PERBANDINGAN MODEL ALGORITMA NAIVES BAIYES DENGAN ALGORITMA WHALE OPTIMIZATION UNTUK PREDIKSI VOLATILITAS HARGA EMAS DI MASA DEPAN

ARYAGUNA, RAKHA FAWWAZ (2024) PERBANDINGAN MODEL ALGORITMA NAIVES BAIYES DENGAN ALGORITMA WHALE OPTIMIZATION UNTUK PREDIKSI VOLATILITAS HARGA EMAS DI MASA DEPAN. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (455kB) | Preview
Preview	Text (ABSTRAK) 02 ABSTRAK.pdf Download (90kB) | Preview
	Text (BAB I) 03 BAB 1.pdf Restricted to Registered users only Download (201kB)
	Text (BAB II) 04 BAB 2.pdf Restricted to Registered users only Download (707kB)
	Text (BAB III) 05 BAB 3.pdf Restricted to Registered users only Download (337kB)
	Text (BAB IV) 06 BAB 4.pdf Restricted to Registered users only Download (672kB)
	Text (BAB V) 07 BAB 5.pdf Restricted to Registered users only Download (96kB)
	Text (DAFTAR PUSTAKA) 08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (215kB)
	Text (LAMPIRAN) 09 LAMPIRAN.pdf Restricted to Registered users only Download (321kB)

Abstract

Gold, as a high-value commodity, serves as a hedge against economic instability. This research aims to develop a model for predicting gold price volatility by optimizing the Naïve Bayes algorithm using the Whale Optimization Algorithm (WOA). The method involves collecting gold price and relevant financial data, processing the data, and developing the Naïve Bayes model with WOA. Two algorithms, Naïve Bayes and WOA, are evaluated using metrics such as MAPE, MSE, RMSE, and AVE. The results indicate that Naïve Bayes achieves high accuracy and low errors, leveraging the assumption of feature independence. WOA provides solid results with a high Rsquared Score but slightly higher errors than Naïve Bayes. Performance evaluation of WOA highlights the sustainability of its results in changing market conditions. The conclusion emphasizes that Naïve Bayes excels in accuracy and stable performance, while WOA offers an adaptive alternative depending on market dynamics. Regular monitoring is necessary to ensure the sustainability and robustness of the model, particularly WOA, in the face of changing market conditions. This research provides valuable insights for investors and business stakeholders in making investment decisions related to gold price volatility. Keywords: Gold, volatility prediction, Naïve Bayes, Whale Optimization Algorithm, model performance Emas, sebagai komoditas bernilai tinggi, digunakan sebagai lindung nilai terhadap ketidakstabilan ekonomi. Penelitian ini bertujuan mengembangkan model prediksi volatilitas harga emas dengan mengoptimalkan algoritma Naïve Bayes menggunakan Whale Optimization Algorithm (WOA). Metode ini melibatkan pengumpulan data harga emas dan data keuangan terkait, pengolahan data, dan pengembangan model Naïve Bayes dengan WOA. Dua algoritma, Naïve Bayes dan WOA, dievaluasi menggunakan metrik MAPE, MSE, RMSE, dan AVE. Hasilnya menunjukkan bahwa Naïve Bayes memiliki akurasi tinggi dan kesalahan rendah, memanfaatkan asumsi independensi fitur. WOA memberikan hasil solid dengan R-squared Score tinggi, namun dengan tingkat kesalahan yang sedikit lebih besar daripada Naïve Bayes. Evaluasi performa WOA menyoroti keberlanjutan hasilnya dalam kondisi pasar yang berubah. Kesimpulan menekankan bahwa Naïve Bayes unggul dalam akurasi dan kinerja stabil, sementara WOA memberikan alternatif adaptif tergantung pada dinamika pasar. Diperlukan pemantauan berkala untuk memastikan keberlanjutan dan ketangguhan model, khususnya WOA, dalam menghadapi perubahan kondisi pasar. Penelitian ini memberikan wawasan berharga bagi investor dan pelaku bisnis dalam pengambilan keputusan investasi terkait volatilitas harga emas. Kata kunci: Emas, prediksi volatilitas, Naïve Bayes, Whale Optimization Algorithm, kinerja model.

Actions (login required)

View Item