DEEP LEARNING BASED PREDICTION MODEL FOR COURSE REGISTRATION SYSTEM

  • T.M.Nithya, K.S.Guruprakash, L.Amudha

Abstract

Nowadays in any educational system, selecting course by students according to their need is a
challenging task. This paper proposed deep learning approach to predict the courses for the student
according to their cutoff marks. The cutoff mark of student is calculated for this course prediction which
analyzes the accurate course to choose for their college education. Choosing the appropriate course in
any educational institution with infrastructure facilities is the major drawback in the existing system. The
existing system will only give the information about the institutions. To overcome the anomalies of the
existing system this system proposes the effective course registration system using deep learning based
prediction model. The major technique used to predict the course is Decision Tree Algorithm. This
algorithm comes under the Deep Learning Technique which comes under Artificial Intelligences that will
process the cutoff mark of the student to know about the Science and engineering colleges. This algorithm
will analyze the uploaded dataset of the various courses in the colleges and the facility that are providing.
The student will initially register their details before logging in to the website. This application will filter
the data based on cutoff mark when the student login to the homepage. This will sort out the course
information on basis of their cutoff marks. The advantage of the proposed system is that the student can
choose the course that they need to study with the accurate predicted data. The Arts and Engineering
College are uploading the detail in admin. The BE course are CS, ECE AND EEE are available in course
prediction

Published
2020-04-13
How to Cite
T.M.Nithya, K.S.Guruprakash, L.Amudha. (2020). DEEP LEARNING BASED PREDICTION MODEL FOR COURSE REGISTRATION SYSTEM. International Journal of Advanced Science and Technology, 29(7s), 2178-2184. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/12653