This Author published in this journals
All Journal Teika
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PREDIKSI HARGA SAHAM PT BANK CENTRAL ASIA TBK BERDASARKAN DATA DARI BURSA EFEK INDONESIA MENGGUNAKAN METODE K-NEAREST NEIGHBORS (KNN) Edward Ridley Tauran
TeIKa Vol 11 No 2 (2021): TeIKa: Oktober 2021
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v11i2.2609

Abstract

Stock prediction using the K-Nearest Neighbors method is intended to be able to provide predictions that can help the public and investors to find out the share price in the future. Through the literature study stage, interviewing and looking at daily stock price data where the attributes used are daily stock open price, highest price, lowest price, daily stock closing price, selling exchange rate data, rupiah exchange rate against the US dollar, and interest rate data 1 month. The results obtained with the total data are 1415 data, with a total of 70% training data and 30% testing data using the K-Nearest Neighbors method, then the accuracy rate of 61.79% is obtained. Through the confusion matrix the value given for the precision or level of accuracy of the expected information for data classified as experiencing an increase is 62.03% and data experiencing a price reduction is 60.76%, while for the recall value or the success rate for information found for data classified as an increase the price was 87.35% and the data classified as having experienced a price decline was 26.82%.