A Web-Based User Interface for Machine Learning Analysis

The purpose of this study is to develop a user-friendly web application that follows human computer interaction design guidelines and principles and is used to recognize patterns in datasets and to predict outputs of instances that it hasn't previously encountered. The application design follows human computer interaction design guidelines and principles and it employs supervised machine learning algorithms linear regression, logistic regression, and backpropagation for prediction. Java is used in the backend to create a model that maps the input and output data based on any of the machine learning algorithms while Play Framework and Bootstrap are used to display content in frontend. The application allows users to upload datasets that will be used to train and test the system. Each column of an uploaded dataset represents an attribute and each row represents an instance. The system is also developer friendly and allows changes be made to the source code for a more customized interaction.