• Ajay Choudhary
• Omansh Kumar Singh
• Kailash Yadav
• Manisha Singh

Machine Learning research fields are now fully emerged as interesting areas for research and development, which are now exposing useful knowledge from large data sets for many purposes like predicting student’s performance in case of Educational Data Mining and Learning Analytics. It can be beneficial for taking rapid actions in today’s educational systems. Existing techniques have used attributes which are mostly related to academic performance, family background, emotional and social influences; while attributes regarding family expenses and student’s personal information are usually ignored. In this paper, Machine Learning techniques, scikit-learn library and its algorithms are applied to predict that a student will be able to perform good in his graduation or not. Predicting performance of a student accurately based on their ongoing academic records is very important for effectively carrying out necessary interventions to ensure students on-time and satisfactory graduation. Predicting student’s performance in completing degrees (e.g. college programs) is much less studied and faces new challenges: (1) Students coming from different backgrounds and have selected different courses;(2) Since the courses are not equal it is not possible to make accurate predictions; (3) The evolving progress of student needs to be incorporated into the prediction. In this paper, we develop a new machine learning technique for predicting student performance in degree programs which is able to address the above key challenges. The proposed methodology has two major features. First, a bi layer structure comprising of multiple base predictor attributes and a cascade of predictors which is developed for making predictions based on students evolving performance states. On the other hand, a data-driven approach based on latent factor models and the probabilistic matrix factorization which aims to discover the course relevance and which is also important for constructing the efficient base predictors.

Prediction, Performance, Data Mining, Learning Analytics

"Tracking and Predicting Student Performance in Degree Programs Using Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.269-273, April-2019, Available :http://www.jetir.org/papers/JETIR1904I47.pdf

"Tracking and Predicting Student Performance in Degree Programs Using Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp269-273, April-2019, Available at : http://www.jetir.org/papers/JETIR1904I47.pdf