2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) ISBN: 978-1-6654-7436-8/22/$31.00 ©2022 IEEE 753 Customer Segmentation and Future Purchase Prediction using RFM measures Akash Patra M.Sc. Data Science Department of Data Science Christ University Christ University Pune, Lavasa akash.patra@msds.christuniversity.i n Ramkrishna Khan M.Sc. Data Science Department of Data Science Christ University Christ University Pune, Lavasa ramkrishna.khan@msds.christuniver sity.in Dr. S. Vijayalakshmi Department of Data Science Christ University Pune, Lavasa Lavasa,India svijisuji@gmail.com Abstract: Winning in the E-Commerce business race at a competitive age like this requires proper usage of Customer data. Using that database and grouping it in similar segments in terms of spending expenditure, observation time, sex, and location so that every customer falls in a segment of characteristics. This mechanism is called Customer Segmentation. In the modern era of highly compatible technological advancements, Machine Learning Algorithms are being vastly used to bring solutions to these difficult yet essential services. In the field of research methods like simple clustering based on purchase behaviour, buyer targeting or automated customer promotion mechanism by dividing into two major categories, have been worked on. However, ensemble algorithms have come handy where different clustering algorithms are combined to deliver best segmentation. Lately combination techniques like clustering and classification mechanism have also delivered good results where, not only segmentation is done but also classification of existing and new customers are possible into the clusters. Depending on that an effective customer relationship management can really benefit the company to a huge extent. Unlike other studies where clustering was performed directly on RFM table, a different approach was taken in this study where, one dimensional clustering was done individually on Recency, Frequency, Monetary columns, then an overall score was calculated and customers were classified into three segments. However, for a new customer depending on his purchase behaviour he/she also can be classified into any of the categories. Keywords: Machine Learning, E-Commerce, Customer Segmentation, Clustering, Classification, K-means, RFM. 1. INTRODUCTION The competition among E-commerce businesses is increasing by each day. The importance of customer segmentation is also increasing. Sumit Koul and Trissa Merrin Philip discuss (1) on Customer being the top priority of any business foundation. Thus keeping a customer happy and satisfied throughout the service is an extremely important job to provide. For that, one needs to identify what a customer needs. To overcome this difficulty we need to analyse the data of customers. The process of analyzing these customer data and grouping them according to their similarities is known as customer segmentation. According to statistical data, in the year of 2019, retail industry generated a revenue of $10,632.4 billion. Therefore, in this highly profitable comparative market, customer expenditure behavior would change dynamically. So, in order to forecast customer online behaviour based on effective analysis of the database available at the enterprises an excellent customer- oriented marketing strategy is very much needed. The rest of the paper has been organized as follows (2). Section 2 briefs about existing models which are in use currently in the market for consumer segmentation along with two different evaluation metrics and mathematical reasoning behind those. Related works were mentioned in the next section 3. The Entire methodology has been discussed in section 4 with the help of flowchart for easy visual understanding. In the 5 th section, the findings and the result of this study has been discussed with necessary plots and tables to justify the researcher’s claim. An overall conclusion has been presented in the 6 th section which discusses about the difficulties with 3-Dimensional clustering on RFM table and how individual clusters were made and aggregated to segment customers more effective. Fig.1. Fundamental idea of Customer Segmentation. 2. RELATED WORKS Related Works: Jun Wu, Li Shi et al have discussed (2) in their work that using RFM and the K-Means clustering technique, customer expenditure behaviour is systematically 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) | 978-1-6654-7436-8/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICAC3N56670.2022.10073993 Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY BOMBAY. Downloaded on July 13,2023 at 16:36:11 UTC from IEEE Xplore. Restrictions apply.