Prediksi Harga Emas Dengan Menambahkan Variabel Covid-19 Menggunakan Metode Naïve Bayes. (Indonesian)

COVID-19 or previously known as the corona virus is a pandemic that is being watched closely throughout the world and the country of Indonesia at this time. The COVID-19 pandemic can have several impacts on various sectors, especially in economic sectors such as stock prices and gold. Gold is one of the precious metals that is in great demand by the public and can change at any time, making it necessary for investors to predict the price of gold. One method or algorithm that can be used to predict prices is the Naïve Bayes Classifier (NBC). This study uses 7 variables to predict gold prices, namely past gold prices, dollar exchange rates, euro exchange rates, world crude oil prices, the number of positive cases of COVID-19, the number of cases recovered from COVID-19, and the number of deaths caused by COVID-19 in Indonesia. The dataset used was obtained from a variety of reliable sources starting from the period March 2 2020 - October 29 2020, testing will later be carried out with a variety of different scenarios. The results of the highest accuracy test in this study were 83% in 3 different test scenarios, while the effect of the COVID-19 variable on the accuracy level using the Naïve Bayes method was not very significant [ABSTRACT FROM AUTHOR]

COVID-19 atau sebelumnya dikenal sebagai virus corona merupakan sebuah pandemi yang sangat di waspadai di seluruh dunia dan negara Indonesia saat ini. Pandemi COVID19 dapat mengakibatkan beberapa dampak di berbagai sektor, terutama di sektor ekonomi seperti harga saham dan emas. Emas merupakan salah satu logam mulia yang cukup diminati oleh masyarakat serta dapat berubah sewaktu-waktu sehingga membuat investor perlu untuk melakukan prediksi harga emas. Salah satu metode atau algoritma yang dapat digunakan untuk memprediksi harga adalah Naïve Bayes Classifier (NBC). penelitian ini menggunakan 7 variabel untuk memprediksi harga emas yaitu variabel harga emas masa lalu, kurs dollar, kurs euro, harga minyak mentah dunia, jumlah kasus positif COVID-19, jumlah kasus sembuh dari COVID-19, dan jumlah kematian yang disebabkan COVID-19 di Indonesia. Dataset yang digunakan diperoleh dari berbagai sumber yang terpercaya yang dimulai periode tanggal 2 maret 2020 - 29 oktober 2020, pengujian nantinya akan akan dilakukan dengan berbagai scenario yang berbeda-beda. Hasil pengujian tingkat akurasi tertinggi dalam penelitian ini yaitu sebesar 83% yang terdapat pada 3 scenario pengujian yang berbeda, sedangkan pengaruh variable COVID-19 pada tingkat akurasi menggunakan metode naïve bayes hasilnya tidak terlalu signifikan. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Comprehensive Science (JCS) is the property of Green Publisher and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)