A STUDENT PERFORMANCE PREDICTION APPROACH USING MACHINE LEARNING

Abstract

Machine learning is used in a variety of fields, including education, pattern identification, gaming, business, social media services, online customer care, and product recommendations. The future of the children is a major factor in the importance of the educational system. All of today's kids want to go to college, which raises the need for M.L. operations in the educational system and leads to higher education producing a lot of data. For the objective of assessing student performance, many tools are available. Reviewing student data will benefit from data mining, which is a technique for discovering hidden information. The amount of information available in the subject of education is very helpful to both instructors and pupils. As the institute grows, it is becoming increasingly crucial to integrate M.L. technology in the classroom. Clustering is one of the core techniques widely used in data analysis. Modified K-means is one of the most well-liked and successful clustering techniques, while there are others as well. There are several methods for classifying data, with decision trees being the most popular. Decision trees are commonly used in analyses of student performance even though they are less stable than modified K-means. the topic of unsupervised algorithms is raised They use cluster analysis to classify the students into groups based on characteristics. The cluster size may be calculated using the elbow technique, which will help in determining the optimal solution. There is an elbow method that scans the length of the arm and the elbow point. It is simple to improve children's performance and future using the M.L. technique. Together with students, institutions and teachers may boost performance