A Hybrid Recommendation System for Retail Marketing

In the modern world, online shopping is extensively popular among humanity. People use online shopping for almost all products and services due to the excellent offers and convenience. Nearly every online service provides shopping assistance to its users through recommendation systems. These recommendations will increase the profit and sales of that firm. At the same time, such a system will assist the customers in product selection and gives additional discounts. However, using such recommendation algorithms in retail marketing is a broad area, and the research scope is still open. In this study, we aim to develop a recommendation system for a retail store by promoting online shopping. The study used transaction data from a supermarket to generate association rules using the well-known methods; Apriori and FP-Growth. Also, we used a recipe information dataset to give recipe recommendations through keyword searching. The results demonstrate that recipe recommendations will improve the system's efficiency from time to time. Also, the system will generate intelligent suggestions based on user preferences. Our study will be beneficial for retail stores to maintain a decent relationship with their customers.