JSAI (Journal Scientific and Applied Informatics)

Detection System Indonesian Sign Language (BISINDO) in Video with YOLOv7

Nurul Renaningtias — 2025-01-01

Sign language is a method of communication that does not use sound but uses physical movements such as hands, body, and lips. One of the sign languages that many deaf people use to communicate is Indonesian Sign Language (BISINDO). This study aims to implement an object detection and image classification model for BISINDO alphabet gestures using the You Only Look Once (YOLO) version 7 algorithm. This research uses video image data consisting of 26 alphabet letters. In this study, three experiments were conducted with different parameter values. Evaluation was carried out using the metrics of mean Average Precision (mAP), precision, recall, and F1-Score. Based on the experiments conducted, the best accuracy was obtained in experiment 1 with parameter values of epoch = 100, batch size = 64, learning rate = 0.001, weight decay = 0.0001, and momentum = 0.9, resulting in mAP@IoU 0.5 value of 0.995, recall 1.00, precision 1.00, F1-Score 1.00. However, it was found that in the application of the model to real-time scenarios, the detection results were not as good as the results obtained during the training process.

MQTT Rancang bangun Server Message Queuing Telemetry Transport ( MQTT) Internet of Things ( IoT) Berbasis Eclipse

irwansyah irwansyah — 2025-01-01

The design of a Message Queuing Telemetry Transport (MQTT) server for the Internet of Things (IoT) utilizes Eclipse Mosquitto as the core server software. The process begins with installation and basic configuration, including port setup, authentication, and encryption to ensure secure communication. Further customization is implemented to meet specific project requirements, such as configuring connection protocols, access permissions, quality of service (QoS) levels, and message retention policies.

Integration with other Eclipse platforms, such as Eclipse Paho, supports the development of MQTT clients for IoT devices, enabling bidirectional communication between the server and devices. Additional tools like Eclipse Vert.x or Eclipse Hono may also be utilized to enhance device management and enable more complex message processing.

Testing results indicate that the MQTT server implemented on a Raspberry Pi 3 B+ successfully received and transmitted data. The ESP32 device also achieved successful data communication via the MQTT server. The system can be accessed across different networks, offering flexible communication without reliance on the same local network. This implementation demonstrates the reliability of MQTT as a robust solution for IoT communication.

Exploration of Sentiment Prediction Models For Social Media Posts

Fitri Purwaningtias — 2025-01-01

Sentiment analysis is a text analysis technique that can be used to understand the opinion, feeling, or sentiment of a text. This research aims to explore and compare sentiment prediction models on social media data with three algorithms, namely GaussianNB, Logistic Regression, and Support Vector Machine (SVM). The dataset used is taken from www.kaggle.com, which consists of social media posts from the Twitter, Facebook, and Instagram platforms with positive, negative, and neutral sentiment categories. The analysis process involves text data preprocessing, data labeling, feature extraction with Bag of Words (BoW) and TF-IDF, and handling data imbalance with SMOTE. The results showed that the SVM model with TF-IDF and SMOTE performed best, with 93.25% accuracy on training data and 92.50% on test data. This research contributes to determining the best model for sentiment analysis of social media data and can be a reference in developing better sentiment prediction systems in the future.

Predicting the Sustainability of Small and Medium Enterprises (SMEs) Using Machine Learning Algorithms

Terttiaavini Terttiaavini — 2025-01-01

Small and Medium Enterprises (SMEs) contribute approximately 60% to Indonesia's Gross Domestic Product (GDP) and absorb more than 97% of the workforce. However, SMEs face various challenges that hinder sustainability, such as limited capital and market instability. This study aims to develop a predictive model to map the sustainability of SMEs based on variables that influence business continuity. The methods used include clustering with Agglomerative Clustering, K-Means, and DBSCAN, as well as classification using algorithms such as Logistic Regression, Random Forest, and XGBoost.

The results show that the Agglomerative Clustering method provides the best performance with a Silhouette Score of 0.68. All classification models initially achieved an accuracy of 1.0 with a standard deviation of 0.0, but indicated overfitting due to class imbalance between the "Continues" and "Does Not Continue" categories, where the minority class consists of only 16 data points. To address this issue, the application of the SMOTE (Synthetic Minority Over-sampling Technique) method and 5-Fold Cross-Validation was implemented. The results showed an improvement in the model's ability to recognize patterns in the minority class, making the model's accuracy more representative of both classes. This research is expected to provide valuable insights for the Office of Cooperatives and SMEs in Palembang to support the sustainability of the SME sector in Palembang.

