A model card provides brief, transparent, responsible reporting for a trained machine learning model.

Model details

Intended use

Important aspects/factors

Metrics

Training data & evaluation data

Quantitative analyses

Overall model performance

## # A tibble: 3 × 3
##   .metric .estimator .estimate
##   <chr>   <chr>          <dbl>
## 1 rmse    standard   60903.   
## 2 rsq     standard       0.792
## 3 mae     standard   46487.

Disaggregated model performance

## # A tibble: 9 × 4
##   type         .metric .estimator .estimate
##   <fct>        <chr>   <chr>          <dbl>
## 1 Condo        rmse    standard   36471.   
## 2 Multi_Family rmse    standard   65143.   
## 3 Residential  rmse    standard   62022.   
## 4 Condo        rsq     standard       0.772
## 5 Multi_Family rsq     standard       0.424
## 6 Residential  rsq     standard       0.788
## 7 Condo        mae     standard   26429.   
## 8 Multi_Family mae     standard   54769.   
## 9 Residential  mae     standard   47590.

Visualize model performance

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.

Make a custom plot

Ethical considerations

Caveats & recommendations