Publication Search

This research aims to implement Business Intelligence and the TOPSIS method in a Decision Support System for selecting the best-selling products in retail stores through an analytical Dashboard. Retail businesses generate large amounts of transaction data every day, but the data is often only used for operational reporting and has not been optimally utilized for strategic decision making. This study integrates Business Intelligence technology, data Warehouse, ETL process, Dashboard Analytics, and TOPSIS method to analyze product sales patterns and determine the best-selling products based on several criteria such as sales quantity, stock turnover, profit level, customer demand, and sales frequency. The research method uses a system development approach consisting of data collection, dimensional modeling, ETL implementation, TOPSIS calculation, Dashboard design, and system evaluation. The results show that the implemented system can accelerate reporting processes, improve decision-making accuracy, and assist management in identifying strategic products quickly and interactively. The integration of TOPSIS with Business Intelligence Dashboards contributes to effective data-driven decision making in retail management.

This study compared the performance of SARIMA and Prophet models in forecasting daily close prices of three major Indonesian banking stocks: BBCA, BBRI, and BMRI, using data from January 2020 to March 2026. Data were retrieved via the yfinance library, preprocessed, and split into 80% training and 20% testing sets. SARIMA modeling followed the Box-Jenkins procedure, while Prophet was configured with a Lag-1 regressor, weekly and monthly seasonality, Indonesian public holidays, and log transformation. Model performance was evaluated using MAPE, MSE, and Dstat metrics. Results showed that SARIMA outperformed Prophet in MAPE and MSE across all six stock-variable combinations, with MAPE values ranging from 1.3368% to 1.9386% for SARIMA and 1.5992% to 2.2300% for Prophet. However, Prophet demonstrated marginally higher Dstat values in several series. Both models achieved "Very Good" forecasting accuracy. A web-based forecasting system was also developed using Streamlit to make the models accessible to investors.

Early Marriage in Pagar Alam City is currently still quite high, the Pagar Alam Religious Court only relies on a recap of the number of cases per year to draw conclusions about the early marriage data. This method has limitations in classifying early marriage factors, so the Religious Court has difficulty in monitoring and controlling the occurrence of Early Marriage in Pagar Alam City. The purpose of this research thesis is to produce a classification system for Early Marriage factors using the K-Nearest Neighbor Algorithm to find out what factors influence the occurrence of Early Marriage, the method used in this study is the Cross Industry Standard Process for Data Mining (CRISP-DM) which has 6 stages, namely: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The testing stage in this study uses Confusion Matrix and BlackBox Testing. The final results of this study indicate that the system can classify Early Marriage factors. The classification model built achieved an Accuracy of 94.12% and a Precise value of 85.71% and a Recall value of 100.00%, while testing using Black Box testing in the form of alpha obtained a feasibility value of 83.2%, so this system is very suitable for use.  

This study proposes a computer vision-based system for automatically verifying the use of Personal Protective Equipment (PPE) in industrial environments. The system integrates the YOLOv8 object detection model, OpenCV for image processing, and a State Machine mechanism to manage the verification workflow. The verification process begins with employee identification through ID card scanning, followed by real-time detection of the head, safety helmet, and face mask using a camera, before generating a final PASS or FAIL decision. System evaluation was conducted using 250 testing scenarios to assess both model and system performance. The results show that the YOLOv8 model achieved an mAP@50 of 93.9%, while the overall verification system obtained 98.4% accuracy, 98.4% precision, 100% recall, and a 99.2% F1-score. The implementation of the State Machine contributed to a more stable and consistent verification process by ensuring that each inspection stage was executed in the correct sequence. These findings demonstrate that the proposed system can effectively support automated PPE compliance monitoring and has the potential to enhance occupational safety management in industrial workplaces. 

This study aims to compare the performance of three boosting algorithms, namely XGBoost, LightGBM, and CatBoost, to predict the success of MSMEs. The data used consists of 250 entries with 13 attributes that include business actor characteristics, initial capital, industry experience, financial record-keeping, internet utilization, business planning, partnerships, and the target variable success. The pre-processing stage includes checking for missing values, standardizing numerical attributes, and splitting the data into 80% training data and 20% test data. The evaluation results show that XGBoost provides the best performance with an accuracy of 0.92, precision of 0.8333, recall of 0.8333, F1-score of 0.8333, and ROC-AUC of 0.9715. LightGBM has an accuracy of 0.88, while CatBoost achieves an accuracy of 0.90. The research results show that XGBoost has the best ability to classify successful and unsuccessful MSMEs. The feature importance results also show that the success of MSMEs is influenced by a combination of several key factors. This research emphasizes that boosting algorithms are effectively used as predictive models to support the analysis of MSME success.

