Open AccessModel Fourier Untuk Prediksi Harga Saham Astrazeneca Menggunakan Algoritma Levenberg-Marquardt
Author(s) -
Hafizh Al Kautsar
Publication year - 2021
Publication title -
jurnal tika
Language(s) - English
Resource type - Journals
eISSN - 2723-8202
pISSN - 2503-1171
DOI - 10.51179/tika.v6i02.486
Subject(s) - levenberg–marquardt algorithm , mean squared error , gradient descent , process (computing) , fourier transform , covid-19 , computer science , artificial intelligence , algorithm , mathematics , statistics , artificial neural network , medicine , infectious disease (medical specialty) , disease , pathology , operating system , mathematical analysis
The soaring cases of covid-19 prompted some countries to find solutions to save their people. One of the steps that is currently being taken is with vaccines. Several leading companies in the world that produce drugs are known to have produced vaccines for covid-19, one of which is AstraZeneca. AstraZeneca vaccine is known as the most widely used vaccine in all countries in the world. Interesting thing to research is how the development of the company's stock engaged in the medical field, especially companies that produce vaccines for covid-19. This study used Fourier's approach to modeling its curve fittings. As for the prediction process using levenberg-marquardt algorithm which is known to be reliable to perform the prediction process. Levenberg-Marquardt's algorithm has the advantage of a fast training process and reliable accuracy due to its work that combines Gauss-Newton and Steepest Descent. The result is root mean square error value from the test result that was lower than the Root Mean Square Error value in the training process. This indicates that the prediction went well.