Effective inventory management is essential to the sustainability and profitability of the retail sector. Retailers are quite concerned about food waste since it affects both the environment and the economy. The application of machine learning (ML) techniques can help classify merchants according to their waste habits by analyzing food waste data and generating insights. Targeted measures for sustainability and waste reduction can be informed by an understanding of store types based on waste data. Decision-making in retail analytics has historically shifted in favor of data-driven strategies. Earlier methods of inventory management included manual tracking, simple analytics, or waste thresholds that were predetermined. These methods do give some insights, but they frequently fall short of machine learning's sophistication and flexibility. Conventional systems find it difficult to recognize subtle trends in big datasets or adjust to the shifting dynamics of retail. The issue at hand is classifying shops using machine learning based on their patterns of food waste. Retailers differ in the kinds of goods they offer, the types of customers they serve, and the waste patterns of their patrons. Creating a machine learning-driven method to evaluate food waste data and group stores into useful groups or clusters is the difficult part of the job. Afterwards, by using this classification, waste reduction techniques that are unique to each type of retailer can be developed. The complexity and unpredictability of retail operations make machine learning (ML)-driven retailer type classification necessary. Large-scale food waste data can be analyzed using machine learning algorithms, which can also be used to spot hidden trends and automatically learn from the data to classify stores according to their waste profiles. With a more sophisticated understanding of the variables influencing food waste, more focused and efficient waste reduction techniques can be developed thanks to this method.