You will split your data set into $70\%$ as train data and $30\%($the remainder$)$ as test data and then apply different statistical learning approaches that we have covered in this course to find the best prediction methods for your data.

You have to at least try out regression $($including ridge and lasso$)$ and tree based methods $($including bagging, random forests and boosting$).$

You have to use $R$ code set.seed $(2^{31}-1)$ right before the $R$ functions you use $($whenever they use randomness, such as splitting data, k$-$fold, etc.$)$ In this way, your results should match my ones.

After you finish your work, please provide one page of an executive summary at the front of your document.

You have to organize your work in Word$/$PDF document in the following manner

List each method and related results

Provide selective computer outputs $($using snipping tool$)$ which contain information for your results

Attach all your $R$ code or other programming code at the end of your document

Name your submitting document as last$-$name initial$-$of$-$first$-$name.docx or $.$pdf $(,$ For example, John Doe's file name should be Doe$-$J$.$pdf$)$ and email the file $($not link$)$ to me before the due time.

You have to submit this signed page. You can take a photo of your signed page or merge this page to the front of your exam file and then email it to me$.$

Data: $q,$ is assigned to