PERANCANGAN SISTEM PENGELOMPOKAN DAN REKOMENDASI SAHAM LQ45 DENGAN K-MEDOIDS, EXPONENTIAL MOVING AVERAGE DAN WEIGHTED PRODUCT

Abstract

Stock is an instrumentation that has the fundamentals
of a company. Owning a share means owning the
shares of the company. Shares can be traded on the
Indonesian Stock Exchange by the entire public. The
LQ45 stock grouping and recommendation application
is a desktop-based application that aims to assist in
making investment decisions in the Indonesian Capital
Market. The application is designed using the Python
programming language. The application applies the KMedoids
Clustering method to group stocks and
Exponential Moving Average along with Weighted
Products to make recommendations or sort shares.
Users can enter the desired share criteria and the
application will recommend according to the input
criteria from the user. Testing on this application is
carried out by the BlackBox testing method,
questionnaire, K-Medoids Algorithm Testing and the
output results of the program. From the results of the
black box testing, the application results can run
according to plan. In testing the K-Medoids Algorithm,
the results obtained that the number of clusters
determined are in accordance with the number of 2
clusters using the elbow method. And in testing the
output results of the program, the results obtained are
the recommendation accuracy of 80.8%.