Pemodelan Data Time Series Menggunakan Pendekatan Regresi Polinomial Lokal Pada Data Harga Saham MDKA

Abstract

<p class="AbstractEnglish">Investment is an important way to manage finances for profit. One of the most popular investments in Indonesia is buying and selling shares. In addition to getting profits, they also have risks. Therefore, analyzing stock prices before buying and selling is an important key in stock investing. Investors should buy stocks at a low price and sell them at a high price. One of the methods used is parametric regression analysis, but it has assumptions that must be met. A more flexible alternative is local polynomial regression without any particular assumptions. PT Merdeka Copper Gold Tbk with MDKA stock code is a company engaged in the mining and industrialization of gold, silver, and other associated minerals. The study of modeling the lowest daily price of MDKA shares using local polynomial regression showed excellent results. The high coefficient of determination exceeding 67% on the in-sample data indicates strong model performance, and the Mean Absolute Percentage Error (MAPE) value on the out-of-sample data is less than 10%, ensuring excellent model accuracy.</p><p class="AbstractEnglish"><strong>Keywords: </strong>local polynomial regression; MDKA shares; time series</p>