Display the column names from the loan data set

Assignment Help Computer Networking
Reference no: EM131016595

Objectives of this project

Use Random Forests, Neural Networks and Support Vector Machines to predict loan status (default or not).

Understand the difference between in-sample fitting and out-of-sample predictive performance.

Use two cross-validation methods to assess analytic model performance.

1) Load the Loan.csv data set into R. It lists the outcome of 850 loans. The data variables include loan status, credit grade (from excellent to poor), loan amount, loan age (in months), borrower's interest rate and the debt to income ratio. Code loan status as a binary outcome (0 for current loans, 1 for late or default loans). Display the column names from the loan data set. Fit the loan data set using random forest function. Copy the trained random forest model and the confusion matrix from R and paste it below.

2) Randomly select 750 out of 850 loans as your training sample. Use the remaining 100 loans as your test set. Train the 2nd random forest model using the training set. Apply the 2nd model to the test set to predict loan status. Compare your predictions to the true loan statuses (using table function). Display the confusion matrix below. Based on this confusion matrix, what's the overall misclassification rate? [10 points]

3) Fit the loan data set using an artificial neural network. Use six neurons in the hidden layer of the ANN. Set maxit to 1000. Use table function to compare in-sample predictions to the true loan statuses. Display the confusion matrix below.

4) Use the training sample (750 randomly selected loans) to build the 2nd artificial neural network. Use six neurons in the hidden layer of the ANN. Set maxit to 1000. Use table function to compare out-of-sample predictions to the true loan statuses (use the remaining 100 loans as your test set). Display the confusion matrix below.

5) Use the training sample (750 randomly selected loans) to build a model of support vector machine. Use table function to compare the SVM's out-of-sample predictions to the true loan statuses (use the remaining 100 loans as your test set). Display the confusion matrix below.

6) Randomly shuffle the loan data set. Run 10-fold cross-validation to evaluate the out-of-sample performance of Random Forest, ANN and SVM. Based on your cross-validation results, which model has the best out-of-sample performance? Please briefly explain why.

7) Run leave-one-out cross-validation to evaluate the performance of random forest algorithm in predicting loan status. Why does it take much longer to run leave-one-out cross-validation than to run ten-fold cross-validation? Based on the result of your leave-one-out cross-validation, how many loans are misclassified by the random forest model?

Attachment:- Loan.csv

Reference no: EM131016595

Role icmp plays in extending the ip protocol architecture

Discuss the role ICMP plays in extending the IP protocol architecture? Looking into the structure of the error reporting ICMP messages, what is the purpose of including the

Implement the appropriate classification method

Analsyse the pcap file that has been made available to provide probable cause of the symptoms may be (within your expertise ) and make recommendations to prevent this from r

What are the different types of networks

What are the principal components of telecommunications networks and key networking technologies? Describe the features of a simple network and the network infrastructure fo

Define the term subnet mask

Define the term subnet mask. What do the bits in the mask whose values are binary 0 tell you about the corresponding IP address(es)? Include an example illustrate your answe

How long will the project take in days and weeks

Implement the above project scope into MS Project 2013 (or appropriate software). The following table forms an idea of the tasks/subtasks to be implemented. Remember the sta

Advantages and disadvantages of moving to a saas provider

Should SoftArc move to a SaaS provider in order to provide email and office automation services for their employees? What are the advantages and disadvantages of moving to a

Design a new network for western trucking

Western Trucking operates a large fleet of trucks that deliver shipments for commercial shippers such as food stores, retailers, and wholesalers. Design a new network for th

Design requirements of lan, voip and wireless

You are required to submit business need and Design Requirements of Entire WWTC Project. The requirements include but are not limited to- Design Requirements of LAN, VOIP and

Reviews

Write a Review

 
Free Assignment Quote

Assured A++ Grade

Get guaranteed satisfaction & time on delivery in every assignment order you paid with us! We ensure premium quality solution document along with free turntin report!

All rights reserved! Copyrights ©2019-2020 ExpertsMind IT Educational Pvt Ltd