CRUDE OIL PRICE MOVEMENT PREDICTION MODEL FOR INVESTMENT USING THE NAÏVE BAYES ALGORITHM

Abstrak

Crude oil prices are a key indicator in the highly volatile global economy, influencing investment decisions in the energy sector. This study aims to develop a predictive model for crude oil price movements using the Naïve Bayes algorithm. The dataset was obtained from historical oil price data along with supporting variables such as currency exchange rates, stock indices, and gold prices over a five-month period. The research process included data cleaning, data selection, data transformation, and modeling and evaluation using RapidMiner Studio software. Validation was performed using the k-fold cross-validation technique to measure model performance based on accuracy, precision, and recall metrics. The test results showed that the Naïve Bayes model was able to provide an accuracy rate of 85.00%, precision of 83.67%, and recall of 85.42%. These findings demonstrate that the Naïve Bayes-based approach is quite effective in predicting the direction of crude oil price movements, thus it can be used as a basis for more rational investment decision-making. This research also provides a practical contribution to the development of data mining-based analytical methods to support energy commodity investment strategies.