Reference no: EM133116750

7BUIS010W Data Warehousing and Business Intelligence - University of Westminster

Learning Outcome 1: Define customer relationship management, change management problems, select and apply appropriate Business Intelligence (BI) methodologies and evaluate BI solutions to these problems;

Learning Outcome 2: demonstrate competence in using BI Technologies and Tools on business data for the purposes of CRM and CM;

Learning Outcome 3: apply CRM knowledge and CM to support change and improve operational processes of service organizations.

Tasks

1. Data Understanding: useful as a preliminary step to capture basic data property. Distribution analysis, statistical exploration, correlation analysis, suitable transformation of variables and elimination of redundant variables, management of missing values.Load the data set to SQLITE and use an SQL query to clean the data set.

2. PerformRFM Segmentation: The first step is to build an RFM model to assign Recency, Frequency and Monetary values to each customer.

3. Customer segmentation with k-means: The second step is to divide the customer list into tiered groups using clustering such as K-means and discuss the profile of each found cluster (in terms of the properties that describe the properties of the customers of each cluster). The report should illustrate the adopted clustering methodology and the cluster interpretation. In particular, it is necessary to discuss the identification of the best value of K.

4. Review of Results: Discuss briefly the business value for marketers of the specific clusters and segments of customers and their behaviour - in terms of increased customer loyalty and customer lifetime value.

5. Data Mart Design: Based on your findings (Tasks (2,3)) and conclusions, suggest the main dimensions and metrics for designing a data mart for the analysis needs of the marketing department.

Tasks

Question 1. Data Understanding: useful as a preliminary step to capture basic data property. Distribution analysis, statistical exploration, correlation analysis, suitable transformation of variables and elimination of redundant variables, data visualisation, management of missing values.Load the data set to SQLITE and use an SQL query to clean the data set.

• Distribution analysis
• Statistical exploration
• Correlation analysis
• Suitable transformation of variables
• Elimination of redundant variables
• Data visualisation
• Management of missing values

Question 2. PerformRFM Segmentation: The first step is to build an RFM model to assign Recency, Frequency and Monetary values to each customer.
• Definition of RFM metrics
• Implementation in Python correct metrics

Question 3. Customer segmentation with k-means: The second step is to divide the customer list into tiered groups using clustering using K-means and discuss the profile of each found cluster (in terms of the properties that describe the properties of the customers of each cluster). The report should illustrate the adopted clustering methodology and the cluster interpretation. In particular, it is necessary to discuss the identification of the best value of k.
• Build of K-Means Model in Python
• Correct Justification of K value
• Testing of K-Means Model in Python

Question 4. Review of Results: Discuss briefly the business value for marketers of the specific clusters and segments of customers and their behaviour - in terms of increased customer loyalty and customer lifetime value.
• Identification of business value customer segments
• Correct Justification of their business value

Question 5. Data Mart Design: Based on your findings (Tasks (2,3)) and conclusions (Task 4), suggest the main dimensions and metrics for designing a data mart for the analysis needs of the marketing department.
• Identification of Dimensions
• Justification of Selected Dimensions
• Identification of Measures
• Justification of Selected Dimensions

Attachment:- Data Warehousing and Business Intelligence.rar