Naive Algorithm Bayesian Model for Gold Price Trend Classification
Article Sidebar
Main Article Content
Abstract
Gold is one of the most attractive investment instruments due to its value stability and role as a hedge against economic uncertainty. However, gold prices are highly influenced by external factors such as global oil prices and currency exchange rates. This study aims to analyze gold price trends by applying the Naïve Bayes algorithm as a data mining classification method. Historical data on gold prices, oil prices, and the USD/IDR exchange rate were processed using the Knowledge Discovery in Database (KDD) framework, including data cleaning, transformation, and grouping. The model was validated using the split validation method. The results indicate that the Naïve Bayes algorithm achieved an accuracy of 87.5% with a Root Mean Square Error (RMSE) of 0.215. These findings confirm the significant impact of macroeconomic factors on gold price fluctuations. Therefore, the proposed model is not only simple and efficient but also has strong potential as a decision support system to assist investors in anticipating market volatility and formulating more effective investment strategies.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Guntur, M., Santony , J., & Yuhandri , Y. (2018). Gold price prediction using the Naive method Bayes in investment to minimize risk. RESTI Journal (System Engineering and Information Technology) , 2(1), 354–360. https://doi.org/10.29207/resti.v2i1.276.
Mahena , Y., Rusli, M., & Winarso, E. (2015). Predicting world gold prices as a support for gold stock investment decisions using data mining techniques . Kalbiscentia : Journal of Science and Technology , 2(1), 36–51. (PDF available in the Kalbis repository ). research.kalbis.ac.id+1
Link: https://research.kalbis.ac.id/Research/Files/Article/Full/LFO7P4HJ6D7O5X587IB41OUPG.pdf . research.kalbis.ac.id
Saputro, ND (2015). Application of the Support Algorithm Vector Machine learning for gold price prediction. UPGRIS Informatics Journal , 1(1), 10–19. (PDF available from Jurnal Informatika / Neliti ). Link (PDF): https://journal.upgris.ac.id/index.php/JIU/article/download/805/1048 . UPGRIS Journal
Nafi'iyah , N. (2016). Comparison of linear regression, backpropagation and fuzzy Mamdani on gold price predictions. Proceedings National Seminar on Innovation and Technology Application in Industry (SENIATI) , pp. 291–296. (PDF / metadata available in the ITN Malang e- journal ). ITN E-Journal+1
Link: https://ejournal.itn.ac.id/index.php/seniati/article/view/840 . ITN E-Journal
Villacampa , O. (2015). Features selection and classification methods for decision making: A comparative analysis ( Doctoral dissertation ). Nova Southeastern University . Retrieved from NSUWorks : https://nsuworks.nova.edu/gscis_etd/63 . NSUWorks+1
Suyanto. (2017). Data mining . Yogyakarta: Informatics.
Vulandari , R.T. (2017). Data mining . Yogyakarta: Gava Media.