Customer Segmentation is fundamental to every business, It allows business to provide targeted product marketing. The retail industry is no different. To be on par with the competition, an UK based online retail company wants to understand their customers buying preferences in order to pinpoint their marketing strategy and to deepen customer loyalty. To achieve the above goals we analyzed the company’s transactional dataset to create segments based on the customer’s purchase history.
Identify customer segments based on the overall buying behaviour of the client
An unsupervised model that generates the optimum number of segments for the customer base
Segments generated can be interpreted and transposed into business actions
Available at the UCI Machine Learning Repository
This dataset contains actual transactions for a UK based e-commerce store from 2010 and 2011. The company mainly sells unique all-occasion gifts. Many customers of the company are wholesalers. Our aim is to analyze the transactions made from the dataset. From the analysis, we will develop a model to segment customers into groups, based on their common characteristics and past purchase behavior.
ETL - Jupyter Notebook, Python Libraries
Visualizations - Matplotlib, Seaborn
ML - Sklearn, K-Means Clustering algorithm
A detailed description of the whole project can be viewed in the Project_Presentation file.