cover
Contact Name
Bahtiar Imran
Contact Email
bahtiarimranlombok@gmail.com
Phone
+6285337626083
Journal Mail Official
bahtiarimranlombok@gmail.com
Editorial Address
Perumahan Green Asia Blok I2-04, Kecamatan Labuapi, Kabupaten Lombok Barat Nusa Tenggara Barat, Indonesia
Location
Kab. lombok barat,
Nusa tenggara barat
INDONESIA
Jurnal Kecerdasan Buatan dan Teknologi Informasi
ISSN : 29636191     EISSN : 29642922     DOI : https://doi.org/10.69916
Core Subject : Science,
Jurnal Kecerdasan Buatan dan Teknologi Informasi or abbreviated JKBTI is a national journal published by the Ninety Media Publisher since 2022 with E-ISSN : 2964-2922 and P-ISSN : 2963-6191. JKBTI publishes articles on research results in the field of Artificial Intelligence and Information Technology. JKBTI is committed to becoming the best national journal by publishing quality articles in Indonesian and English and becoming the main reference for researchers. All submissions are blind and reviewed by peer reviewers. All papers can be submitted in BAHASA INDONESIA or ENGLISH. Scope : Neural Networks, Machine Learning, Deep Learning, Data Mining, Big Data, Decision-Making System, Information System, Mobile Application, Data Warehouses, Database, Internet of Thing, Expert System.
Articles 170 Documents
Analysis and Design of a Fitness Equipment Sales Website at MBB Mart Fitness Using User-Centered Design (UCD) Puspa Hapsari; Andi Marwan Elhanafi
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.426

Abstract

Digital commerce requires retail businesses to provide product information and transaction services through accessible, structured channels aligned with customer needs. MBB Mart Fitness, a fitness-equipment retailer in Medan, has utilized social media and third-party marketplaces, but these channels provide limited control over product presentation, transaction management, and customer data. This study aimed to analyze user requirements and design a dedicated web-based fitness-equipment sales system for MBB Mart Fitness using User-Centered Design (UCD). Data were collected through an interview with the business owner and questionnaires involving 20 respondents. The UCD process comprised understanding the context of use, specifying user requirements, producing design solutions, and evaluating the resulting system. The system was implemented using Laravel 12 and MySQL and provides customer functions including product catalogs, keyword search, category and usage-type filtering, product details, shopping cart, checkout, payment information, order confirmation, and rating. Administrator functions include authentication, category management, product management, order monitoring, and order-detail processing. Functional verification used black-box testing across ten principal scenarios. All scenarios produced the expected outputs, resulting in a functional success rate of 100%. The study demonstrates that UCD can be adapted to a specialized fitness-equipment retail context by integrating customer purchasing activities and administrator sales management within an independent digital sales channel. The system remains limited by semi-manual payment verification, automated shipment tracking, and standardized usability evaluation. Future development should address these aspects through payment integration, delivery tracking, security testing, and broader usability evaluation under real conditions.
An Integrated Web-Based Sales Information System for Original Second-Hand Footwear: A Prototype-Based Case Study of PT. Taria_2ndshoes Dinda Puspa Sari; Andi Marwan Elhanafi
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.500

Abstract

The sale of original second-hand footwear requires transparent and well-organized product information because each item may differ in physical condition, size, appearance, availability, and level of wear. At PT. Taria_2ndshoes, product promotion and customer communication were previously conducted primarily through social media and private messages, resulting in product, stock, payment, transaction, and reporting information being distributed across separate channels. This study aimed to design and implement a web-based shoe sales information system using the Prototype method and to evaluate its principal functions through black-box testing. The development process comprised requirements identification, rapid design, prototype construction, evaluation, system development, and functional testing. The implemented application integrates customer and administrator workflows, including product catalog access, search and category filtering, registration, authentication, shopping cart, checkout, payment-proof submission, product management, transaction management, user management, and sales reporting. The system was developed using PHP, CodeIgniter 3, MySQL, HTML, CSS, Bootstrap, and XAMPP. Functional testing consisted of 25 predefined scenarios, including 15 valid-input and 10 invalid-input scenarios. All 25 scenarios produced the expected responses, resulting in a functional test pass rate of 100%. The findings demonstrate that the proposed system provides an integrated workflow connecting item-level footwear information, customer product discovery, purchasing activities, transaction administration, and period-based sales reporting. The contribution is contextual and functional, specifically addressing the information-management requirements of original second-hand footwear sales. The evaluation was limited to functional testing; usability, performance, security, scalability, and concurrent-access behavior require further quantitative investigation in future studies.
K-Nearest Neighbors Classification Analysis of Rice Farmer Productivity Using Harvest Data for Agricultural Evaluation in Sayur Matinggi District Ahmad Fauzan Purba; Mulkan Azhari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.512

