Publication Search

Career selection is an important process for students at Darussalam Gontor University (UNIDA) because it influences their academic development and future employment. However, many UNIDA students experience difficulties in determining suitable careers due to a lack of understanding of their psychological characteristics. This study aims to build a Decision Support System (DSS) for career recommendations for UNIDA students based on psychological test results using the Simple Additive Weighting (SAW) method. The psychological data used are non-clinical test results collected through a structured questionnaire from six respondents and converted into numerical scores. The research stages include determining criteria and weights, compiling a decision matrix, normalization process, calculating preference values, and ranking career alternatives using SAW. The career alternatives used consist of academics, corporate professionals, entrepreneurs, managers, and social/public services. The results show that the managerial career alternative obtained the highest preference value of 0.861, followed by entrepreneurs at 0.824, corporate professionals at 0.778, social/public services at 0.737, and academics at 0.703. These findings demonstrate that the SAW method is capable of providing objective and systematic career recommendations based on the psychological profiles of UNIDA students. This research is expected to assist UNIDA students and academics in making more informed career decisions tailored to individual characteristics

The selection process for students eligible for the National Selection Based on Achievement (SNBP) requires objective and structured assessment because it involves various academic and non-academic criteria. This study aims to develop a Decision Support System (DSS) to determine the ranking of SNBP eligible students at SMAN 8 Surabaya using the Additive Ratio Assessment (ARAS) method. The ARAS method is used to evaluate student alternatives based on their report card scores for semesters 1-5, academic ability tests (TKA), academic achievements, non-academic achievements, discipline, organizational activity, and attendance through a normalization process to obtain relative Ki values. The results of the study show that the system is capable of producing objective student rankings with relative utility values (Ki) ranging from 95.15 to 89.38, where the highest value indicates the best alternative from all alternatives. The application of ARAS-based DSS can improve the efficiency, transparency, and consistency of the SNBP student selection process.

Heart disease is the leading cause of death in Indonesia and globally, necessitating an early screening system that is both accurate and clinically trustworthy. Although XGBoost demonstrates high predictive performance, its black-box nature undermines clinical trust, while low recall risks missed diagnosis an unacceptable consequence in population screening, especially in middle-income countries with limited healthcare resources. This study aims to develop a sensitive, transparent, and implementation-ready heart disease screening framework through the integration of SHAP-based Explainable AI. The CDC's Indicators of Heart Disease dataset (319,795 samples) was processed according to WHO/CDC standards, followed by class imbalance handling, hyperparameter optimization using RandomizedSearchCV, evaluation based on metrics sensitive to minority classes (AUC, recall, F1-score, AUC-PR), and threshold tuning to maximize recall. The baseline model showed a very low recall of 12.18%. After optimization and threshold tuning at 0.10, the model achieved recall >96% (96.79%) with a G-mean of 0.7477, supported by SHAP interpretation stability and the ability to capture non-linear interactions between advanced age (AgeCategory_WHO) and poor general health (GenHealth). SHAP analysis confirmed the alignment of dominant features with medical evidence, and its visualizations provide transparent explanations for healthcare professionals indicating its potential implementation as an interpretable clinical decision support system.

The assessment of students’ academic performance in higher education is generally still dominated by conventional numerical approaches, which are less capable of representing qualitative and subjective variables such as classroom activeness and student participation. These approaches often result in evaluations that are not holistic and do not fully reflect students’ overall academic achievements. Therefore, this study aims to analyze the concept of fuzzy logic as a support tool for assessing students’ academic performance in higher education, with a case study of students at Universitas Asahan. The research method employs a descriptive qualitative and quantitative approach by applying Mamdani fuzzy logic. The input variables consist of exam scores, assignment scores, and classroom activeness, while the system output is the category of academic performance, namely sufficient, good, and very good. The sample data consist of ten active undergraduate students from Universitas Asahan. The data processing stages include fuzzification, the construction of fuzzy rules (rule base), fuzzy inference, and defuzzification using the centroid method. The results indicate that fuzzy logic is able to integrate quantitative and qualitative variables and accommodate uncertainty in academic assessment. The resulting evaluation is more proportional and realistic compared to conventional assessment methods based solely on average scores. Therefore, fuzzy logic can be considered an effective and flexible alternative approach to support student academic performance assessment systems in higher education.

