Publication Search

This study compares the effectiveness of MAUT (Multi-Attribute Utility Theory), SMART (Simple Multi-Attribute Rating Technique), and WASPAS (Weighted Aggregated Sum Product Assessment) methods in a decision support system for determining the best employees at Sisilia Boutique. The quality of human resources is crucial in the retail business, but performance evaluation is often influenced by subjectivity. To address this, a multi-criteria-based decision support system is needed. MAUT translates preferences into a numerical scale, SMART calculates the average value of attributes based on weights, while WASPAS combines weighted summation (WSM) and weighted multiplication (WPM) for more balanced results. Employee performance data from Sisilia Boutique in June 2025, including attendance, store layout, customer service, and discipline, were used as the research object. The comparison results show consistency in the highest (K3) and lowest (K7) ratings across the three methods, with differences in the middle ratings. WASPAS offers a more balanced distribution of final scores, making it a comprehensive alternative for performance evaluation.

Behind the success of the Free Nutritious Meal Program (MBG), there are several problems related to the health factors of the program targets, namely, there are several cases of allergies that occur in schools, inadequate understanding of allergen management owned by food processing vendors, and the high cost of laboratory tests and the process that takes a long time. So, to overcome these problems, an application is proposed that can help detect allergens in food products using data mining and machine learning approaches. SVM and AdaBoost algorithms each have advantages that can be used to help build an optimal allergen detection model. This research uses a cross-validation model validation method with a value of K = 10 to help improve the performance of the model built. In this study, from the entire fold, an average accuracy value of 98.74% was obtained. To evaluate the model built, this research has also conducted several new data inputs, and in each new data input, the accuracy value is obtained above 99%. This indicates that the model built, namely the combination of SVM and AdaBoost algorithms with the cross-validation model validation method, produces high accuracy, so this model can greatly assist the allergen detection process in food products.

This study aims to analyze the factors that influence students' interest in continuing their education to college using a machine learning approach. Data was collected through an online questionnaire completed by 727 students between July 27 and August 22, 2025, covering 23 variables consisting of respondent identity (gender, grade level, major) as well as internal and external factors such as parental support, learning motivation, and preferred type of college. The data preparation stage was carried out through column cleaning, deletion of empty data, encoding of categorical variables, and division of the dataset into 80% training data and 20% test data. The Naive Bayes algorithm of the CategoricalNB type was used because it was suitable for the categorical nature of the data. The evaluation results showed that the model was able to predict student interest with 96% accuracy. For the class of students interested in continuing their studies, the precision, recall, and F1-score values were above 0.95, while the performance in the class of students who were not interested was slightly lower due to the smaller amount of data. These findings show that Naive Bayes is proven to be effective and reliable in classifying students' interest in continuing their studies and can be the basis for decision-making in designing more targeted educational strategies.

This study aims to analyze and compare the performance of the Naive Bayes, K-Nearest Neighbors (KNN), and Decision Tree algorithms in predicting the purchase intention of e-commerce visitors using the Online Shoppers Purchasing Intention Dataset, which consists of 12,330 records and 18 variables, with the Revenue variable serving as the classification target. The preprocessing stage involved transforming categorical and boolean variables into numerical form, standardizing features using StandardScaler, and splitting the dataset into 80 percent training data and 20 percent testing data. Model evaluation was conducted using accuracy, precision, recall, F1-score, and ROC-AUC metrics, and was further strengthened by 10-fold cross-validation to obtain more stable results. The findings indicate that KNN achieved the highest accuracy of 0.866180, while Naive Bayes produced the highest recall value of 0.690998 and the highest ROC-AUC value of 0.821696. Meanwhile, Decision Tree demonstrated relatively balanced performance with an accuracy of 0.857259 and an F1-score of 0.571776, whereas the cross-validation results identified KNN as the model with the highest average accuracy of 0.8770. These findings suggest that the selection of a classification model for purchase intention prediction cannot rely solely on a single evaluation metric, as each algorithm possesses different strengths. Therefore, a comparative approach among algorithms can help determine the most suitable model for supporting consumer behavior analysis on e-commerce platforms.

This study evaluates the performance of three community detection algorithms—Leiden, Infomap, and Label Propagation—on the legal network of the Republic of Indonesia spanning the period 2014–2024. The network consists of 679 nodes and 2,295 edges, constructed based on citation relationships among regulations. The evaluation employs four network topology metrics: modularity, coverage, conductance, and inter-cluster density. Results show that the Leiden algorithm achieves the highest modularity score (0.522991), indicating the formation of communities with strong internal density. Additionally, it yields the lowest conductance value (0.302455), suggesting relatively well-isolated communities. In contrast, the Label Propagation algorithm produces the highest coverage (0.835294) and inter-cluster density (0.542331), but with a lower modularity (0.431583), reflecting the formation of large communities with less distinct boundaries. Infomap exhibits moderate performance, with a modularity score of 0.508406 and inter-cluster density of 0.420803, yet records a relatively high conductance (0.410409). Network visualizations reveal three major communities for each algorithm, representing thematic clusters such as institutional governance, constitutional law, and public finance. Overall, the Leiden algorithm is considered the most optimal for detecting modular, stable, and thematically coherent community structures within the complex and interrelated network of Indonesian laws.