Abstract

Personalized learning experiences have undergone revolutionary transformations as a result of the use of artificial intelligence (AI) into education. The application of AI-driven adaptive learning methods designed especially for the Parakh assessment system's multiple-choice question (MCQ) selection is examined in this abstract. In order to dynamically evaluate a student's ability and modify the question complexity in real time, the suggested method makes use of machine learning models. The system carefully chooses questions that address each learner's unique learning gaps and offer suitable challenge levels based on past performance data and question information. Preprocessing assessment data, extracting features from student interaction logs, and creating a recommendation system to improve the accuracy of MCQ selection are all part of the methodology. Evaluation measures like knowledge retention rates, time to completion, and response accuracy are utilized to evaluate the effectiveness of the system. By optimizing learning outcomes, this AI-based strategy seeks to provide a more stimulating and productive assessment environment. The method might completely change the way formative evaluations are carried out and guarantee that every student gets a customized education that is in line with their particular academic requirements.