Analytics Assignment submit R code and Word document( in addition to the responses to these questions). at least 600 Words.
You are working as a Senior Data Analyst for Northeastern Bank.
One of the initiatives currently being discussed is to implement a new customer evaluation process, which will allow the Bank wants to set certain Preferred Customer Interest Rates to attract more customers who will potentially have larger savings account balances.
For any new customers who want to open a Savings Account, the Bank Senior Leadership would like to be able to predict what the Savings Account balances would be, given certain data that is being gathered about each customer, from a newly developed DataMart.
This DataMart includes 3rd party credit score ratings, as well as customers credit card account limits. The Bank also gathers internal data from the Savings Account Application form, which includes customers income, age, education level, Student status.
The CFO wants to know which customer attributes are most favorable to a larger Savings account Balance.
Using the provided dataset, please answer the following questions:
1. Create a set of simple linear regressions of each covariate against the outcome variable.
Based on your simple linear models, rank order the covariates by the strongest R^2 association to the outcome. What are the top two covariates?
2. Generate the Full model (Hint: In your code, list the covariate with the strongest association first, second strongest associate listed second, etc.)
Which of the covariates have significant association with the outcome in the full model?
Are these the same covariates you would have expected based on your simple linear models?
3. Senior Leadership states that the acquisition of third party credit scores is a significant expense for the Bank, and is asking if this data is valuable?
Explain you data-driven recommendation to Senior Leadership, as to whether or not the Credit Ratings add significant value to the models predictive power.