Journal of System and Computer Engineering

Application of the C45 Decision Tree Method in Evaluating the Potential and Contribution of Retribution to Pad: Case Study of Barru Regency

2025-05-15T13:09:34+00:00

Local Original Revenue (PAD) is a vital source for financing regional development, with levies as the main component. However, the main challenge faced is the inability of conventional evaluation methods to identify factors that influence the contribution of levies to PAD effectively. This study aims to evaluate the potential and contribution of levies to PAD by applying the Decision Tree C4.5 method. This research method uses a quantitative data-based approach, by analyzing tax data from various sectors, including Hotel Tax, Parking Tax, Entertainment Tax, and Advertising Tax. The results of the study indicate that the C4.5 method successfully identified more complex contribution patterns and provided a deeper understanding of the influence of seasonal and external factors on tax contributions. Entertainment Tax and Hotel Tax showed the largest contributions in certain periods, while Parking Tax showed greater stability throughout the year. The implications of this study indicate that the application of C4.5 can improve the effectiveness of PAD management, by providing a basis for tax policies that are more data-based and responsive to economic and seasonal fluctuations.

Classification of Chocolate Consumption Using Support Vector Machine Algorithm

2025-05-16T00:07:21+00:00

Chocolate, derived from the processing of cocoa beans (Theobroma cacao), is a widely consumed product with potential health risks when consumed excessively. This study investigates the classification of chocolate consumption behaviors using the Support Vector Machine (SVM) algorithm and evaluates its classification performance. A benchmark dataset on chocolate consumption was employed, partitioned into nine folds for training and testing purposes. To mitigate issues related to data imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The experimental findings indicate that SVM, enhanced by SMOTE, demonstrates a reliable capacity for classifying chocolate consumption categories. Performance evaluation across multiple experiments revealed variations in Accuracy, Precision, Recall, and F1-Score, with overall accuracies ranging from 50% to 60%, suggesting moderate but consistent classification performance.

Optimizing Car Wash Services with Web-Based Ordering System

2025-05-15T13:09:20+00:00

The car wash service industry faces various operational challenges such as long queues, difficulty in finding a reliable location, and unclear information about prices and services. This study aims to optimize car wash services through a web-based booking system. This system allows customers to book services online, choose a convenient time, and make electronic payments, which can reduce waiting times and increase convenience. The research method used is a mixed approach, with data collection through surveys, interviews, and observations at several car wash locations. The results show that the implementation of a web-based booking system improves operational efficiency and customer satisfaction, especially in terms of ease of booking, speed of service, and quality of information provided. However, there is still room for improvement in terms of the timeliness of the wash and the quality of service results. This study also identifies factors that influence customer adoption of web-based systems, such as ease of use, perceived benefits, and social influence. In conclusion, the implementation of a web-based booking system has a positive impact on the performance of the car wash service business by improving operational efficiency, customer satisfaction, and service quality.

Sentiment Analysis in Indonesian’s Presidential Election 2024 Using Transfomer (Distilbert-Base-Uncased)

2025-05-17T13:01:05+00:00

Utilizing a transformer-based natural language processing model called DistilBERT-base-uncased, this study investigates the use of sentiment analysis in relation to Indonesia's 2024 presidential election. Particularly during political events, sentiment analysis is a potent tool for gaining insight into public opinion. The program divides public posts' sentiment into positive and negative categories by examining social media data (twitter). In order to assure consistency and correctness, the dataset used in the research has been carefully selected. DistilBERT is then used to train the model. The result shows from 19920 row of data only 4.47% of Indonesia’s citizen left positive comment.

Decision Decision Support System for Aren Sugar Aid Using SMART Method

2025-05-15T13:19:25+00:00

Sugar palm (Arenga pinnata Merr) is a type of palm plant that is widely found in Indonesia. This plant is able to produce sap liquid from its cut flower bunches. Chemically, sugar palm sap contains 87.2% water, 12.7% carbohydrates, 0.24% ash, 0.2% protein, and 0.02% fat. Simple Multi Attribute Rating Technique is a multi-attribute decision-making method used to assist decision makers in determining several alternative choices. Each alternative is arranged based on a number of attributes, where each attribute has a certain value that is assessed on a certain scale. In addition, each attribute is given a weight that indicates its level of importance compared to other attributes. The application of a Decision Support System with this method can produce more effective, fast, and accurate decisions in the initial selection process for recipients of palm sugar production assistance. The reliability of this system is proven through testing using the White Box Testing and Basis Path Testing methods, which produce a V(G) value of 9.