A Recommender System for Rural and Urban Learners

In Educational data mining, learning process evaluation reveals the students’ involvement in learning. It leads to improve the quality and success rate of the students in educational environment. Students’ intellectual performance varies in learning environment and evaluated by different criteria. This study helps to find out the intelligent quotient level of the student and their performance, which are dissimilar in a classroom. Stanford Binet Intelligence Scale and Criterion Reference Model are used to evaluate the intelligence and performance of the students. Machine learning techniques are employed to find the intelligent quotient and performance of rural and urban students using students’ dataset. Model based clustering technique is used to determine the similarity in the students’ dataset based on the nature of the intelligent quotient and performance. Each cluster reveals the identity based on students intelligence level. The performance also categorized on descriptive modeling. Multilayer Perceptron technique classifies the intelligent level of the students and their performance. The study determines the association between intelligent level of the rural and urban students and performance through descriptive and predictive modeling. This analysis recommends the teaching community to provide right training to the rural students for their improvement of academic competence.