Creating customer value segmentation using data analysis techniques and its application in the retail industry

Advancements in technology and logistics activities allow businesses to have a wider customer base. As a result of this change, businesses now need to know their customers better. Businesses aim to infer insights from customers' behavior and habits, and create strategic approaches for their customers, expecting high levels of positive feedback in return. In this thesis, a literature review on data mining was initially conducted. As a result of the literature review, the behaviors and habits of over 1,000,000 customers in a retail sector were examined based on certain criteria. The data was processed through a preliminary stage and made suitable for analysis. Then, by determining the number of clusters, the data was divided into clusters using the K-Means method, grouping customers with similar behaviors and habits together. Strategic approaches that can be created for each cluster were identified by defining the value of each cluster. In the final section, conclusions were drawn based on the results.