• Aditya Shelar
• Siddhi Bhendkahle
• Mohit Patil
• Prof. Jitendra Chavan
• Sushmita Gatne

Precisely foreseeing students' future execution dependent on their continuous scholarly records is essential for viably doing important instructive sessions to guarantee students' on-schedule and acceptable graduation. In spite of the fact that there is a rich writing on anticipating student execution when taking care of issues or contemplating for courses utilizing information driven methodologies, foreseeing student execution in finishing degrees (for example school programs) is considerably less examined and faces new difficulties: (1) Students contrast massively as far as foundations and chose courses; (2) Courses are not similarly useful for making exact expectations; (3) Students' advancement should be consolidated into the forecast. In this paper, we build up a novel ML technique for foreseeing student execution in degree programs that can address these key difficulties. The proposed technique has two noteworthy highlights. Initial, a study of students marks variations in subjects is understood, by using ML techniques. Second, information driven methodology dependent on survey for students study habits and daily routine is considered to affect the performance.

Index Terms—Student performance prediction, personalized education, impact factor, gradient.

"STUDENTS PERFORMANCE PREDICTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.528-532, May-2019, Available :http://www.jetir.org/papers/JETIR1905O83.pdf

"STUDENTS PERFORMANCE PREDICTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp528-532, May-2019, Available at : http://www.jetir.org/papers/JETIR1905O83.pdf