MAT 303 Module Six Problem Set Report done (2)
docx
keyboard_arrow_up
School
Southern New Hampshire University *
*We aren’t endorsed by this school
Course
303
Subject
Mathematics
Date
Jan 9, 2024
Type
docx
Pages
4
Uploaded by melgal14
MAT 303 Module Six Problem Set Report
Decision Trees
Melissa Galvan
Melissa.galvan@snhu.edu
Southern New Hampshire University
1.
Introduction
The credit default and economic data sets are the two under investigation. Financial institutions like
banks and credit card firms may use the data to assess a person's risk of default when they ask for credit
lines or loans. This Economists can use this method to study trends in wage growth. Decision trees are a
form of evaluation of these two problem sets.
2.
Data Preparation
The set of questions you receive requires you to examine some key variables. Determine and
elucidate these variables. In your analysis, answer the following questions: This data set's key
variables are default, credit utilization, missed payments, assets, marriage, education, sex, and
age. In this data set, there are eight columns and six hundred rows.
3.
Classification Decision Tree
The initial data set contains 600 rows. 180 are the validation data sets, while 420 are the training data
sets. The table below shows the variable's classification decision tree based on the provided predictors.
CP nsplit rel error xerror xstd 2 0.048913 1 0.206522 0.20652 0.031951 3 0.016304 3 0.108696 0.10870
0.023719 4 0.010000 4 0.092391 0.11413 0.024275 In the pruned tree, the cp value is 0.793478. The
resulting decision tree has an appropriate cp value of 0.793478; the plot is shown below.
Reporting Results
Evaluating Utility of Model
Evaluate the utility of the classification decision tree. Address the following questions in your analysis:
The Obtained report for the true positives, negatives and false positive and negatives are as follows:
true positives, = 84
true negatives, = 87
false positives = 5
false negatives = 4
Report the following:
○ Accuracy = 19 20 = 0.95 ○ Precision = 84 89 = 0.94 ○ Recollect = 21 22 = 0.95
2
Making Predictions Using Model
Utilizing the regression model, make predictions. Consider the following queries when analyzing: This
forecast is for someone who has never missed a payment, owns a home or vehicle, and has a credit
utilization ratio of 30%. There is a chance that someone who skips a credit payment may default on their
debt, have no assets, and only use 30% of their credit limit.
‘
4. Regression Decision Tree
Reporting Results
The set.seed(705526) The training data set of the economic data set has 79 rows, the test set has 20
rows, and the split ratio is 80% and 20%. 0.035 is the correct cp value to use when pruning trees. Below
is the regression decision tree and table for the specified predictor variables.
Evaluating Utility of Model
Analyze the categorization decision tree's usefulness. Consider the following query as you analyze it:
For this regression decision tree, the root mean squared error is 0.8386. The distance between the
points and the regression line data is used to generate the points, and the RMSE determines how
Divide the residuals amongst themselves.
Making Predictions Using Model
ress the following questions in your analysis:
Utilizing the regression model, make predictions. Consider the following query when analyzing: In the
absence of a recession, the growth rate would be 7.7924. The growth rate would be 2.6364 in the event
that the economy were to enter a recession.
5. Conclusion
Using appropriate definitions of statistical words and concepts, thoroughly explain the implications of
these conclusions for your particular circumstance.
3
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help
In my case, the outcome would provide the business with additional data to determine your eligibility for
a high credit limit. If you are able to pay the credit card company on time, it will also benefit the credit
card company. The outcome would provide credit card data on the proportion of users who are able to
make their payments on time. The significance of the analyses I conducted lies in the fact that they
provide us with precise figures and forecasts, enabling us to adjust for eventualities.
4