User Handling Customer Queries Since intercity cabs are relatively rare in India, Ultra has developed an extensive FAQ page that answers the most common customer queries. However, several customers still directly ask questions through FB chat. Given that you can’t always provide an immediate response, what should you do?

1. TelTek Project Submission
Name - Tahir Ashraf
Student ID -

2. Q-1) What is the RFM score of customer 26 and customer 150.
For Customer 26:
Recency (R) score: 16/02/2017
Frequency (F) score : 03
Monetary value (M) score: 595
For Customer 150:
Recency (R) score: 05/08/2017
Frequency (F) score : 4
Monetary value (M) score: 375

3. Q-2) Match the targeting strategies with the RFM scores given in the table.
RFM scores Targeting strategy
A. Customers with all the recency, frequency and monetary value
scores of 3 and 4 such as 4-4-4,4-4-3,3-4-3
i. TelTek should send them notifications about new TV shows
being screened on its OTT service partner’s platform. In this way,
the firm can make the customers consume more data, eventually
pushing them to recharge more frequently.
B. Churned best customers with low recency scores and high
frequency and monetary scores such as 1-4-4, 1-3-4, 1-3-3
ii. TelTek should ensure that these type of customers have a
great experience. Any Conflict or complaint should be resolved
promptly.
C. Customers with low-frequency scores and high recency
and monetary value scores such as 4-1-4, 3-1-4, 3-1-3
iii. The firm should use upselling strategy to make these
customers upgrade their existing subscription or subscribe for
additional services.
D. Customers with low monetary value score and high recency
and frequency scores such as 4-4-1, 3-4-1,3-3-1
iv. The company should develop a strategy to reacquire and re-
engage these type of customers by offering them incentives and
great customer experience
A - 2, B - 4 , C - 1 , D - 3

4. Q-3) Which cluster comprises of the most valuable customers? What targeting
strategy should the company use for these type of customers?.
Cluster: 4
Targeting strategy:
-Offer them exclusive discounts and promotions like discounts on their monthly bill, free
upgrades to their service, etc.
- assigning them a dedicated customer service representative, offering them 24/7
customer support.

5. Q-4) Study each metric of cluster 2 and cluster 3. Which cluster is the best
among the two? What can you do to the other cluster to become the best
among the cluster 2 and 3?
Cluster: Cluster 3 is the most valuable customer segment. They have the highest ARPU, the longest
tenure with the company, and the fewest complaints.
Targeting strategy:
- Cluster 2 customers have prepaid plans. The company can offer them postpaid plans, which
have more benefits, such as greater convenience, better service quality, and additional
features.
- Cluster 2 customers have a higher number of complaints in comparison to cluster 3. The
company should prioritize resolving these complaints promptly and efficiently.

6. Q-5) How would you approach cluster 3 to make them more profitable?
Targeting strategy:
Cluster 3 is the second most profitable set of customers, so we should give them
discounts and offer personalized messages to encourage them to buy more.
We can also entice them with offers that will allow them to try out more Teltek
services.

7. Q-6) Which metrics will you use in selecting the best classification model?
Metric 1:
The logistic regression model would be used. We only need to predict or
classify the categorical dependent variablebased on one or more
independentvariables.

8. Q-7) In order to predict the customer churn, the firm is required to solve a binary classification
problem. Apart from logistic regression that you have already seen, there are other models as
discussed in the video. Based on the confusion matrix (given on the platform) for each of these
models, choose the best method for building the propensity to churn model?
Classificationmodel:
Logistic regression
Accuracy=0.65
Error Rate=0.35
Specificity=0.71
Sensitivity=0.60
Randomforest
Accuracy=0.72
Error Rate=0.27
Specificity=0.80
Sensitivity=0.65
Decision tree
Accuracy=0.8
Error Rate=0.24
Specificity=0.84
Sensitivity=0.71
Among the three models,the "DecisionTree model"
demonstrates the highest accuracy, sensitivity and
specificitywith lowest error rate. This suggests that the
DecisionTree modelcould be the most suitable
approach forconstructing the propensityto churn
modelin this particular scenario.

9. Q-8) From the churn analysis, which factors have a significant influence on
customer churn at a 95% confidence level?
Significant factors:
Contract bucket (p-value = 0.0001)
Customer billing (paperless or not) (p-value = 0.005)
Tenure group (p-value = 0.012)

10. Q-9) Which channels have a significant influence on the total unit sales at 95%
confidence level?
Significant Channels:
Print (GRP) & Search (No. of impressions) havesignificantinfluenceon the total unit sales at 95%
confidencelevel as their P-value is less than 0.05

11. Q-10) State the regression coefficients of the channels?
RegressionCoefficients:
TV: 9.25587939343629
Radio:3.41973070217645
Print:67.188845759955
Search:11.1837153913009
Facebook:1.4056610312505

12. Q-11) State the multiple linear regression equation based on the results
obtained?
Regressionequation:
Digital regression equation: Sales = 1876 + 11.18xsearch + (-
)1.4xFacebook
Non Digital regression equation:
Sale = 2985 +(-)9.25xTV + 3.41xRadio +_67.88xPrint