The determination of scholarship recipients is a very important process in supporting students’ educational success, particularly in providing fair opportunities for high-achieving students who require financial assistance. However, in practice, this process often faces various challenges, such as assessor subjectivity and uncertainty in evaluating the applied criteria. Therefore, a decision support system is needed to assist decision-making in an objective and measurable manner. This study aims to implement the Fuzzy Tsukamoto method as a decision support system for determining scholarship eligibility. The criteria used in this study include Grade Point Average (GPA) as an indicator of academic achievement and parents’ income as an indicator of students’ economic conditions. The Fuzzy Tsukamoto method was selected because it is capable of producing crisp output values based on predefined fuzzy rules. Student data were processed through several stages, namely fuzzification to transform input data into fuzzy values, inference using the minimum operator, and defuzzification using the weighted average method. The results of the study indicate that the application of the Fuzzy Tsukamoto method is able to generate more objective, consistent, and measurable decisions. Based on the calculation results, a scholarship eligibility score of 63.9 was obtained, which falls into the eligible category. Thus, the Fuzzy Tsukamoto method can be considered an effective alternative to support fair, systematic, and transparent decision-making in determining scholarship recipients.

This research aims to design and develop a decision support system to determine the recipients of assistance in the Family Hope Program (PKH) in Pogo Tena Village. This system uses the (Technique for Order Preference by Similarity to Ideal Solution) method which aims to assist decision-makers in selecting families who meet the criteria to receive social assistance based on several predetermined factors, such as income level, number of family dependents, health conditions, and education. The method used in this study is a qualitative and quantitative method with a case study approach on PKH Pogo Tena Village. Data was obtained through interviews with related parties, field observations, and data collection from existing documents. In this system, the assessment is carried out by comparing alternative performance values based on pre-established criteria, and then using the TOPSIS method to determine the families who are eligible for assistance. The results of this study show that the designed decision support system can provide more objective and transparent recommendations for aid recipients. Using the TOPSIS method, the system can prioritize beneficiaries based on their proximity to the ideal solution, which helps minimize subjective errors in the beneficiary selection process. This research is expected to contribute to increasing the effectiveness and efficiency in the implementation of the Family Hope Program in Pogo Tena Village, as well as as a reference for other agencies that want to apply similar methods in social assistance programs.

The process of determining scholarship eligibility often faces challenges related to subjectivity and uncertainty in assessment criteria, which can result in inaccurate and unfair decisions. Scholarship selection generally involves multiple criteria, such as academic achievement, family economic conditions, and supporting factors that are difficult to evaluate using conventional decision-making methods. Therefore, an appropriate decision support approach is required to handle such uncertainty effectively. This study aims to implement the Fuzzy Mamdani method in a decision support system to determine scholarship eligibility more objectively and accurately. The research method consists of data collection, fuzzification of input variables, formulation of fuzzy rules, inference using the Mamdani approach, and defuzzification using the centroid method to obtain a crisp eligibility value. The results show that the Fuzzy Mamdani method is capable of producing flexible eligibility scores by considering the degree of membership of each criterion. The generated output reflects real conditions more comprehensively compared to traditional methods. The implementation of this method can assist decision-makers in improving transparency, consistency, and fairness in scholarship selection. This research is expected to contribute to the development of intelligent decision support systems in the field of educational assessment.

The process of determining eligibility for social assistance recipients is often constrained by subjective assessments and uncertainty in decision-making criteria. This condition can lead to inaccurate targeting and unfair distribution of aid. Therefore, an appropriate decision support method is required to handle data uncertainty effectively. This study aims to apply the Fuzzy Mamdani method to determine the eligibility of social assistance recipients based on several assessment criteria. The criteria used in this study include monthly income, number of dependents, and housing conditions. The research method consists of data collection, fuzzification, formulation of fuzzy rules, inference using the Mamdani approach, and defuzzification to obtain a crisp output value. The results show that the Fuzzy Mamdani method is able to classify recipients into eligible and non-eligible categories more flexibly compared to conventional methods. The generated eligibility values reflect real conditions more accurately by considering degrees of membership for each criterion. The implementation of this method can assist decision-makers in improving the accuracy, objectivity, and fairness of social assistance distribution. This research is expected to contribute to the development of intelligent decision support systems in the social welfare sector.

