Objectives
The objectives of this final exercise are to: 1) practice building and evaluating predictive models using logistic regression to identify which customers in our database should receive a future marketing communication from our company, 2) evaluate the lift and gains of the predictive model and 3) evaluate the profitability of the predictive model.
Assignment
As a provider of investment advice to real estate investors, The Real Estate Investors Club, has achieved steady growth in its customer base. In addition, the company periodically offers additional newsletters for an additional subscription fee.
Yet while sales have grown steadily, profits began falling when the database got larger and the company increased the number of offers sent to customers. The falling profits have led Dave Lawton, The Real Estate Investors Club’s marketing director, to experiment with different database marketing approaches in improve the club’s communication yields and profits.
Dave began a series of live market tests, each involving a random sample of customers from the database. An offer for a new newsletter is sent to the sample and then the sample customers’ responses, either subscription or no subscription, are recorded and used to calibrate a response model for the current offering. The response model’s results are then used to “score” the remaining customers in the database and select customers from the full customer database for the ‘rollout’ of the mailing campaign for the new newsletter.
Dave’s team continues to debate whether statistical techniques can help to better identify potential targets for its new newsletter and improve profitability. As a result, the team wants to compare the effectiveness of the predictive model vs. not using any model.
Dave has a dataset containing the responses of a random sample of 1,345 customers to the newsletter offer. He is eager to assess the potential value of using statistical methods for predicting customer response and has asked you to complete the following analyses.
Note: In to complete this analysis you will need the two attached files: 1) Subscriber Data.sav, SPSS data file which contains all of the data needed to create volume deciles and to conduct the logistic regression analysis, and 2) Subscriber Analysis.xlsx, which contains a pre-formatted worksheet to assist you in your assessment of lift, gains and profitability. You will need to copy and paste data from SPSS output into Excel to complete your assessment.
Attention: This assignment requires you to perform another lift/gains/profit analysis. If needed, review the three videos in Fox Video Vault: 1) Evaluating Models: Lift Analysis, 2) Evaluating Models: Gains Analysis, and 3) Evaluating Models: Profit Analysis.
Due Date:
Monday, December 9 at 11:59 p.m.
Question 1: Evaluate the following two Model Comparisons
Comparison 1:
-2LL(C) | 1475.918 |
PC | 1 |
-2LL(A) | 1390.470 |
PA | 2 |
Improvement Chi Square | 85.448 |
Probability of
Improvement Chi Square (sig) |
0.000 |
Interpretation of Findings
(Include Improvement Chi Square and Probability of Improvement Chi Square) |
Reject the Ho.
The addition of age significantly improves prediction of subscription |
Prediction Equation of
Log Odds for Model A |
Ln(p/1-p) =0.795-0.052(age) |
What is the predicted probability of subscription for a prospective customer that is 35 years of age? | P=e^0.795-0.052(35)/1+e^o.795-0.052(35) =0.36/1.36=0.26 |
Comparison 2:
-2LL(C) | 1390.470 |
PC | 2 |
-2LL(A) | 1381.112 |
PA | 3 |
Improvement Chi Square | 9.358 |
Probability of
Improvement Chi Square |
P(X^2) =9.358=0.002<a=0.05 |
Interpretation of Findings
(Include Improvement Chi Square and Probability of Improvement Chi Square) |
Reject Ho
Controlling for age the addition of gender significantly improves prediction of subscription |
Prediction Equation of
Log Odds for Model A |
Ln(p/1-p) = 0.598-0.052(age)+0.407(gender) |
Question 2:
Which set of variables gives the best prediction of the dependent variable? |
The set contains both the age and gender gives the best prediction of the dependent variable. |
What is your evidence? | The model with age is better than the one without age, and the model with age and gender have improvement compare to the one having age variable. Thus, the model with gender and age is the best. |
Question 3:
Using the equation with both Age and Gender as independent variables, how are the odds of subscription affected by:
Hint: Interpret the logistic regression coefficients.
Question | Answer |
3a | [P/(1-p)] =e^[0.598-0.052(age)+0.407(gender)] =e^0.598*e^-0.052(age)*e^0.407(gender)
e^-0.052=0.949 1-0.949=0.05 When the age increases by 1year, then the odds decrease by 5%. |
3b | Gender e^0.407=1.502 1.502-1=0.502
If female (1) then odds of subscription increase by 50.2%. |
Question 4:
Conduct a Lift/Gains/Profitability analysis in Excel.
Use the following cost information to assess the profitability of both modeling methods.
Cost to Mail Offer to Customer | $1.00 |
Selling Price of Newsletter (including shipping) | $15.00 |
Contribution Margin (%) | 33% |
Using the data from the Lift/Gains/Profitability Analysis that you completed in Excel, complete the following table.
Method to Identify Customers | Maximum Cumulative Operating Profit | % of Customers Receiving Mailing | Acquisition Costs per Customer | ROI = Operating Profit/ Total Fixed Costs of Campaign |
Mail All Customers in Database | 255 | 100% | = $1345/320 =4.2 | = $255/$1345= 19% |
Logistic Regression Model | 450 | = 540/1345= 40% | = $540/198= 2.727 | = $450/$540= 83% |
Question 5 | Based on your analysis of the data table from Question 4, which approach do you recommend be used to identify those existing customers to receive the newsletter: Logistic Regression Model or “Mailing All Customers in the Database”? |
Answer
(Cite Evidence) |
Logistic regression model approach I recommend be used to identify those existing customers to receive the newsletter. It has higher cumulative operating profit, lower acquisition costs per customer and higher return on investment. |
Delivering a high-quality product at a reasonable price is not enough anymore.
That’s why we have developed 5 beneficial guarantees that will make your experience with our service enjoyable, easy, and safe.
You have to be 100% sure of the quality of your product to give a money-back guarantee. This describes us perfectly. Make sure that this guarantee is totally transparent.
Read moreEach paper is composed from scratch, according to your instructions. It is then checked by our plagiarism-detection software. There is no gap where plagiarism could squeeze in.
Read moreThanks to our free revisions, there is no way for you to be unsatisfied. We will work on your paper until you are completely happy with the result.
Read moreYour email is safe, as we store it according to international data protection rules. Your bank details are secure, as we use only reliable payment systems.
Read moreBy sending us your money, you buy the service we provide. Check out our terms and conditions if you prefer business talks to be laid out in official language.
Read more