Tomato (Solanum lycopersicum) is a high-value horticultural commodity in Indonesia, yet its cultivation is frequently disrupted by leaf diseases that are difficult to distinguish visually. Diseases such as Bacterial Spot, Early Blight, and Tomato Yellow Leaf Curl Virus often present overlapping visual symptoms, making early and accurate diagnosis a significant challenge for farmers. The manual identification methods currently in use are inefficient and error-prone, ultimately leading to reduced crop yield  and quality. The general objective of this study is to develop software capable of automatically classifying tomato  leaf diseases. Specifically, this research aims to implement the MobileNetV3 Small architecture based on Convolutional Neural  Network (CNN) with ImageNet pre-trained weights to classify 10 types of tomato leaf diseases. The research methodology encompasses dataset collection from Kaggle comprising 10,000 images (1,000 per class), image pre-processing through resizing to 224x224 pixels, and normalization, as well as hyperparameter optimization (optimizer, learning rate, epoch, batch size) via scheduler. Model performance is evaluated using a confusion matrix encompassing accuracy, precision, recall, and F1-score.

This study aims to analyze the effect of artificial intelligence (AI)-based demand forecasting and big data analytics on inventory optimization through prediction accuracy among e-commerce actors or marketplace sellers in Curug. This research employed an explanatory quantitative approach involving 100 respondents selected through purposive sampling based on predefined criteria relevant to the research objectives. Data were collected using a structured Likert-scale questionnaire and analyzed using Structural Equation Modeling Partial Least Squares (SEM-PLS) by evaluating the measurement model, structural model, and mediation effects. The findings reveal that AI-based demand forecasting and big data analytics have a positive and significant effect on prediction accuracy. Furthermore, prediction accuracy has a positive and significant effect on inventory optimization and significantly mediates the relationship between AI-based demand forecasting, big data analytics, and inventory optimization. These findings indicate that the integration of AI and big data analytics contributes to more accurate demand prediction, leading to improved inventory management performance. The implication of this study suggests that e-commerce actors should improve data quality, analytical capability, and the adoption of predictive technologies to support more accurate, efficient, and responsive inventory decisions, thereby enhancing operational performance and competitiveness in responding to dynamic market demand.      

Artificial Intelligence (AI) has increasingly influenced higher education, including learning practices among students of Islamic Education (PAI). Applications such as ChatGPT, Claude AI, and Gemini are widely used to support academic activities, including information searching, understanding course materials, idea generation, and assignment completion. This study aims to examine the use of AI among PAI students and analyze its implications for critical thinking skills. A qualitative descriptive approach was employed at the Islamic Education Program of UIN Salatiga. Data were collected through written interviews with 12 students selected using purposive sampling and analyzed using an interactive data analysis model. The findings reveal that AI has become an important part of students’ academic activities due to its perceived usefulness and ease of use. Most participants demonstrated critical thinking behaviors by verifying AI-generated information, comparing multiple academic sources, and evaluating the accuracy of responses before using them for academic purposes. Nevertheless, excessive dependence on AI was found to potentially reduce students’ independent learning and analytical engagement. The study concludes that AI has a dual impact on critical thinking: it can enhance critical thinking when used reflectively and responsibly, but it may also weaken cognitive involvement when relied upon excessively. Therefore, strengthening AI literacy, digital literacy, and critical thinking skills is essential in higher education learning practices.

This study explores the role of artificial intelligence in strengthening cybersecurity threat detection frameworks for next-generation network environments. The rapid expansion of cloud computing, Internet of Things ecosystems, and distributed digital infrastructures has significantly increased cybersecurity risks and operational vulnerabilities. Traditional cybersecurity systems often struggle to detect sophisticated and evolving threats due to their dependence on static detection mechanisms. Using a qualitative research approach and content analysis method, this study examines recent developments in artificial intelligence, machine learning algorithms, and intelligent cybersecurity frameworks. The findings indicate that AI-driven cybersecurity systems improve real-time threat detection, anomaly identification, automated monitoring, and predictive security analysis. Machine learning technologies such as Random Forest, Support Vector Machine, and deep learning models demonstrate strong potential for enhancing intrusion detection accuracy and reducing false positive rates. The study also identifies critical challenges related to ethical governance, privacy protection, computational complexity, and adversarial attacks in AI-based cybersecurity systems

