Answer:
Two good reasons for using linear regression instead of kNN could be:
Linear regression is better able to cope with data that is not linear , as it explicitly models the linear relationship between the input features and output variable. On the other hand, kNN is a non-parametric algorithm that relies on the local similarity of input features, so it may not perform well in cases where the relationship between features and output variable is non-linear.
Linear regression is easier to tune, as it has fewer hyperparameters to adjust than kNN. For example, in linear regression, we can adjust the regularization parameter to control the model complexity, whereas in kNN, we need to choose the number of nearest neighbors and the distance metric. However, it should be noted that the choice of hyperparameters can also affect the performance of the model.
Step-by-step explanation: