Fandi Presly Simamora
Universitas Mikroskil

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimisasi Hyperparameter BiLSTM Menggunakan Bayesian Optimization untuk Prediksi Harga Saham Simamora, Fandi Presly; Purba, Ronsen; Pasha, Muhammad Fermi
Jambura Journal of Mathematics Vol 7, No 1: February 2025
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjom.v7i1.27166

Abstract

The accuracy of deep learning models in predicting dynamic and non-linear stock market data highly depends on selecting optimal hyperparameters. However, finding optimal hyperparameters can be costly in terms of the model's objective function, as it requires testing all possible combinations of hyperparameter configurations. This research aims to find the optimal hyperparameter configuration for the BiLSTM model using Bayesian Optimization. The study was conducted using three blue-chip stocks from different sectors, namely BBCA, BYAN, and TLKM, with two scenarios of search iterations. The test results show that Bayesian Optimization was able to find the optimal hyperparameter configuration for the BiLSTM model, with the best MAPE values for each stock: BBCA 1.2092%, BYAN 2.0609%, and TLKM 1.2027%. Compared to previous research on Grid Search-BiLSTM, the use of Bayesian Optimization-BiLSTM resulted in lower MAPE values.
Random Forest Optimization Using Recursive Feature Elimination for Stunting Classification Marpaung, Sophya Hadini; Sinaga, Frans Mikael; Rambe, Khairul Hawani; Simamora, Fandi Presly; Kelvin, Kelvin
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.35295

Abstract

Stunting is still a major health problem in Indonesia, with a prevalence of 27% in toddlers in 2023, far from the WHO target of below 20%. RSU Mitra Medika Tanjung Mulia in Medan serves patients with various socio-economic backgrounds, which affects the quality of services, including stunting detection. Conventional methods are prone to bias and error. This study used the Random Forest algorithm and the Recursive Feature Elimination (RFE) feature selection method to improve the accuracy of stunting classification. After data preprocessing and feature selection, two main variables were identified, namely age and height. The initial Random Forest model achieved an accuracy of 94.38%, which increased to 94.42% after hyperparameter tuning. The results showed that this approach produced an accurate, efficient model that can be integrated into clinical systems, helping medical personnel identify children at risk of stunting quickly and accurately, increasing the effectiveness of interventions, and supporting government efforts to reduce the prevalence of stunting