This study aims to analyze demand patterns and determine the most accurate forecasting method for the Kawachi KL 6167 A+ Emergency Lamp product to support inventory control decision-making. The data used in this study consist of product demand over 12 periods, showing an increasing trend with slight fluctuations in certain periods. The forecasting methods applied in this research include the Linear Trend Method, Quadratic Trend Method, and Moving Average (MA), while forecasting accuracy was evaluated using Mean Squared Error (MSE). The results indicate that the linear trend method provides a more suitable forecasting model compared to the quadratic trend method. The MSE value of the linear method is 69.31, whereas the quadratic method produces an MSE of 81.50, indicating that the linear method is more accurate due to its lower forecasting error. In addition, a 3-period Moving Average (MA) method was applied to forecast demand from period 13 to period 24. The forecasting results show that demand tends to stabilize within the range of 276–277 units, with the forecast for period 24 reaching 276.66 units, rounded to 277 units. Based on the findings, it can be concluded that the demand pattern for the Kawachi KL 6167 A+ Emergency Lamp demonstrates a relatively stable upward trend, making the linear trend method the most appropriate forecasting approach for predicting future demand. These forecasting results are expected to serve as a reference for companies in optimizing inventory planning to minimize the risks of stock shortages and overstocking.

Digital transformation in public services has encouraged government institutions to develop technology-based services, including the Online Police Record Certificate (SKCK) service at Kupang City Regional Police Resort. This study aims to analyze the effectiveness of the Online SKCK service as an administrative requirement at the Kupang City Regional Police Resort. The research employed a qualitative approach with a descriptive method. Data were collected through observation, interviews, and document analysis involving service officers and users of the Online SKCK service. Data were analyzed using an interactive model consisting of data reduction, data display, and conclusion drawing. The findings indicate that the Online SKCK service has improved accessibility, service efficiency, and transparency through the implementation of the PRESISI POLRI application. Based on the effectiveness indicators, namely program understanding, target accuracy, timeliness, goal achievement, and real change, the service can be categorized as moderately effective. Target accuracy and real change emerged as the strongest indicators, while program understanding and timeliness still face several challenges, including limited digital literacy among users, application system disruptions, and data verification issues. Nevertheless, the Online SKCK service has provided significant benefits in supporting the modernization of public services. The study concludes that improving system quality, strengthening public outreach, and developing a more integrated service system are necessary to optimize the effectiveness of the Online SKCK service at the Kupang City Regional Police Resort.

Hypertension is one of the leading non-communicable diseases contributing significantly to cardiovascular morbidity and mortality worldwide. Despite the availability of extensive electronic medical record data in healthcare institutions, these data are often utilized only for administrative reporting rather than predictive analysis. Consequently, opportunities to identify age groups with a higher probability of developing hypertension remain underutilized. This study aims to implement the Naïve Bayes classification algorithm to analyze age distribution and classify the risk of hypertension among patients using healthcare data. The research adopted the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, including business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Patient medical record data consisting of demographic and clinical attributes, including age, systolic blood pressure, diastolic blood pressure, body weight, gender, and hypertension status, were processed using the Naïve Bayes algorithm. Model performance was evaluated using a confusion matrix by measuring accuracy, precision, recall, specificity, and balanced accuracy. The implementation demonstrates that the Naïve Bayes algorithm is capable of classifying hypertension risk efficiently while providing probabilistic information regarding age groups with a higher tendency to experience hypertension. The resulting classification model offers an effective decision-support tool for healthcare providers in conducting targeted screening, preventive interventions, and evidence-based health planning. The findings also indicate that data mining techniques can transform routinely collected medical records into valuable clinical knowledge for early hypertension prevention and healthcare decision-making.

Teacher performance evaluation is a crucial factor in improving educational quality, but many schools still conduct it manually and subjectively, resulting in less transparent, time‑consuming, and error‑prone outcomes. This study aims to design and develop a web‑based decision support system using the Simple Additive Weighting (SAW) method for selecting the best teacher at MTs Mambaul Ulum. The system was developed using the Waterfall model with the Laravel 12 framework and MySQL database, incorporating two evaluator roles: the principal (assessing 5 criteria: teaching hours, responsibility, mastery of material, personality, and attendance) and the vice principal (assessing 4 criteria excluding personality). Data were collected through observation, interviews, and document review. System testing employed Black Box Testing and accuracy validation by comparing system outputs with manual Excel calculations. The results show that the SAW method effectively ranks teachers objectively, with Kusyanti achieving the highest score of 0.9450. The system attained 100% accuracy, as no difference was found between manual and system calculations. Moreover, the system reduced evaluation time from days to seconds and provides well‑documented results, thus supporting more transparent and accountable decision‑making. Therefore, this system proves to be reliable, objective, and efficient in assisting school administrators in evaluating teacher performance in a structured and fair manner.