This research explores the role of human algorithm interaction mechanisms in enhancing trust, reliability, and user confidence in Decision Support Systems (DSS). Traditional DSS models often focus solely on algorithmic accuracy and performance, neglecting crucial factors such as transparency and user engagement, which are essential for building trust. By incorporating explainable AI (XAI) techniques like SHAP and LIME, real-time feedback mechanisms, and user-friendly interfaces, the study develops structured interaction models that improve the interpretability of AI-driven decisions. The results show that transparent decision-making processes and interactive features significantly enhance user trust, making DSS more reliable and easier to adopt. Users interacting with systems that provide clear, understandable explanations of decisions, along with real-time updates on the system’s confidence, reported higher levels of decision-making confidence, especially in high-stakes scenarios. These improvements lead to greater user engagement and adoption of the system in various domains, including healthcare and finance. The study also highlights the importance of balancing interpretability with efficiency in user interface design to ensure both trust and usability. The findings contribute to the design of more user-centric DSS that prioritize trust, interpretability, and cognitive factors, providing a framework for the successful integration of intelligent decision support systems in complex decision-making environments. Future research should focus on refining interaction models and exploring the broader applicability of these systems in different sectors.

This study explores the transformative role of big data-driven Decision Support Systems (DSS) in global digital enterprises, particularly focusing on their impact on operational efficiency and corporate governance. By leveraging big data analytics, DSS offer organizations the tools to process vast amounts of real-time data, enabling executives to make more informed decisions that optimize resources, improve productivity, and reduce operational costs. The research highlights the integration of predictive analytics, machine learning, and real-time data processing within DSS, which allows businesses to gain strategic insights and anticipate market trends. Furthermore, the study emphasizes the significant role of DSS in enhancing corporate governance, improving transparency, accountability, and compliance with regulations. These systems foster better decision-making processes, which contribute to building trust among stakeholders and ensuring long-term organizational success. However, the study also identifies several challenges in implementing big data-driven DSS, including data management complexities, technological integration difficulties, and the need for skilled personnel. Despite these challenges, the findings demonstrate that big data-driven DSS are pivotal in driving competitive advantage, operational optimization, and governance improvements. The research concludes with actionable recommendations for executives to adopt and implement big data-driven DSS, emphasizing the importance of continuous support, training, and system integration. The study also suggests future research directions, including exploring the integration of emerging technologies like AI and IoT into DSS and assessing their long-term impact on sustainability and corporate governance.

This research aims to implement a Multi-Attribute Decision Making (MADM) approach using the AHP–TOPSIS method to assist PT. XYZ in selecting the most suitable intern candidate for the Social Media Specialist position. The increasing number of applicants each year makes the selection process more complex, requiring a systematic and data-driven decision support system. AHP was used to determine the priority weights of five main criteria—Interview, Experience, Portfolio, Skill, and Achievement—along with their subcriteria. All pairwise comparison matrices met the consistency requirements, indicating valid weights. The TOPSIS method was then applied to calculate the preference scores of ten candidate alternatives based on the weighted normalized decision matrix, ideal solutions, and distance measures. The results show that candidate A3 achieved the highest preference score (0.9422), followed by A7 and A8, making them the top recommended candidates. This study demonstrates that integrating AHP and TOPSIS effectively supports companies in conducting objective, efficient, and accurate recruitment decision-making processes.

Manual quality assessment of Platelet Concentrate (TC) is highly subjective and inconsistent, necessitating an objective, automated classification system. This study aims to develop a computationally efficient, low-cost model for TC quality classification using Histogram Features extracted from grayscale images combined with the K-Nearest Neighbor (KNN) algorithm. The methodology employed critical preprocessing steps, including StandardScaler for normalization and SMOTE for balancing the training data, followed by optimization across K=1 to K=30. The optimal model achieved a maximum accuracy of 69.23% at K=6, with an F1-Score of 71.43%, confirming robust performance on the imbalanced testing set. The results validate the effectiveness of the Histogram-KNN approach as a consistent and reliable decision support system for rapid TC quality screening in resource-limited settings.

