International Journal of Informatics and Data Science

Film Popularity Analysis through Combined K-Means Clustering and Gradient Boosted Trees

Agi Candra Bramantia — 2025-06-30

The dynamic and competitive nature of the global film industry presents complex challenges in predicting film popularity, as success is shaped by the interplay of production investment, casting decisions, and audience preferences. This research addresses the limitations of previous studies that have focused primarily on direct relationships, such as budget versus box office returns, by introducing an integrated analytical framework that combines K-Means clustering and Gradient Boosted Trees (GBT) with explainable AI techniques. Utilizing the TMDB movie dataset and constructing features such as actor influence and studio power, the study segments films and predicts audience ratings while providing interpretable visualizations. The results reveal four distinct film clusters and demonstrate that actor influence and budget allocation are the most significant predictors of popularity. The proposed model achieves an R² score of 0.75 and a mean squared error of 0.35 in predicting audience ratings, while cluster analysis shows that Blockbuster films reach the highest average ratings (6.76), and Underperforming films the lowest (2.42). By integrating interpretable predictive modeling and interactive scenario tools, this research offers both theoretical advancement and practical value for industry stakeholders. However, the findings are limited by the available metadata and do not account for factors such as marketing or real-time audience trends, suggesting opportunities for future research to expand the analytical framework.

Decision Support System for Selecting the Best Hotel Using the Multi-Objective Optimization Method on the Basis of Simple Ration Analysis (MOOSRA)

Mesran — 2025-06-30

Selecting the best hotel is an important decision-making process that requires careful consideration of various criteria. In this study, we use the Multi-Objective Optimization by Simple Ratio Analysis (MOOSRA) method to determine the most suitable hotel based on a set of predetermined criteria. The MOOSRA method is a multi-objective optimization technique that uses a simple ratio of the overall favorable and unfavorable criterion scores to avoid negative values and reduce the impact of large variations in criterion values. This study aims to develop a decision support system that helps customers choose the best hotel based on criteria. The MOOSRA method is applied to a decision matrix constructed from hotel attributes, and the overall performance score of each hotel is calculated using a simple ratio formula.

Decision Support System for Performance Assessment of the Best Salesperson with the Integration of Entropy and WASPAS

Junhai Wang — 2025-06-30

The salesperson performance assessment is an important aspect of improving the effectiveness of a company's marketing strategy. However, this assessment process often faces the challenge of subjectivity, especially in determining the weights of the criteria used. To address this issue, this study implements a combination of the Entropy and WASPAS methods. The Entropy method is used to objectively determine the weights of the criteria based on data variation, while the WASPAS method is used to evaluate and rank alternatives. A case study was conducted on five salesperson personnel with the criteria used in selecting the best salesperson being sales target achievement, product mastery, communication skills, creativity, and work ethics. The results showed that Muhammad Iqbal (A3) ranked first with a score of 0.882, followed by Andi Saputra (A1) with a score of 0.796, Rizky Kurniawan (A5) with a score of 0.770, Budi Santoso (A2) with a score of 0.724, and Siti Rahmawati (A4) with a score of 0.655. The main contribution of this research is to present a more accurate and objective salesperson performance evaluation model through the integration of the Entropy–WASPAS method. This finding has practical implications for companies in selecting the best employees, identifying salesperson personnel with outstanding performance, and supporting strategic decision-making in human resource development in the marketing field.

Decision Support System for Selecting Student Recipients of Single Tuition Fee (STF) Assistance using Multi-Objective Optimization on the Basis of Simple Ratio Analysis (MOOSRA) Method

Johannes Syahputra Sihombing — 2025-06-30

Single Tuition Fee (STF) is a tuition fee borne by each prospective new student based on their economic capability. The process of determining the STF groups requires precision and time, as student data needs to be compared with the STF criteria one by one. The decision-making system in determining the STF groups that exist currently utilizes five criteria in assessing the parents' ability to pay for their child's education, namely: Parental Income, Possession of PKH Card, Document Completeness, Parental Dependents, and Academic Performance. Therefore, a decision support system is needed that applies the MOOSRA method to assist in determining the STF groups. There are five criteria used in this research: parental income, ownership of the PKH card, document completeness, parental dependents, and academic performance. The calculation results for several sample data yield the best final optimization value in the selection of students eligible for STF assistance, which is found in alternative A7 (Meli) with a total score of 0.863.

Decision Support System for Selecting the Best Graduates of Undergraduate Students Using the Analytical Hierarchy Process (AHP) Method

Lucius Yupiter Telaumbanua — 2025-06-30

The selection of top graduates is a crucial process in higher education, aiming to reward students who demonstrate the best performance during their studies. However, in practice, this process often only considers academic grades such as the Grade Point Average (GPA), without considering other factors such as organizational activity, non-academic achievements, or student attitudes and ethics. This can lead to unfairness and subjectivity in decision-making. This study aims to develop a Decision Support System (DSS) to assist the selection process of top undergraduate graduates objectively and measurably using the Analytical Hierarchy Process (AHP) method. AHP is used to determine the weight of each criterion based on its relative importance through pairwise comparisons. The criteria used include GPA, academic and non-academic achievements, organizational activity, and student behavior. This system provides a final result in the form of a graduate ranking based on the highest score. Test results indicate that the system is able to improve accuracy and transparency in the selection process of top graduates. This research is expected to become an information technology solution that supports fair and data-based decision-making in higher education.