A Multi-Layer Perceptron Model in Analyzing Parametric Classification of Students’ Assessment Results in K12

This paper focuses on assessment results based on the analysis of parametric classification with the support of the multi-layer perceptron (MLP) model. MLP is the most effective tool or model to assess and evaluate training sets, such as the score of each student, exam results, and the like. Domains are evaluated as to know the career pathing of students in the different categorical aspects. Indispensable to each categorical response are the results of the completed curriculum under the K12 educational approach. Career assessment should be administered to classify students in the different categorical domains namely: arts and design, business, information and communication technology, criminal justice and law, culinary arts, education, engineering and architecture, health care, liberal arts, math and science, and vocational respectively. MLP model has been implemented to assess students’ scores and compare them to what specific categorical domain do they belong. The three main components of MLP as the computational model are the input layer, hidden layer, and the output layer. Employment of MLP in a supervised learning problem helps to pair all the training sets of input and output to train the dependence between them. This paper gives the reader the results of parametric training through associating MLP in all training datasets and the 87% accuracy results being garnered to sustain relevant parametric results.