Jurnal Pilar Nusa Mandiri
Vol 14 No 2 (2018): PILAR Periode September 2018

PREDIKSI HARGA CRYPTOCURRENCY DENGAN METODE K-NEAREST NEIGHBOURS

Haerul Fatah (Program Pascasarjana Magister Ilmu Komputer STMIK Nusa Mandiri)
Agus Subekti (Pusat Penelitian Elektronika dan Telekomunikasi Lembaga Ilmu Pengetahuan Indonesia (LIPI))



Article Info

Publish Date
15 Sep 2018

Abstract

Electronic money is getting more popular as online transaction means among people especially for entrepreneurs, businessmen and investors due to its practicality. Cryptocurrency emerges as the solution to resolve the contrains of electronic money that depends heavily on third parties. One of widely used Cryptocurrency is Bitcoin. The price of bitcoin fluctuates in very short duration. It is similar with the fluctuation of stock price in stock market. Prediction for future price becomes important anad interesting. In this paper, we propose a prediction model for cryptocurrency price. Out proposed model predict the cryptocurreny price using KNN (K-Nearest Neighbors) method. With the parameter of k=3 and using linear NN search algorithm, out proposed method gives a mean absolute error (MAE) of 0.0018 and root mean squared error (RMSE) of 0.0089.

Copyrights © 2018






Journal Info

Abbrev

pilar

Publisher

Subject

Computer Science & IT

Description

Jurnal Pilar merupakan jurnal ilmiah yang diterbitkan oleh program studi sistem informasi STMIK Nusa Mandiri. Jurnal ini berisi tentang karya ilmiah yang bertemakan: Rekayasa Perangkat Lunak, Sistem Pakar, Sistem Penunjang, Keputusan, Perancangan Sistem Informasi, Data Mining, Pengolahan ...