Scribd
Upload
477 views3 pages

Bnad 277 Lab 7 Web

This analytics report contains two regression models: one to predict credit card limits and one to predict the likelihood of defaulting on payments. The credit limit model uses variables like gender, education level, marital status, and age to predict an individual's limit. It finds that females tend to have higher limits than males, and those with graduate degrees higher than high school. The payment default model uses average bill amount, payment amount, and age. It finds the likelihood of default increases slightly with age but decreases with higher payments and bills. Both models were significant and help interpret factors influencing credit limits and default risk.

Uploaded by

api-530715476
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
477 views3 pages

Bnad 277 Lab 7 Web

This analytics report contains two regression models: one to predict credit card limits and one to predict the likelihood of defaulting on payments. The credit limit model uses variables like gender, education level, marital status, and age to predict an individual's limit. It finds that females tend to have higher limits than males, and those with graduate degrees higher than high school. The payment default model uses average bill amount, payment amount, and age. It finds the likelihood of default increases slightly with age but decreases with higher payments and bills. Both models were significant and help interpret factors influencing credit limits and default risk.

Uploaded by

api-530715476
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

ANALYTICS REPORT

TO: MICHAEL ESPINO

FROM: JOHN MCCLINTOCK

SUBJECT: LAB 7

DATE: APRIL 14TH, 2020

Introduction
The research on this report is regarding credit card data from Taiwan. The data was used
to make regression models to predict both credit card limit, and the likelihood of
someone defaulting on their next month’s payment.

Data Analysis

^
Credit Limit=376.50+ 366.04 ( Female )−1135.59 ( High School ) +2321.85 ( Grad School )+ 2978.66 ( Married ) −

All variables from the list should be included in the model because all P-Values provide
significance. Significance variables should not be removed from the model.

R2: We are 11.87% of the way to perfectly predicting credit limit using this model.
Standard Error: We are about $4027.96 off from predicting the actual amount of dollars
in the model.

Female: On average, females have a credit limit $366.04 high than males and all else
constant.

High School: Someone with a high school degree has a credit limit $1135.59 lower than
someone with a university degree, on average and all else constant.

Grad School: On average, someone with a grad school degree has a credit limit of
$2978.66 and all else constant.

At zero years old, married people would have a credit limit $2979.66 higher than single
people, on average and all else constant.

Single People: As age increases by 1 year, credit limit increases by $117.96, on average
and all else constant.

Married People: As age increases by 1 year, credit limit increases by $67.02 less than for
a single person, on average and all else constant.

^
P( Default =1)=0.20+0.0000069 ( Avg . Bill )−0.001 ( Avg . Payment ) +0.001( Age)

All the variables above should be included in the model since all are significant variables.

R2: We are 1.39% of the way from predicting the chance of default in the model.

Standard Error: Predictions of default chance are off by an average of 41.21 percentage
points.

2
Avg. Bill: As average bill amount increases by $1, chance of defaulting increases by
0.00069 percentage points, on average and all else constant.

Avg. Payment: As average payment increases by $1, chance of defaulting decreases by


0.001 percentage points, on average and all else constant.

Age: As age increases by 1 year, chance of defaulting increases by 0.001 percentage


points, on average and all else constant.

The credit limit for a 35-year-old, single, female with a high school degree according to
the “Limit” model is $3735.55.

The probability of someone defaulting who is 25-years-old, has an average bill amount of
$1150.00 and an average payment of $900.00 is -0.6670 percentage points compared to a
Default = 1, and is least likely to default on their next month’s payment.

Conclusion
The regression models for credit limit predictions and probability of defaulting on next
month’s payment can both be used to make interpretations. All variables in each of the
models were significant so this makes it necessary for the variables to be included in the
respective models. Based on the variables from the credit limit model, Females tend have
high credit limits than men, and Graduate Degree holders tend to have higher credit limits
compared to High School degree holders. Based on the probability of defaulting model,
as Age increases, the percentage points of the probability of defaulting on payments also
increases.

You might also like