The development of digital services by BPJS Ketenagakerjaan through the JMO (Jamsostek Mobile) application has triggered a surge in large-scale and unstructured user reviews on the Google Play Store, thereby complicating manual analysis and conventional sentiment analysis in accurately identifying specific issues. This research aims to implement the Aspect-Based Sentiment Analysis (ABSA) method to granularly evaluate JMO application reviews based on specific aspects, while simultaneously addressing class imbalance and computational efficiency issues. The proposed method combines the pretrained IndoBERT model as a contextual feature extractor, the SMOTE technique to balance the training data, and an artificial neural network (Neural Network) as the classification layer without performing full fine-tuning. The dataset used consists of 90,268 unique reviews categorized into five main aspects through keyword matching, namely General Satisfaction/Complaints, Performance & Stability, Service & Support, Feature Quality, and UI/UX, with initial lexicon-based labeling using the InSet Lexicon. The research results indicate that the proposed model successfully achieves highly optimal performance with an accuracy rate of 91.81% and a weighted F1-score of 92%. Furthermore, the implementation of SMOTE proved effective in enhancing model reliability on the minority class (negative sentiment), achieving an F1-score of 89%. The implications of this research contribute an accurate and efficient aspect-based sentiment analysis framework for developers, and serve as a strategic evaluation tool for BPJS Ketenagakerjaan in mapping specific user complaints to accelerate continuous improvements in the performance, stability, and service quality of the JMO application.

This study aims to identify the pragmatic failures of Large Language Models (LLMs) and the biases of Anglophone-based AI moderation algorithms in detecting Indonesian hate speech expressed through sarcasm, satire, euphemism, and local cultural metaphors. It also examines the extent to which AI systems understand and interpret the pragmatic meanings within the corpus. This study employs a qualitative descriptive approach with a comparative design. Data were collected through the documentation of hate speech expressions on social media containing elements of local cultural hatred. The data were analyzed using qualitative descriptive methods with pragmatic and thematic approaches. The findings show that all corpus data contain political satire and indirect hate expressed through irony, sarcasm, absurd metaphors, and popular culture wordplay. Testing with Claude AI showed that the system was capable of identifying the data as implicit criticism and recognizing the pragmatic functions of emoticons and contextual meanings in the utterances. However, the analysis also demonstrated limitations in understanding local sociocultural contexts, particularly the metaphors “daun nangka” and “daun sawit,” which were interpreted merely as absurd humor. These findings indicate that AI detection accuracy does not necessarily reflect a deep pragmatic and cultural understanding within the Indonesian context.

Stunting is a multifactorial public health problem influenced by various risk factors that may emerge during the prenatal period. Early identification of stunting risk during pregnancy is important to support preventive interventions. This study aimed to develop a stunting risk prediction model based on maternal prenatal factors using the Random Forest algorithm. Secondary data from 172 pregnant women, consisting of 83 stunting cases and 89 non-stunting cases, were analyzed. The predictor variables included maternal age during pregnancy, height, hemoglobin level, mid-upper arm circumference (MUAC), smoking history, hypertension, asthma, and diabetes mellitus. The research stages consisted of data preprocessing, model training using Stratified 5-Fold Cross Validation, performance evaluation, external testing, and feature importance analysis. Internal evaluation results showed an accuracy of 60%, precision of 60.6%, recall of 57.3%, F1-score of 58.9%, and AUC of 0.6688. External testing yielded an accuracy of 70% and an AUC of 0.6167. Feature importance analysis identified maternal age during pregnancy as the most influential variable in the prediction process. The findings indicate that maternal prenatal factors have potential for early stunting risk identification, although the predictive performance remains moderate. This approach may serve as a foundation for developing early screening tools to support targeted interventions among high-risk pregnancies.

