INTERNATIONAL JOURNAL OF ADVANCE RESEARCH
IN MULTIDISCIPLINARY

This study's experimental setting is based on the PSEB, India student dataset. The dataset under consideration consists of many parameters that describe the students' academic performance, learning environment, and examination. To determine the dependencies between the features of learners, all of these factors have been taken into account. To eliminate the abnormalities and convert the obtained dataset into the necessary format, data preparation has been carried out. The qualities of the learners have been stored as a multidimensional array using the multidimensional OLAP features. These characteristics let the analyst provide the learner profile in a multifaceted manner. Additionally, we have suggested a methodology based on collaborative frequent pattern mining approaches for evaluating student performance and responding to challenging educational questions. This model has identified multiple hidden relationships among learners' features by utilizing the association rule mining idea in conjunction with the decision tree classification technique. Thus, "Multi-dimensional frequent pattern discovery for association rule classification system" is the name given to the suggested model. A multi-dimensional dataset was subjected to constraint-based analytical mining in order to identify intriguing patterns within the educational dataset. The suggested architecture also incorporates visual analytics tools to provide a graphical representation of the findings. Additionally, an automated decision support system is required to analyze student performance in accordance with the needs examined in the national context. In order to address the educational questions, the "EDARC" analytical tool was created as part of this research project.