PREDIKSI HARGA SAHAM PERUSAHAAN KELAPA SAWITMENGGUNAKAN PEMODELAN MLP DAN RBF

Linda Sari Dewi (Sistem Informasi STMIK Nusa Mandiri)

Techno Nusa Mandiri : Journal of Computing and Information Technology
Vol 11 No 1 (2014): Techno Nusa Mandiri : Journal of Computing and Information Technology Periode Ma

There is great demand estimation method to obtain accurate predictions of the future and use the predictions to the decision making process. This study aims to estimate the daily stock price PT. Astra Agro Lestari Tbk, Indonesia's crude oil company, using one of the promising alternative tool, the Neural Network. Two Neural Network model, namely Multilayer Perceptron (MLP) and Radial Basis Function (RBF). Various combinations of data preprocessing techniques, network topology, functions, and training algorithm is presented in order to obtain the best model. The empirical results show that neural networks Radial Basis Function provides the best forecasting accuracy than Multilayer Perceptron.