Kazumali, Eliah2020-04-182020-04-182016Kazumali, E. (2016) Neural network model for predicting students’ achievement in blended courses at the University of Dar es Salaam, Master dissertation, University of Dar es Salaam, Dar es Salaam.http://41.86.178.5:8080/xmlui/handle/123456789/9556Available in print form, East Africana Collection, Dr. Wilbert Chagula Library, Class mark (THS EAF QA76.87K39)Knowledge about the likely students’ achievement in blended courses prior to sitting for examinations provides educators room for early intervention on students’ learning process, especially to those at risk. Unfortunately, Leaning Management Systems (LMSs), Moodle in particular lacks an environment to assist educators obtain the likely achievement of students from time to time before undertaking their examinations. This raised the need to propose a model that would predict students’ achievement based on their activities in Moodle and previous achievement at undergraduate studies, taking a case of blended postgraduate programmes at the University of Dar es Salaam (UDSM). This study applied a branch of artificial intelligence, namely artificial neural network, in building a prediction model. A simulation experiment was conducted in Matrix Laboratory (MATLAB) utilizing seventy eight instances (78) of students’ logs of three blended courses extracted from Moodle for 2013/2014 and 2014/2015 academic years. Mean Square Error (MSE) and Coefficient of Determination (R2) performance metrics were used to find the best prediction model considering ten possible models. The study revealed a model with an architecture of 4:10:1 trained with Bayesian Regularization (BR) to be the best model resulting to least MSE of 0.0170 and high R2 of 0.93 on training. During testing, the model successfully predicted 78% of the students’ achievement with risk and pass status.enNeural computersArtificial intelligenceAcademic achievementEducation, SecondaryUniversity of Dar es SalaamBlended coursesThesis