Abstract

Rice productivity evaluation in Sayur Matinggi District has traditionally relied on descriptive comparisons of harvest records, which do not provide a consistent classification of productivity levels across villages. This study develops a web-based analytical system using the K-Nearest Neighbors (KNN) algorithm to classify rice farmer productivity from harvest data collected in 19 villages during 2023-2025. The original wide-format dataset was transformed into 57 village-year observations. Productivity labels were constructed objectively using the 33rd and 66th quantiles of the production-to-harvested-area ratio, producing Low, Medium, and High classes. A stratified random split allocated 45 observations to training data and 12 observations to testing data. Three numerical attributes were used in the final model: harvested area, rice production, and cropping index. Min-Max normalization was applied before Euclidean-distance computation and majority voting. Evaluation of K values from 1 to 10 showed the highest accuracy at K=4 and K=5, both reaching 41.67%; K=4 was selected as the simpler model. At K=4, five of twelve testing observations were classified correctly. The confusion matrix showed a tendency to over-predict the Medium class, while macro-average precision, recall, and F1-score were 44.44%, 38.33%, and 34.43%, respectively. Functional black-box testing across twelve scenarios produced results consistent with the expected outputs. The findings indicate that the KNN workflow was implemented correctly, while the limited predictive accuracy is primarily associated with small sample size and weak class separability in the available harvest attributes.
Digital Customer Journey Mapping for Business Scale-Up and Loyalty Optimization: A Case Study of Aroma Coffee Bland Winda Azhara; Septiana Dewi Andriana
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.519

Abstract

Digital transformation requires micro, small, and medium enterprises to manage customer experience as a structured source of business insight rather than relying solely on informal observation. Aroma Coffee Bland, a beverage MSME that has operated for approximately six years, had not yet implemented an integrated mechanism for recording customer interactions, transaction histories, feedback, and the stages of the customer journey. This study designed and implemented a Laravel-based Customer Journey Mapping prototype to support customer-loyalty optimization and the scale-up process of Aroma Coffee Bland. Data were collected through interviews, direct observation, and literature study. System development followed the Prototype method through requirements collection, prototype construction, user evaluation, and iterative refinement. The application was implemented using Laravel 13, MySQL, Laragon, Visual Studio Code, Figma, and Draw.io. The resulting system supports Admin and Operator roles and provides customer, product, transaction, feedback, customer-journey, segmentation, and reporting functions. Customer interactions are visualized across six stages: Awareness, Consideration, Purchase, Experience, Retention, and Loyalty, while customer segmentation is grouped into New, Active, Potentially Loyal, Loyal, and Inactive categories. Black-box testing covered 13 principal scenarios, and all scenarios produced the expected outputs. The prototype provides a structured basis for monitoring customer interactions and supporting data-informed service improvement at Aroma Coffee Bland.
Fashion Product Sales Prediction Using Random Forest Regression Algorithm Based on Historical Data Lusiana Situmorang; Mukhlis; Muhammad Yasir
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.583

Abstract

Tulip Store at Metropolitan Mall Bekasi, managed by PT Star Asia Brothers,relies on historical sales data for evaluation and target planning. However,sales volume fluctuations, ranging from 385 units in October 2025 to1,122 units in March 2026, make heuristic planning unreliable. This studybuilds a daily sales volume prediction model using Random Forest Regressionbased on daily recapitulation data from October 2025 to March 2026. Followingthe CRISP-DM framework, data preparation involved cleaning, dailyaggregation, and feature engineering to construct 11 input features categorizedinto temporal indicators, historical lag variables, and rolling statistics.The model was trained using an 80:20 train-test split with hyperparametersn_estimators = 200, max_depth = None, and random_state = 42. Evaluationon 36 test instances yielded a Mean Absolute Error (MAE) of 1.7649and a Root Mean Square Error (RMSE) of 2.9740, with 91.67% of predictionsexhibiting errors within ±5 units. Feature importance analysis revealed thatsequential month (Bulan_ke, 0.385) and previous-day sales (Lag_1, 0.294)were the most influential variables, indicating that monthly seasonal trendsand immediate sales momentum drive daily demand. The proposed modelprovides robust operational decision support for daily sales evaluation, targetsetting, and stock allocation.
CashFlowMate: A Cross-Platform Mobile Application for Personal Financial Management Hasnawati; Nurhalisa; Untung Suwardoyo; Ade Hastuty; Muhammad Basri
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.587

Abstract

Personal financial recording remains a challenge for most people because it is generally done manually or solely relying on memory. This condition causes transaction data to be easily lost, is difficult to monitor, and makes it difficult for users to accurately determine income and expenditure flows. This study aims to design and build a Flutter-based personal financial recording mobile application that can record income and expenses, manage transaction categories, display financial reports in graphical form, and provide monthly installment reminders through a local notification feature. The research method used is software engineering with a Waterfall development model that includes requirements analysis, system design, implementation, testing, and maintenance. Data collection techniques were carried out through literature studies and observations of the running system, as well as system testing using black box testing and white box testing. The results of the study indicate that the application was successfully developed and all main features can function properly according to the system design, including the transaction recording process, financial report visualization, transaction history, and automatic installment reminders.
Customer Service Time Prediction Using Gradient Boosting Regressor for Sequential Queuing Systems Amelia Sari Dewi; Eva Rahmawati; Sri Diantika
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.590

