Crop Recommendation System Using Improved Apriori Algorithm

Abstract

A crop suggestion system is a technologically advanced tool that helps farmers choose which crops to plant in a certain location or with precise environmental circumstances. These systems use a variety of data sources and analytical methods to give farmers customized crop recommendations. This work presents the Crop Recommendation System Using an Improved Apriori Algorithm, which is an Apriori-based crop recommendation system. The goal of the system is to assist farmers in making well-informed choices about which crops to grow and what fertilizers to use depending on the properties of the soil and environment. With consideration for crop variety, climate, and soil nutrient content, the suggested method is an enhanced version of the Apriori algorithm. Tests of the updated algorithm on a dataset of soil samples from different parts of India revealed that it could correctly suggest the optimal crop. The model's output, association rules, is a suggestion system that farmers can use to boost crop productivity while lowering input costs. The method suggested operates in three phases: In the first stage, preprocessing the data is carried out to gather the input parameters that are crucial for determining the recommendation system. In Stage 2, the recommendation system's association rules are extracted by using an iterative approach to determine the threshold support count and confidence. Stage 3: The recommendation system's knowledge base is formed by pruning the top 8 apriori rules depending on priority. From the experiments, it is evident that the improved apriori algorithm-based extracted recommendation system is an interesting development in precision agriculture that could raise farming practices' sustainability and efficiency.