<![CDATA[Selecting engine oil that is appropriate for vehicle characteristics is an important factor in supporting engine maintenance and performance. At Automekanika Bosch Car Service, the oil selection process still relies on technicians’ experience, which may result in less consistent recommendations. This study aims to develop a web-based synthetic engine oil recommendation system using the Naive Bayes algorithm to support oil selection based on vehicle characteristics. The research data were obtained through interviews with workshop technicians and processed into a training dataset consisting of 96 records with 8 input attributes, namely engine type, engine capacity, vehicle age, transmission, usage intensity, operating environment, driving pattern, and engine condition. The data were classified into 9 synthetic engine oil classes. The system was developed using the Waterfall method, consisting of requirements analysis, design, implementation, testing, and maintenance. Classification performance was evaluated using the Leave-One-Out Cross-Validation (LOOCV) method. The evaluation of 96 data records resulted in 73 correctly classified records and 23 incorrectly classified records, achieving an accuracy of 76.04%. These results indicate that the Naive Bayes algorithm can be applied to a synthetic engine oil recommendation system based on vehicle characteristics and can support a more structured and consistent recommendation process.]]>
Copyrights © 2026
