Waht is Bias-Variance Tradeoff? | Intellipaat

The goal of every supervised machine learning is to minimise bias and variation while producing predictions with high accuracy.

• The k-nearest neighbour method has a low bias but a high variance; however, the trade-off may be changed by increasing the value of k, that boosts the number of friends who participate to the forecast and, in turn, raises the biases of the models.
  

It is impossible to ignore the relationship between bias and variation in machine learning. If the bias is raised, the variance will go down. Bias will become less pronounced as variety rises.