The selection of the best employee is an important performance evaluation process aimed at improving employee motivation and productivity. At the Statistics Indonesia (BPS) of Gorontalo Province, the selection process still involves subjective considerations, which may affect the consistency and objectivity of decision-making. Therefore, a data-driven approach is needed to support the evaluation process. This study aimed to implement the Naïve Bayes algorithm to classify the best quarterly employee based on employee performance assessment data. The dataset consisted of performance records from 54 employees of BPS Gorontalo Province collected from the first quarter of 2023 to the fourth quarter of 2024. The classification process utilized BerAKHLAK behavioral indicators, discipline indicators, and Employee Performance Achievement (CKP) as predictor variables, while the target variable was employee status, namely best employee and non-best employee. The research stages included data preparation, data transformation, training and testing data partitioning, model development using the Naïve Bayes algorithm, and model evaluation using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The evaluation results showed that the proposed model achieved an accuracy, precision, recall, and F1-score of 100%, indicating high classification performance on the dataset used in this study. These findings demonstrate that the Naïve Bayes algorithm is effective in classifying employee performance and can be utilized as a decision-support tool for determining the best quarterly employee. The implementation of this method is expected to enhance the objectivity, consistency, and transparency of employee performance evaluation at Statistics Indonesia (BPS) of Gorontalo Province.