An optimized approach towards increasing the sale rate in a Grocery Mart by using Association Rule Mining Approaches

Sales can be affected by many factors due to heavy competition in the business world. The analysis to identify the customer's interest in advance is an important factor in it. Association rule mining in machine learning allows for analyses of the huge dataset to identify associated item sets. A focus is given to the daily sales of grocery datasets. In this paper, we have collected a dataset from a local grocery market and taken initial steps for analysis. It has been identified that the dataset for a year will be analyzed completely to identify the customer's interests. The customer's interest also varies based on the season and the customer's regular purchase habits. Based on the purchase interests observed, regular customers can be encouraged by sending messages about associated product offers. A brief study on the Apriori and FP Growth algorithms has been conducted based on a literature review to determine their performance. Based on the analysis, a model has been proposed in which our dataset can be used for identifying associated datasets based on different factors such as customer and season. The best algorithm shall be selected based on accuracy, execution time, and the number of associated pairs. Further, a hybridization of algorithms and other tools is suggested for enhancing performance.