Segmentation of online shopping customers in the fast-moving consumer goods sector

The fast-moving consumer goods sector, which has existed for years, has entered the scope of e-commerce in recent years and become increasingly important. Especially with the effects of the COVID-19 pandemic, people's shopping habits have started to change and fast-moving consumer goods have started to be purchased from online shopping sites intensively. These developments mean that new companies are added to the sector everyday and each company needs to maintain its market share. Therefore, in this relatively new market, investigating customer characteristics and behaviors, and improving service and profitability have become more important. Customer segmentation has an important role in the field of Customer Relationship Management. In this thesis, customer segmentation is studied with the purchasing data of the customers of an online shopping site working in cooperation with many companies in the fast-moving consumer goods sector. Firstly, it is determined which feautures will be considered from the existing set of features. Primarily, the recency, frequency and money feautures in the literature are selected. Using feature selection methods, the order number percentage with coupons feature is also determined to be worth using, and four features are used in total. With these selected feautures, the appropriate number of sets is determined. Later, customer segmentation is carried out with K-Means, Birch Hierarchical and Gaussian Mixture Clustering methods. The results of the segmentation are compared with the determined performance metrics, and with the examination and opinion of the company officials, it is decided that the results of the K-means clustering method will be used. Finally, for clusters determined by the the K-means clustering method, customer relationship development strategies are suggested. Keywords: Fast Moving Cunsumer Goods industry, online shopping, feature selection, customer segmentation, clustering algorithms, customer relationship development strategies