Outsourcing Strategy and Planning in Information System Development by Utilizing CMMI-ACQ

Riny Nurhajati — 2025-01-01

Finance companies often face challenges in managing information system development projects through outsourcing. There is a need to improve efficiency and alignment between IT and business in the Project Planning (PP) process. By adopting the McFarlan Strategic Grid and CMMI-ACQ, mapping the current information system and development plan based on four quadrants, measuring the maturity level of the project planning process, and identifying areas that need improvement. Based on the results of the maturity level measurement in the Project Monitoring and Control area, it shows that Specific Goals (SG) have low achievements, with SG 1 (27%) and SG 2 (39%) showing great room for improvement in monitoring and corrective action management. At the Specific Practices (SP) level, practices that have been quite good are project planning monitoring (SP 1.1, 60%) and problem analysis (SP 2.1, 50%). Still, many areas need improvement, such as risk monitoring (SP 1.3, 7%), data management (SP 1.4, 20%), and stakeholder involvement (SP 1.5, 20%). These findings highlight the importance of formulating project risk management, improving project management capabilities, and strengthening collaboration between teams to achieve the success of information system development projects. By implementing the proposed approach, companies can develop more efficient PP process standards, ensure IT alignment, and optimize resource and cost allocation.

Implementation of the K-Nearest Neighbors Algorithm for Spam Email Classification

Diani Putri Kusumaningrum — 2025-01-01

In modern life, internet access has become essential for communication. Email is one of many communication tools. Cyberattacks such as ransomware, phishing, and cryptojacking continue to evolve and are difficult to detect by security systems as technology rapidly advances. Therefore, this study uses email spam as the subject of research. The aim of this study is to implement and calculate the accuracy of the K-Nearest Neighbors (KNN) algorithm in classifying spam emails with ham and spam labels. An accuracy of 85%, precision of 87%, recall of 93%, and F1-score of 90% were obtained from tests conducted with an 80% training data and 20% testing data ratio. The results show that the K-Nearest Neighbors algorithm can effectively classify spam emails.

E-Commerce Marketing Strategy Optimization Through Machine Learning-Based Conversion Prediction

Agustina Heryati — 2025-01-01

The research identifies the problem of enhancing e-commerce sales conversion through TikTok amidst intense content competition. The objective of the study is to develop a machine learning-based marketing strategy to analyze user behavior and categorize them into Non-Purchasers and Purchasers.The method employed includes clustering using K-Means, K-Medoids, and Fuzzy C-Means algorithms, with K-Means demonstrating the best performance, achieving the highest Silhouette Coefficient (0.1857) and the lowest Davies-Bouldin Index (1.9991). Following clustering, classification is performed using Naïve Bayes, Decision Tree, and Random Forest algorithms. The Random Forest model yields the best results with an accuracy of 0.9945, showcasing its effectiveness in predicting sales conversions.The conclusion of this study indicates that K-Means and Random Forest are the optimal methods for clustering and classification, respectively, in understanding user behavior on TikTok. These findings can assist e-commerce players in tailoring their marketing strategies, improving sales conversion rates, and enhancing advertising efficiency

Implementation of Data Warehouse and Business Intelligence for AIDS Cases in West Java

Cahyono Budy Santoso — 2025-01-01

This study discusses the design of a data warehouse for analyzing AIDS cases in West Java using the Nine Step Methodology. The background of this research is the high prevalence of AIDS cases in West Java during 2018–2019 and the need for an integrated data management system to support data-driven health policies. The objective of this study is to design and implement a data warehouse capable of integrating data from various dimensions, such as region, age group, gender, and year, to support epidemiological analysis of AIDS. The methodology employed includes stages such as data extraction from various sources, data transformation to enhance quality, and data loading into a PostgreSQL-based data warehouse system. The study also utilizes the ETL (Extract, Transform, Load) process to ensure the integrity of the processed data. The results indicate that the designed data warehouse successfully maps the distribution of AIDS cases based on relevant dimensions. Key findings reveal that the productive age group (25–49 years) and males have the highest number of cases, with Bandung City being the region with the most cases. The contribution of this study is the provision of a data platform that supports evidence-based decision-making while identifying high-risk regions and groups for more effective health interventions. Limitations include the scope of data limited to two years and the absence of predictive analytics features. Future research is recommended to expand the time coverage and integrate predictive analysis to enhance the effectiveness of health policy

