Tableau: Data Exploration Report $($loans$)$

Background

You are a data scientist at Lending Club and you are trying to improve your accuracy in predicting how likely each customer will be to pay back their loan. You need to begin by working through the Data Understanding Phase for this project. Recall that there are four reports typically generated from this phase:

Initial Data Collection Report

Data Description Report$*$

Data Exploration Report$*$

Data Cleaning Report

However, you are only requried to generate Reports $2$ and $3($in a single combined Word document$)$ for this assignment using the Lending Club data set below. There is a sample report included for download in the files below. However, to keep this assessment to a realistic scope, you can ignore the hypotheses and references$/$citations used in the example report. You only need to include the analyses themselves. See the details below.

Task Description:

Use Word and any combination of Tableau and Excel you would like to complete the tasks outlined in the questions below, which will walk you through creating the Data Description Report and Data Exploration Report.

Data Source:

Use the lc$\_$large.csv file available to download below.

Drag the table: lc$\_$Loans into the entity view in Tableau. Select the "Extract" option for the connection in Tableau.

Data Dictionary:

Features about the loan

loan$\_$status: current status of the loan

loan$\_$status$\_$numeric: a rank$-$ordered numeric version of loan$\_$status

loan$\_$amount: the listed amount of the loan applied for by the borrower

issue$\_$d: the date the loan was funded$/$issued

term: the number of payments on the loan

int$\_$rate: the interest rate on the loan

installment: the monthly payment owed by the borrower

total$\_$pymnt: payments received to date for total amount funded

total$\_$rec$\_$prncp: payments received to date for total amount funded

total$\_$rec$\_$int: interest received to date

total$\_$rec$\_$late$\_$fee: late fees received to date

recoveries: post charge off gross recovery $($i$.$e$.,$ if the loan was charged off, how much money was recovered afterward, if any$)$

title: the loan title provided by the borrower

purpose: a category provided by the borrower for the loan request

Features obtained from the borrower before the loan was issued

emp$\_$title: the job title supplied by the borrower

emp$\_$length: employment length in years

home$\_$ownership: the homeownership status provided by the borrower

annual$\_$income: the self$-$reported annual income provided by the borrower

verification$\_$status: was income verified by LC$,$ the source, or not verified

Features obtained from the credit bureau about the borrower before issued

acc$\_$now$\_$delinq: the number of accounts on which the borrower is now delinquent

delinq$\_2$yrs: the number of $30+$ days past$-$due incidences of delinquency in the borrower's credit file for the past $2$ years

earliest$\_$cr$\_$line: the month the borrower's earliest reported credit line was opened

inq$\_$last$\_6$mths: the number of unsecured inquiries in the past $6$ months

mths$\_$since$\_$last$\_$delinq: the number of months since the borrower's last delinquency

mths$\_$since$\_$last$\_$record: the number of months since the last public record

open$\_$acc: the number of open credit lines in the borrower's credit file

pub$\_$rec: number of derogatory public records

revol$\_$bal: total credit revolving balance

revol$\_$util: the amount of credit the borrower is using relative to all available revolving credit

tot$\_$coll$\_$amt: total collection amounts ever owed

tot$\_$cur$\_$bal: total current balance of all accounts

total$\_$acc: the total number of credit lines currently in the borrower's credit file

total$\_$rev$\_$hi$\_$lim: total credit limit on revolving accounts

Features engineered by LC based on the credit bureau data

dti: a ratio calculated using the borrower's total monthly payments on the total debt obligations, excluding mortgages and the requested LC loan, divided by the borrower's combined self$-$reported monthly income

grade: the likelihood that the loan will be paid back

sub$\_$grade: a more granular version of grade

To limit the scope of this assignment, you will not need to include every feature above in your report. Instead, only complete the tasks required in the questions below. Additional details:

Use loan$\_$status$\_$numeric as the label for this project.

It represents the outcomes we are interested in: charged off $=0,$ default $=1,$ late $31120=2,$ late $1530=3,$ grace period $=4,$ current $=5,$ fully paid $=6$

You do NOT need to write hypotheses $($H$1,$ H$2,$ etc$)$ or Summary descriptions for your report as demonstrated in the example project documentation included. You can keep this simple by only generating the visualizations, metrics, and statistics required by the questions below.