The disparity in the quality of rehabilitation services across regional work units presents a significant challenge to effective public management. This study aims to bridge the gap between problem diagnosis and policy prediction by proposing a hybrid, data-driven approach. We integrate K-Means Clustering to map the current state of service quality and Stochastic Simulation to predict the impact of strategic interventions. Using the 2024 Public Satisfaction Index (IKM) dataset from the National Narcotics Agency (BNN), the K-Means algorithm initially identified 26 work units (15.7%) in the "Red Zone" (critical performance), highlighting urgent areas for improvement. Next, a stochastic simulation modeling a "Directed Priority Intervention" scenario was run. The results predicted a significant structural shift in the distribution of service quality, characterized by an 80.8% decrease in critical units (down to 5 units) and a 71.8% increase in excellent performing units (up to 67 units). These findings validate that the integration of clustering and simulation provides a comprehensive framework for evidence-based decision-making, enabling policymakers to optimize resource allocation and efficiently accelerate national service standardization.

Penelitian ini bertujuan untuk mengembangkan sistem pendukung keputusan yang dapat membantu tim Marketing Officer (MO) PT. Alvarel Technology Innovation dalam menentukan status pelanggan secara objektif dan terstruktur. Sistem ini dirancang menggunakan kombinasi metode Analytical Hierarchy Process (AHP) dan Weighted Sum Model (WSM). Metode AHP digunakan untuk menentukan bobot kriteria yang meliputi Potensial Pasar, Urgensi, Finansial, serta Hubungan dan Reputasi, dengan memastikan konsistensi matriks perbandingan berpasangan. Hasil pembobotan kemudian digunakan dalam metode WSM untuk melakukan perhitungan skor total pelanggan dan menyusun pemeringkatan status berdasarkan nilai tertinggi hingga terendah. Data penelitian diperoleh dari catatan internal perusahaan dan wawancara dengan Marketing Officer, dengan jumlah sampel 30 pelanggan. Hasil pengujian menunjukkan bahwa sistem dapat menghasilkan peringkat status pelanggan dalam lima kategori, yaitu potensial, prospek, pending, pasif, dan skip. Temuan utama memperlihatkan bahwa kategori prospek memperoleh skor tertinggi dan menjadi prioritas tindak lanjut. Dengan demikian, sistem pendukung keputusan berbasis AHP–WSM ini mampu mengurangi subjektivitas, meningkatkan efisiensi, serta memberikan rekomendasi yang lebih akurat dan terukur untuk mendukung pengambilan keputusan strategis perusahaan dalam pengelolaan pelanggan.

This study investigates the role of knowledge management (KM) capabilities in enhancing managerial decision-making within organizational settings. Using a systematic review approach, ten peer-reviewed journals published between 2019 and 2024 were analyzed to identify key themes, patterns, and empirical findings related to knowledge management implementation and its influence on decision-making processes. The review reveals that strong knowledge management capabilities particularly in knowledge acquisition, storage, sharing, and utilization significantly contribute to improving the accuracy, speed, and strategic quality of managerial decisions. The findings also show that organizations with well-developed knowledge management infrastructures, supported by digital technologies and a culture of knowledge sharing, demonstrate greater adaptability, innovation, and problem-solving effectiveness. This study concludes that knowledge management capabilities are essential for strengthening evidence-based decision-making and enhancing organizational competitiveness. Implications for managers emphasize the need to invest in knowledge management systems and foster collaborative knowledge practices. Suggestions for future research include expanding the scope to cross-industry comparisons and integrating knowledge management with emerging technologies such as AI-based decision support systems..

Decision Support Systems (DSS) can become inaccurate when used with imprecise, incomplete, or dynamically changing data. Fuzzy logic techniques based on conventional methodologies may be strong at handling vagueness, but are unable to adapt their behavior in response to different data distributions on their own. This paper recommends the creation of an Adaptive Fuzzy Logic Integration Framework that dynamically updates membership functions and rule weights in response to data variation to enhance decision accuracy under uncertainty. The described framework combines Fuzzy Inference Systems (FIS) with learning-based parameter update concepts borrowed from adaptive optimisation. The model was simulated and executed on a hybrid algorithmic platform that included gradient-based parameter tuning and iterative feedback learning. Experimental tests were conducted on uncertainty-generated data sets to compare adaptive and conventional fuzzy models in terms of ISME (Root Mean Square Error), convergence stability, and decision accuracy. Previous results show that the adaptive model achieves a 21.4% increase in accuracy and a 28% improvement in convergence rate compared to non-adaptive fuzzy systems. Moreover, the model ensures stable performance even in the presence of random data perturbations, demonstrating its ability to handle uncertainty. This book incorporates a self-tuning fuzzy decision model that converts static inference structures to dynamic evolving decision engines. The outcomes establish a foundation for next-generation smart DSS for real-time optimization in uncertainty.