Data-Driven Approach for the Development of a Poverty Rate Prediction Model in Indonesian Provinces

Evi Purnamasari — 2025-01-06

Poverty in Indonesia remains a major issue that requires serious attention, particularly at the provincial level. Various factors, such as access to education, healthcare, and employment opportunities, affect the poverty rate. This study aims to develop a poverty prediction model using a data-driven approach through cluster analysis and classification. The methods used in clustering are K-Means, Hierarchical Clustering, and DBSCAN, while for classification, the algorithms applied are Random Forest, Naive Bayes, and Support Vector Machine (SVM). The clustering analysis results show that K-Means provides clearer cluster divisions with the highest Calinski-Harabasz Index value (179.45). In classification model testing, Naive Bayes provides the best results with an accuracy of 99.42%, which is higher than the other models. To address overfitting, cross-validation testing was conducted, yielding a Mean Accuracy of 99.32% and a Standard Deviatin of 0.23%. This study successfully identifies the factors influencing poverty levels in Indonesia’s provinces, which can be used as a basis for government policies in poverty alleviation efforts. The results achieved contribute significantly to the development of a more accurate and effective predictive model for addressing poverty issues in Indonesia.

Sentiment Analysis of UMSIDA Student Trust Services Using the Support Vector Machine (SVM) Method

Angga Wibawa Saputra Angga — 2025-01-13

The myUMSIDA application supports academic activities at Universitas Muhammadiyah Sidoarjo, but student reviews reveal complaints about its services and facilities. Sentiment analysis is necessary to classify these reviews into positive or negative categories, providing insights to improve service quality.This study uses the Support Vector Machine (SVM) algorithm with a linear kernel, known for its high accuracy, combined with the TF-IDF feature extraction method to enhance text classification. A total of 1,300 reviews from 2023 were processed through labeling, preprocessing, transformation, and classification. Data were split into three scenarios: 70:30, 60:40, and 50:50 for training and testing. Performance was evaluated using accuracy, precision, recall, and F1-Score.The best results were achieved in the 70:30 scenario, with an accuracy of 86.92%, precision of 86.60%, recall of 84.72%, and F1-Score of 85.7%. This study highlights the effectiveness of SVM with a linear kernel and TF-IDF in analyzing sentiment, offering a basis for enhancing the myUMSIDA application's services.

Evaluation of Information Technology Governance of Service Applications at PT.PQR with Cobit 4.1

Wishnu Aribowo Probonegoro — 2025-01-13

PT PQR is a company engaged in the application of shipping services. It is important for PT PQR to manage and utilize information technology well, but there has never been an assessment of the management system and its application. The author conducted research to assess the management of information technology using the COBIT 4.1 standard, which has 34 processes. This research was conducted through observations, interviews, and measurement of maturity levels, with the aim that PT PQR knows the information technology governance that is carried out, and knows the gaps that exist so that they can be resolved immediately to improve services and compete with other companies. The results showed that the current maturity level at PT PQR is close to level 3, with 14 Information Technology processes in two domains, namely Delivery Support and Monitoring Evaluate. PT PQR has clear and written standard procedures regarding the procedures and management of information technology, which are socialized among management and employees. Overall, the maturity level evaluation shows that PT PQR has fairly good IT governance, with an average achievement close to the expected target. The DS domain has an almost optimal performance with an achievement of 99%, while the ME domain requires more attention to increase the achievement from 90% to 100%. Improvement efforts can be focused on areas that require improvement based on the findings of this analysis.

Time Series Analysis for Forecasting Livestock Population in Indonesia with LSTM Model

Tito Prabowo — 2025-01-13

Livestock population in Indonesia is one of the key indicators supporting national food security, particularly in meeting the demand for animal-based protein. However, the suboptimal utilization of livestock population data for strategic planning remains a challenge in the livestock sector. This study aims to predict livestock population in Indonesia using the Long Short-Term Memory (LSTM) method, a variant of Recurrent Neural Network (RNN) designed for time series data analysis. The livestock population data used in this research was obtained from the Central Statistics Agency (BPS) for the period of 2006 to 2022. The LSTM model was trained using 80% of the data for training and 20% for testing, with evaluation conducted using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results indicate that the LSTM model can forecast the national livestock population up to 2033 with good accuracy, particularly for livestock such as goats (MAPE 5.47%) and beef cattle (MAPE 5.64%). However, a higher error rate was observed for buffalo (MAPE 16.57%). The predictions indicate a significant growth trend in poultry populations, such as broiler chickens and laying hens. In conclusion, this model can support data-driven decision-making to ensure stable and sustainable animal protein availability, thereby strengthening national food security.

