MIS784 Marketing Analytics

Case Study

Tesco PLC is a British multinational supermarket chain headquartered in Welwyn Garden City, Hertfordshire, England, United Kingdom. It is the third largest retailer in the world measured by profits and second-largest retailer in the world measured by revenues. It has stores in 12 countries across Asia and Europe and is the grocery market leader in the UK, Ireland, Hungary, Malaysia, and Thailand. The company currently offers products in nine different categories including Apparel, Bakery, Deli, Dairy, Fresh Produce, General Merchandise, Grocery, Liquor, and Meat.

Tesco launched its customer loyalty scheme, the Tesco Clubcard, in 1995, with two levels (Silver and Gold). It has been cited as a pivotal development in Tesco’s progress towards becoming the UK’s largest supermarket chain and one that fundamentally changed the country’s supermarket business. Cardholders can collect one Clubcard point for every £1 they spend in a Tesco store, or at Tesco.com. This enables the company to collect data on purchase behaviour of customers and utilize it to design customized offers and conduct targeted retention campaigns.

Data

The data of this assessment task relates to a random sample of 30,000 customers from Tesco Clubcard (20,000 training set & 10,000 test set) in a period from 1 January 2015 to 31 December 2015. The 18 variables in the data table are described below:

Variable Name	Description
ID	Unique ID of customers
Purchase	Number of purchases during the observation period1
	The time gap between customer’s first purchase and last purchase during the
T.last	observation period
	The time gap between customer’s first purchase and last day of the
T.active	observation period
Loyalty	A binary variable to show membership level: (0) Silver  (1) Gold
Service Failure	Number of service failures during the observation period
Total Profit	Total profit generate by the customer during the observation period
AP.spent	Total spending on Apparel category during the observation period
BH.spent	Total spending on Bakery category during the observation period
DL.spent	Total spending on Deli category during the observation period
DY.spent	Total spending on Dairy category during the observation period
FV.spent	Total spending on Fresh Produce category during the observation period
	Total spending on General Merchandise category during the observation
GM.spent	period
GR.spent	Total spending on Grocery category during the observation period
LQ.spent	Total spending on Liquor category during the observation period
MT.spent	Total spending on Meat category during the observation period
	Socio Economic status of  the customer on a scale from 1(lowest) to 10
Socio.Economic	(highest)
	A binary variable to show the churn status of the customer in the prediction
Churn	period2 (0) non-churner (1) churner

Analysis Tasks

1- Construct a model to predict customer churn using binary classification trees (C&R Tree) and evaluate the performance of the constructed model on the holdout sample provided (use metrics related to confusion matrix).

2- Evaluate the performance of the constructed model against the RFM method (use lift chart-i.e. concentration to make the comparison).

Report Tasks

1- Introduction and problem definition

2- Literature review: Use only academic journal articles.

3- Methodology and empirical study: this should include a discussion of your analytical techniques, your model evaluation metrics, your working data, and your model building process.

4- Results: evaluate your analysis results to explain how the constructed models perform and also how they are positioned against a random model (random guessing).

5- Conclusion and Recommendations: This should consider the implications of your results and how they may contribute to customer retention and reduce marketing expenditure.

  Do you need high-quality Custom Essay Writing Services?