# Adjusted count R-squared

Adjusted count R-squared is a measure of improvement from the constant model to the fitted model.

It is obtained by computing the model classification accuracy improvement over the constant model and dividing it by the constant model classification error. Constant model always predicts the target mode and its classification accuracy is estimated by the mode frequency. Reliable predictive relationship is reported when the model predictive strength is greater than a default threshold of 10%.

In some calculations of the adjusted count R-squared, data for categories with low total counts are not used in the calculation. This filtering reduces the influence of low-frequency categories.