Affiliations: [a] Department of Artificial Intelligence and Data Science Panimalar Engineering College, Chennai, Tamil Nadu, India
| [b] Department of ECE, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India
| [c] V.S.B. Engineering College, Karur, Tamil Nadu, India
| [d] Sathyabama University, Chennai, Tamil Nadu, India
Correspondence:
[*]
Corresponding author. V. Sathya, Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai-600123, Tamil Nadu, India. E-mail: [email protected].
Abstract: In a recent survey conducted in the year of 2022, it came to know that India contains around 50 percentages of its population is occupied by young people belonging to the age group of 25 and falls under a category of student. Guiding this young mass people in a right guidelines and strengthening the future of this students are a huge responsibility. The power of students are elder citizens of India such as their parent’s teachers, professors, entrepreneur etc. The only way to strengthen the future of the young students is through educating them. In order to analyze how effectively the student can compete with the modern world and what kind of teaching methodology are needed to be adopted to each student, which is very important to every country peoples. Therefore, we are provided to be interpret the effective education to the children’s and students. To monitor student’s academic record there is a need of building a new model which can predict the performance and risk factor associated with the students for the next academic year. This is done by gathering the student’s previous academic record to analysis with different classifier techniques. The proposed work is aim to build a model, that can predict the student’s competency level and the risk factors or students are improve himself with all fields effort to both academic and non-academic activity. This proposed model also helps the parents, teachers, and educational institutes. This entire analysis is done by using different Machine Learning (ML) bifurcations algorithm. Also we aim to find the best classifier which can emerge with a highest predicting accuracy among all other classifiers to the above said problems.
Keywords: Decision tree, random forest, support vector, logistic regression, classifier