Abstract

Service quality in financial service companies depends on the ability to provide efficient and timely customer services. PT FIFGROUP Cikampek Branch utilizes the Integrated Self-Service Smart Queue Information System (ISSSIAP), which implements a sequential queueing system where customers may pass through different service stages with varying processing durations. This complexity makes customer service time prediction challenging and may affect resource allocation and queue management. This study aims to develop a customer service time prediction model using the Gradient Boosting Regressor algorithm based on historical ISS-SIAP data. A quantitative approach was applied through data collection, preprocessing, 10-Fold Cross Validation, model development, and performance evaluation using R 2 , MAE, MSE, and RMSE metrics. The experimental results show that the proposed model achieved an R 2 value of 0.866, MAE of 2.726 minutes, MSE of 15.308, and RMSE of 3.903 minutes. These results demonstrate that the Gradient Boosting Regressor provides good predictive performance in estimating customer service time. The proposed model provides practical support for improving operational efficiency at PT FIFGROUP Cikampek by enabling better service planning, resource allocation, and queue management decisions.
Sentiment Analysis of the Joko Widodo Diploma Controversy Using NLP and Multi-Layer Perceptron Herdiansyah Herdiansyah; Nazori Suhandi; Dwi Asa Verano
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.591

Abstract

The polemic regarding the authenticity of President Joko Widodo’s diploma has become a public issue widely discussed on social media, particularly on the YouTube platform. YouTube comment sections contain various public opinions that are unstructured and written in informal language, making manual analysis difficult. Therefore, this study aims to analyze public sentiment toward the polemic of Joko Widodo’s diploma using a Natural Language Processing (NLP) approach with the Multi Layer Perceptron (MLP) algorithm. The research data were obtained from YouTube user comments related to the issue. The data were processed through text preprocessing stages, including cleaning, case folding, tokenization, stopword removal, and stemming. Furthermore, the text data were transformed into numerical representations using the Term Frequency–Inverse Document Frequency (TF-IDF) method. Sentiment classification was performed using the Multi Layer Perceptron algorithm into three sentiment classes, namely positive, negative, and neutral. Model performance evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that the Multi Layer Perceptron algorithm is able to classify public sentiment with a good level of accuracy and effectively learn non-linear patterns in textual data. This study is expected to serve as a reference for the development of Indonesianlanguage sentiment analysis based on machine learning.
Implementation Rule-Based System and Hamilton Method Based on Legal Provisions Governing Labor Union Representation Zidane Fauzannajah; Anita Ratnasari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.592

Abstract

Determining the representation of workers’ organizations in national tripartite bodies requires a fair and transparent calculation mechanism. Conventional data management has proven to be highly susceptible to duplicate worker identities and involves extremely time-consuming bureaucratic processes. This study aims to design and develop a web-based trade union membership tallying system using the Laravel framework. This system integrates a Rule-Based System algorithm to assess administrative eligibility in accordance with Ministry of Manpower and Transmigration Regulation No. KEP-201/MEN/2001 and the Hamilton Method algorithm to calculate proportional seat allocation. The methodology applied is software engineering through the Agile development model, which involves black-box testing and load testing on massive-scale population data. Test results demonstrate that the system is capable of executing multi-level validation and distributing remaining fractional seats without human subjectivity. The implementation of a security architecture using role-based access control successfully isolates the permissions of six user levels to prevent attempts to manipulate reporting data. The conclusion of this study confirms that automating the tabulation of the labor force using a combination of absolute rule logic and the largest remainder method can significantly improve accuracy, transparency, and fairness in industrial relations.
Random Forest-Based Performance Prediction for Teachers and Staff at Yayasan Al Istiqomah Al-Islamiyah Prabumulih Hilmy Putra Dwi Anwarsyah; Rendra Gustriansyah; Evi Purnamasari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.593

Abstract

Teacher and staff performance evaluation is important for supporting managerial decision-making and maintaining the quality of educational services in educational institutions. However, the manual evaluation process at the Al-Istiqomah Al-Islamiyah Foundation in Prabumulih is time-consuming and less effective in supporting decisions regarding the appointment of Permanent Foundation Teachers (GTY) and Permanent Foundation Employees (PTY). This study aims to develop and evaluate a Random Forest-based model for predicting teacher and staff performance. The study used a quantitative approach based on 100 historical performance evaluation records collected from January 2022 to January 2024, with ten assessment variables. The research stages included data preprocessing, training-testing data splitting using five ratios (50:50, 60:40, 70:30, 80:20, and 90:10), Random Forest modeling, and evaluation using accuracy, precision, recall, F1-score, confusion matrix, feature importance, ROC-AUC, and k-fold cross-validation. The 70:30 split produced 96% training accuracy and 97% testing accuracy. The testing confusion matrix correctly classified 24 of 25 GTY/PTY-appointed cases and all 5 not-appointed cases. The model also achieved an AUC of 0.992, indicating strong classification capability. These results show that the Random Forest model can provide a systematic, consistent, and objective approach to supporting teacher and staff performance evaluation and appointment decisions