amount at different percentiles - for example, '90th percentile: $50,000' means 90% of predictions have errors less than $50,000
| Percentile | 10th | 25th | 50th | 75th | 90th | 95th |
|---|---|---|---|---|---|---|
| Error Amount | $17,574 | $46,103 | $109,965 | $255,544 | $576,240 | $1,095,979 |
Model configuration & training
| Training Samples | 181979 |
| Testing Samples | 10710 |
| Training R² | 0.850 |
| Testing R² | 0.840 |
| Last Updated | 2026-11-11 |
Additional performance metrics
| Mean Absolute Percentage Error | 22.0% | Average percentage error across all predictions |
| Forecast Standard Deviation | $1,281,298 | Spread of prediction errors |
| Coefficient of Variation | 92.7% | Relative variability of predictions |
| 10th Percentile Error % | 2.2% | 10% of predictions have error less than this |
| 90th Percentile Error % | 41.7% | 90% of predictions have error less than this |