This study presents the integration of a Large Language Model (LLM) Ollama with the OpenStreetMap (OSM) API within a Business Intelligence (BI) framework to develop an intelligent, location-based recommendation system. The system is designed to assist users in finding dining, leisure, and resting places through natural language interaction and contextual understanding. The LLM interprets user input semantically, transforms it into structured spatial queries, and retrieves relevant geospatial data from OSM. The data are then analyzed, categorized, and visualized using BI methods to enhance interpretability and decision-making. The system was implemented using Next.js, Leaflet.js, ensuring interactivity and scalability for web-based deployment. Technical evaluation focused on system accuracy, response time, and output consistency. Results demonstrate an average response time of 1.74 seconds, 80% accuracy, and 80% consistency, proving the model’s efficiency in producing relevant, context-aware recommendations. This integration highlights the potential of combining open geospatial data, local LLMs, and BI analytics to create intelligent, data-driven decision support systems applicable to tourism, urban planning, and spatial information management.

The selection process for prospective cadets at a maritime college is routinely carried out every year. In the current system, the processing and calculation of prospective cadet scores uses Microsoft Excel tools, but this takes a long time and can lead to errors in the calculation of scores and the recapitulation of selection results. In addition, unintegrated data can lead to data duplication, resulting in inaccurate selection results that can be detrimental to prospective cadets. A fast, precise, and accurate integrated decision support system is needed to support the selection process for prospective cadets. The author conducted a study on the prospective cadet admission system at UNIMAR AMNI Semarang using the Multi-Objective Optimization On The Basis Of Ratio Analysis (MOORA) method to assist in the selection of qualified prospective cadets who meet the established criteria. With this decision support system using the Multi-Objective Optimization On The Basis Of Ratio Analysis (MOORA) method, it can be used to solve the selection problem for prospective cadets because it has a short calculation time, is simple, transparent, and has high flexibility. This system will be built using the Codeigniter Framework and a MySQL database.

N the rapidly evolving digital era, decision-making has become a critical aspect across various fields, including education, where choices such as selecting an Islamic boarding school (pondok pesantren) are often influenced by complex and subjective factors. This study addresses the dilemma faced by Diyah, a junior high school student, in determining the best reasons for choosing Pondok Pesantren Darularafah Raya, highlighting the limitations of manual, personal-based processes that fail to systematically consider measurable criteria like educational quality, learning environment, facilities, discipline, and instilled religious values. The advancement of information technology provides a solution through Decision Support Systems (DSS), utilizing the ORESTE (Organization, Rangement Et Synthèse De Données Relationnelles) method, which effectively processes ordinal data to produce objective rankings based on subjective yet structured preferences. Unlike other methods such as SAW or AHP that rely on numerical data, ORESTE emphasizes relative preference weights, making it suitable for individual decision-making contexts like educational choices. The novelty of this research lies in applying ORESTE in a DSS focused on analyzing an individual's best reasons for selecting a pesantren, aiming to reduce subjective bias and enhance rationality. The primary objective is to develop a DSS using the ORESTE method to analyze and determine Diyah's optimal reasons for choosing the pesantren. Through this, the system is expected to accelerate evaluation processes, improve objectivity, and identify dominant factors influencing educational decisions. Findings from the implementation demonstrate accurate rankings that prioritize key criteria, leading to more efficient and data-driven outcomes. Implications include aiding students, schools, and educators in understanding influential factors, fostering objective assessment systems, and serving as a reference for future studies integrating MCDM methods with computer-based systems in personalized educational decision-making.

Lecturers are a key element in improving the quality of education in higher education. Effective assessment of lecturer performance is essential for evaluation and improvement of education quality. Instituito Profissional de Canossa (IPDC) evaluates lecturer performance through manual methods involving students, this process often produces inaccurate data and slows down decision making. For this reason, a decision support system is needed that can accommodate all the criteria needed in decision making using the promethee method to assess lecturer performance. Promethee was chosen in this research because of its ability to consider data characteristics and provide more accurate results. This DSS will consider three assessment criteria, including education, community service and research. The results of the DSS implementation with the Promethee method can provide recommendations for lecturer performance rankings that help the quality assurance team in identifying outstanding lecturers.