• Adarsh Saji
• Dinesh Satre
• Deepanjaya Modak
• Aniket Chavan
• Aniket Dandade

The estimation of the difficulty level of a given question is required in order to understand how well the student understood a particular topic, which would help the teachers to grade a student accordingly and decide how much attention is to be given to a particular student. there is no doubt that teachers often misjudge the difficulty level of the questions. In order to avoid that, a module is created in a data processing system for rating difficulty of a question. In this mechanism, a set of question bank is set by the teacher/admin whose difficulty level is judged by the basically two factors, first, the number of times the question is answered correctly by a particular number of students and second, the amount of time required in by the student to provide a sound analysis. The mechanism that generates the difficulty score of a question based on such above-mentioned factors uses a machine learning module. This machine learning module map features to assigned weights for scaling the difficulty score. This provided analysis could be very valuable for both teachers and students in order to detect unclear problem statements and rectify students’ misconceptions.

Machine Learning, Ordinal Logistic Regression, classify

"Computerized Adaptive Assessment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.353-356, June 2019, Available :http://www.jetir.org/papers/JETIR1908797.pdf

"Computerized Adaptive Assessment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp353-356, June 2019, Available at : http://www.jetir.org/papers/JETIR1908797.pdf