Sales Trend Analysis and Product Prediction of CV. Sentosa Using Linear Regression

Dona Marcelina — 2025-01-13

This study analyzed sales trends and forecasted the sales of CV Sentosa's products, namely Ater 360 New (X1), Bon Bon (X2), Mini Peanut Crackers (X3), and Marie Susu Int (X4), during the period of January 2019 to August 2023. Monthly sales data were processed using exploratory data analysis (EDA) and linear regression to predict sales trends. The linear regression analysis results indicated that X2 and X3 experienced sales growth with a slope of m=0.01, representing an average increase of 0.01 units per month. Conversely, X4 showed a slight decline with m=−0.01, while X1 remained stable with m=−0.00, indicating minimal changes in sales volume.

The accuracy evaluation of the predictions based on MAE, MSE, and RMSE showed that X2 had the best performance with MAE 0.14, MSE 0.03, and RMSE 0.19, followed by X1 and X3, which had similar prediction errors. Although X4 initially showed significant growth, its model exhibited higher prediction errors (MAE 0.17, MSE 0.04, RMSE 0.21). This study provides valuable insights for CV Sentosa's business strategies, highlighting X2 and X3 as promising products due to their consistent growth trends and accurate predictions. This research provides a strong foundation for CV Sentosa in formulating more effective marketing strategies and product development in the future

Expectation Precision of Telemarketing on The Bank Portugal: Utilizing Data Mining

irfan abbas — 2025-01-13

Banks play a basic role in economic improvement as well as contribute various cash related organizations to clients. Telemarketing is a commonly applied exchange method inside banks to offer and develop unused organizations to their clients. This kind of campaign generates a vast collection of data, A suitable examination of this data can support banks in organizing future strategies. Furthermore, it considera proposed data mining approach, to analyze and predict using atelemarketing campaign dataset. This dataset is composed based on demonstration pieces collected from clients, amid live call sessions organized by the bank. To execute the proposed view. The results show that the calculated backslide gives the best precision among the three models, recorded at 91.48%.

Application of the Rule Base System Method to Determine the Type of Disease Based on Symptoms in Pig Farms Based on a Website

Antonius Lake — 2025-01-13

The rule base system method was used in this research because disease diagnosis in pigs requires a structured approach, where symptoms can be linked to specific rules to produce accurate decisions. The development of this system is in the form of a website that can easily access information and diagnosis anytime and anywhere. This system can help early detection of disease in pigs, reduce the risk of spread, and increase the effectiveness of pig health management in the North Central Timor district. The method used in developing this expert system is a waterfall or what is often called a waterfall which is a classic life cycle. The sequence of developing this method starts from analysis, design, coding, testing, and maintenance stages. A website-based expert system is an application designed to help users diagnose problems or provide recommendations based on the knowledge of an expert that has been modeled in a knowledge base. These systems work by collecting data from users, such as specific symptoms or problems, through a web-based interface, then using an inference engine to analyze that data and generate solutions or suggestions. Based on the results of the User Acceptance Test (UAT) with 5 test categories (menu on the website) and 12 test parameters, overall test results were obtained with an average value of 91%.

Information Systems Audit Analysis Using the Committee Of Sponsoring Organizations Of The Treadway Commission (COSO) Framework at PT. Persero Batam

Reza Ardiansyah — 2025-01-18

An information system (IT) audit is one of the important aspects of maintaining the effectiveness and efficiency of company operations. In this study, an information system audit at PT PERSERO was conducted to determine the extent of the company's capability level and provide recommendations to improve the performance of information systems to achieve the company's business objectives. The control standard used in this study is the Committee of Sponsoring Organizations of the Treadway Commission (COSO) which consists of the components of Control Environment, Risk Assessment, Control Activities, Information and Communication, and Monitoring. The purpose of this study is to evaluate whether the system is equipped with controls that are carried out properly and correctly. From the results of the research, data was obtained through interviews, observations, and document studies, which were analyzed using quantitative descriptive methods. The results showed that the average value of each component ranged from 4.46 to 4.74, with the overall assessment percentage reaching 90.8% and a capability level of 4.54. This shows that the internal control system at PT Persero Batam is in the very good category. The best-performing component is Monitoring Activities (4.74), while Control Environment (4.46) is an area of potential improvement. The gap analysis shows a small difference of 0.16, which indicates that internal control has almost reached the ideal level.