This study examines human resource competence in improving financial management at the Public Service Agency of Gorontalo State University, a public higher education institution that operates under a flexible financial management model while remaining accountable for public funds. The main problem addressed is how financial management personnel translate regulatory knowledge, technical skills, and professional attitudes into efficient, effective, and accountable financial governance. This study aims to analyze the competence of financial management personnel and explain its contribution to strengthening institutional financial management. A qualitative descriptive approach was employed through interviews, observation, and document analysis involving bureau leaders, financial work team officials, treasurers, and financial managers across relevant work units. The findings show that knowledge competence is reflected in personnel understanding of regulations, policies, financial systems, budgeting procedures, reporting requirements, and the linkage between budget and institutional performance. Skills competence is demonstrated through financial administration, transaction recording, document verification, use of financial information systems, reconciliation, reporting, and preparation of accountability documents. Attitudinal competence appears in professionalism, compliance, integrity, prudence, responsibility, and openness to evaluation and audit. Financial management has been directed toward performance-based planning, expenditure control, budget realization monitoring, reporting, supervision, and audit follow-up. However, challenges remain in regulatory adaptation, system integration, data quality, document timeliness, account-code accuracy, inter-unit coordination, and consistency of audit follow-up. The study concludes that strengthening human resource competence is essential for improving financial management that is efficient, effective, accountable, and performance-oriented in public university financial governance.

Batik motif classification has attracted growing attention in visual computing due to its role in cultural heritage preservation, textile informatics, museum documentation, and automated cataloging. Although many studies report high classification accuracy, robustness under real-world acquisition conditions remains insufficiently understood. Batik images are frequently affected by illumination variation, blur, folds, watermark overlays, wearable deformation, scale inconsistency, and background clutter, creating challenges that extend beyond conventional image-noise assumptions. Existing studies largely focus on improving classification performance, while the interactions among acquisition variability, feature representation, evaluation practice, and deployment constraints remain fragmented. This systematic literature review addresses this gap by synthesizing batik classification research through a robustness-aware perspective. Using query expansion, backward and forward citation chaining, relevance screening, and thematic coding, 116 candidate records were identified, resulting in 50 highly relevant studies for detailed analysis. The review reveals that robustness is shaped less by denoising alone than by the combined effects of acquisition conditions, representation design, evaluation realism, and deployment context. Handcrafted descriptors remain competitive for small datasets and structured motifs due to their data efficiency and interpretability, whereas deep learning models achieve the highest reported accuracy when supported by sufficient data diversity and realistic augmentation. Hybrid representations emerge as the most consistently balanced approach, combining local texture stability with higher-level abstraction across heterogeneous acquisition settings. The review further identifies recurring robustness failure patterns, including background dependency, illumination instability, motif-scale inconsistency, wearable deformation, and source-shift vulnerability. Based on these findings, a robustness-oriented research agenda is proposed, emphasizing cross-acquisition evaluation, representation-stability analysis, batik-specific robustness benchmarks, acquisition-aware augmentation, and deployable lightweight or hybrid architectures. The study contributes a domain-specific synthesis that reframes batik motif classification from an accuracy-centric task toward a robustness-aware visual recognition problem.

The Free Nutritional Meal Program (MBG) is a government policy that is widely discussed by the public through social media, especially TikTok. Various comments that have emerged indicate differences in public opinion towards the program, so an analysis is needed to determine the tendency of public sentiment. This study aims to analyze TikTok user sentiment towards the Free Nutritional Meal Program using the Naive Bayes method. The research method is carried out through several steps, namely collecting TikTok comment data, preprocessing text, labeling sentiment data into positive, negative, and neutral, feature transformation using TF-IDF, and classification using the Naive Bayes algorithm. Based on the analysis of 500 comment data, the results show that positive sentiment dominates public opinion by 42% (210 data), followed by negative sentiment by 36% (180 data), and neutral sentiment by 22% (110 data). Testing the classification model using Naive Bayes produces excellent performance with an accuracy rate of 86%, precision of 84%, recall of 85%, and F1-score of 84%. The conclusion of this study shows that the Naive Bayes method is effective as an approach in social media sentiment analysis to map public responses to government policies.

This study investigates the implementation of the Gradient Boosting Machine (GBM) algorithm for network intrusion detection using the CICIDS2017 dataset within the CRISP-DM framework. The process encompasses Business Understanding, Data Understanding, and Data Preparation including data cleaning, categorical feature encoding, normalization, and data split (80 % training, 20 % testing). In the Modeling phase, GBM Hyperparameters (learning_rate = 0.1; max_depth = 5; n_estimators = 150) were optimized via Grid Search with 2-fold Cross Validation, and F1-Score  was selected as the primary metric due to class imbalance. Evaluation on the test set yielded accuracy of 99.99 %, precision of 100 %, Recall of 99.98 %, and F1-Score  of 99.99 %, demonstrating exceptional detection capability with minimal false negatives and false positives. Compared to previous studies, this GBM model outperforms in accuracy and stability without overfitting. These findings confirm GBM’s effectiveness for modern Intrusion Detection Systems and its suitability for Deployment in resource-constrained operational environments.