Abidatul Izzah, Yuita Arum Sari, Ratna Widyastuti, Toga Aldila Cinderatama
Stock Prediction is developed in both of two studies, economics, and data mining. Stock predictions got special attention due to its importance for creating a more effective and efficient planning. In this study, Improved Multiple Linear Regression (IMLR) was built into a mobile application based android platform for stock price prediction. IMLR is a hybrid Multiple Linear Regression with Moving Average technique. The app was built in several steps, which are requirement analysis, system design, implementation, and testing. Data were collected from the finance.yahoo.com page with category 'Jakarta Composite Index (A JKSE)' which were automatically taken by using Yahoo Finance API. In this app, users not only could see daily stock history but also stock price predictions in real time. The mobile app accuracy prediction give the better result than the common algorithm with the value are 15087.465 in MSE, 122.831 in RMSE, and 3.255 in MAPE. © 2017 IEEE.
Informatics Engineering, Polytechnic of Kediri, Kediri, Indonesia; Computer Science, Brawijaya University, Malang, Indonesia
