Adaptive Learning for Standardised Test Preparation

Online learning platforms have revolutionized education and gained immense popularity, particularly after the onset of the Covid-19 pandemic, due to their provision of flexible and accessible learning opportunities. Many educational platforms now incorporate adaptive learning technologies to personalize the learning experience for individual students based on their strengths and weaknesses. This stands in contrast to traditional tutoring systems that employ a one-size-fits-all approach. Despite the significant advancements in Intelligent Tutoring Systems, there remains a noticeable gap in the integration of adaptive learning for standardized tests such as GRE, GMAT, SAT, and O/A Levels, tests that collectively attract millions of students each year. Thus, the objective of this paper is to extend the application of adaptive learning, exposing students to topics and questions of varying difficulty levels based on their individual strengths and weaknesses when preparing for standardized tests, and eventually helping them to break the traditional cycle of attempting all the past papers for MCQ based examinations. Through our experimental results, we demonstrate that the pipeline employed to develop our tutoring system can significantly enhance learning speed and assess topic proficiency by catering to the unique needs and abilities of each student.