Abstract

Understanding the various facets of a customer’s data is very important for businesses. This insight can help them identify patterns and opportunities to improve their operations. RFM values are often used to identify which customers are valuable for a company. They are then used to identify which promotional activities are most appropriate for them. K-means clustering is an unsupervised learning technique that works when you have unlabeled data. It allows the identification of new data points and groups. This paper proposes a novel approach that combines data cleaning and analyzing customer data to divide a broad market into various consumer groups, and then designing and implementing marketing campaigns that effectively target these consumers. This study aims to identify profitable segments based on historical data (such as purchased items and the associative monetary expenses). The proposed model is formulated using a decision tree and the RFM model to put the customers in three segments (Gold or Silver or Bronze). The decision tree is a type of supervised algorithm that can interpret clustering. It will use labels to classify the data and then plot the clusters.

Publication Date

12-19-2021

Document Type

Master's Project

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research (Dubai)

Advisor

Sanjay Modak

Advisor/Committee Member

Hammou Messatfa

Campus

RIT Dubai

Download

Share

COinS