This assignment will provide you with an opportunity to apply different classification models.

2007 was a memorable year for the economy. The real estate bubble burst and the economic downturn that followed was the most severe since the Great Depression. Many parties were blamed for misdeeds and excesses, federal funding agencies among them. Fannie Mae is a federally sanctioned corporation that promotes property ownership by buying up privately issued mortgages. Fannie Mae among others received its share of criticism after the mortgage crisis. While there are many opinions, evidence is needed to shed light on the matter.

Should Fannie Mae had known better than to buy the mortgages that were originated in Q1 2007?

Data - Q1 mortgage origination + delinquency status dataset.

Data dictionary:

http://www.fanniemae.com/resources/file/mbs/pdf/lld-filelayout-0516.pdf

http://www.fanniemae.com/resources/file/mbs/pdf/lld-glossary-051616.pdf

Note that Fannie Mae has changed the data format since the data were collected for this task. The data dictionary will contain additional fields - you can ignore information about the fields, not present in the data.

1. Explore and pre-process data as needed. Provide a bullet list of pre-processing steps. (5 pts.)