Model Card for Census Income Classifier

Model Card for Census Income Classifier

Model Details

Overview

This is a wide and deep Keras model which aims to classify whether or not an individual has an income of over $50,000 based on various demographic features. The model is trained on the UCI Census Income Dataset. This is not a production model, and this dataset has traditionally only been used for research purposes. In this Model Card, you can review quantitative components of the model’s performance and data, as well as information about the model’s intended uses, limitations, and ethical considerations.

Version

name: 2d1bd3b5688079d2da1b20350118dda7

Owners

References

Considerations

Use Cases

Limitations

Ethical Considerations

Train Set

This section includes graphs displaying the class distribution for the “Race” and “Sex” attributes in our training dataset. We chose to show these graphs in particular because we felt it was important that users see the class imbalance.
counts | Race
counts | Sex

Eval Set

Like the training set, we provide graphs showing the class distribution of the data we used to evaluate our model’s performance.
counts | Race
counts | Sex

Quantitative Analysis

These graphs show how the model performs for data sliced by “Race”, “Sex” and the intersection of these attributes. The metrics we chose to display are “Accuracy”, “False Positive Rate”, and “False Negative Rate”, because we anticipated that the class imbalances might cause our model to underperform for certain groups.
binary_accuracy | Race
binary_accuracy | Race, Sex
binary_accuracy | Sex
fairness_indicators_metrics/false_negative_rate@0.5 | Race
fairness_indicators_metrics/false_negative_rate@0.5 | Race, Sex
fairness_indicators_metrics/false_negative_rate@0.5 | Sex
fairness_indicators_metrics/false_positive_rate@0.5 | Race
fairness_indicators_metrics/false_positive_rate@0.5 | Race, Sex
fairness_indicators_metrics/false_positive_rate@0.5 | Sex