Obtaining the optimal tuning parameter value for Ridge Regression



Recently, I found out that ridge regression penalizes/shrinks the co-efficients in regression to alleviate the effects of multi-collinearity. This penalization of co-efficients is done according to some tuning parameter. How can we obtain the optimal value of the tuning parameter?



You can use GRIDSEARCH to tune the parameter value of a estimators. It can be set by searching a parameter space for the best Cross-validation while evaluating estimator performance score.

Any parameter provided when constructing an estimator may be optimized in this manner. Specifically, to find the names and current values for all parameters for a given estimator.