Framework for Data Analysis of Retail Market using Machine Learning Algorithms

Presenting a comprehensive analytical framework for analyzing and forecasting supermarket sales data with the goal of understanding the seasonal sales trends and customer approach towards the product to improve overall business performance. The methodology begins with data preprocessing and cleaning to ensure quality, integrity and reliability towards the data which is followed by Exploratory Data Analysis (EDA) to uncover sales trends, seasonal patterns, and product and customer anomalies. Product price analysis with respect to different countries was conducted to detect customer approach. Customers are sectioned together using customer repetition analysis, K-means clustering with Elbow method, and customer lifetime value models to categorize customers into low, medium, and high-value customers. Market Basket Analysis with association mining rule to identify products which are collectively co-purchased. Ultimately in the end, sales were forecasted using Seasonal ARIMA (SARIMA) to predict future revenue to inform critical business decisions. The proposed system provides actionable insights analyzing the potential growth of a business on the surface of the global market