RFM (recency, frequency, monetary) analysis is a marketing technique used to determine quantitatively which customers are the best ones by examining how recently a customer has purchased (recency), how often they purchase (frequency), and how much the customer spends (monetary).
The developed system takes raw data from user, it can be bank sector data or retail sector data and send it to the backend API which detects the data category from its content and after cleaning this data, it performs analysis on it using machine learning techniques, and divides the users in different segments (New, Best, Loyal, Lost, Almost lost etc). based on their spending behaviors.
The system also predicts the future sales of different categories based on the data provided in case of retail data, otherwise in case of bank data it predicts the account balance, withdrawal amount, and deposit amount of each customer in future.
In case of retail data, instead of predicting the sales of all the products which can be in hundreds, we first categorize the products in different categories based on their descriptions using NLP and ML techniques and then predict the sales of each category. Below image shows the occurrences of each keyword (identified by the system) in the data and the word-clouds of each category.