The TOGAF ADM Approach in the Development of Enterprise Architecture at SMAN 16 Surabaya

Divani Jane Forinda Putri — 2025-01-20

This research aims to improve operational efficiency and quality of education services at SMAN 16 Surabaya through enterprise architecture design using the TOGAF ADM framework. The school faces challenges in operational management due to the lack of a structured and adequate system to support the digitization process. With a systematic methodological approach, this research includes the stages of literature review, data collection, and architecture development based on organizational needs, which include the preliminary phase, architecture vision, business architecture, information systems architecture, technology architecture, and opportunities & solutions. The results showed that the average implementation achievement reached 90.0%, with the main successes at the visioning, business architecture, and technology solution planning stages. Some of the priority solutions identified include digitizing administrative processes, integrating student data, and managing information technology infrastructure that supports learning. Also, the results of this research will provide a technology and information systems blueprint that summarizes system needs and candidate applications for each business process, providing integrated solutions and supporting the optimization of school operations as a whole.

Analysis Of Digital Literacy Information Systems To Enhance Students' Understanding Of The ITE Law And Religious Norms At Man Kepulauan Selayar

Abdul Ma'arief Al Imran — 2025-01-18

The research focused on MAN Kepulauan Selayar students' level of understanding of the Electronic Information and Transaction Law (UU ITE) and how religious norms influence their attitudes to using digital technology. Selayar Islands, with its distinctive social, cultural, and spiritual characteristics, provides a relevant context for exploring digital literacy in an area with unique educational challenges. Using descriptive methods, a multiple choice test was used to measure students' understanding of the ITE Law. In contrast, a Likert scale questionnaire was used to assess the influence of religious norms on their attitudes. The data obtained were analyzed quantitatively to provide a comprehensive picture of students' digital literacy. The results showed that the average score of students' understanding of the ITE Law was 74, which was classified as a High category. Ranking analysis revealed that class XII students had the highest score of 80.77 (High category), followed by class XI with a score of 74.83 (High category), and class X with a score of 66.4 (Medium category). In addition, the average percentage of students' answers in the questionnaire shows a value of 79.42%, which is classified as Influential in reflecting the influence of religious norms on students' attitudes toward using digital technology. This finding shows that although students' level of understanding of the ITE Law is relatively good, there are differences in the level of understanding between grades. In addition, religious norms have a significant influence on students' attitudes toward the responsible use of digital technology.

RAD Implementation on Halo Gamers Website Development

SOPHYA HADINI MARPAUNG — 2025-01-19

The presence of Key Opinion Leaders (KOL) is increasingly important in the business world, especially in increasing consumer purchasing intentions. KOLs are now widely used in various sectors, including the gaming industry. One of them is the presence of Halo Gamers, a YouTube channel that focuses on gaming product reviews. Since 2017, Halo Gamers has targeted the Indonesian gaming market, driven by government projections to control 50% of the gaming industry market share. With more than 2,700 subscribers and collaboration with 16 brands as of November 2024, Halo Gamers acts as a successful KOL in promoting gaming products. Obstacles arise, especially in managing all content portfolios owned by channel owners and information regarding collaboration with brands that are spread across various platforms without centralized media that makes it difficult for channel owners to collaborate with related parties. To overcome this, the author developed a website with the RAD method (a common and popular method in system development that starts from the requirement planning, user design, construction to implementation stages) which functions as a centralized container for Halo Gamers, allowing brands to access portfolios and published content, as well as expanding opportunities for future collaboration at the address halogamers.info.

Implementation of Retrieval Augmented Generation (RAG) in the Design of Digestive Health Chatbot

Gufranaka Samudra — 2025-01-22

The development of artificial intelligence technology, especially in the development of chatbots, has brought significant progress, especially in the health sector. However, the main challenge in using large language models (LLM) is the potential for bias and lack of accuracy in providing information, especially on critical topics such as digestive health. This study aims to implement Retrieval-Augmented Generation (RAG) in designing a digestive health chatbot to improve the accuracy and relevance of the information delivered. The RAG method integrates a generative model with a document-based retrieval system to provide more reliable and evidence-based answers. The research process involves collecting digestive health datasets through data scraping from Alodokter, as well as data processing through the preprocessing stage, embedding using the Indonesian language model (firqaaa/indo-sentence-bert-base), and data processing using a vector database with the HNSW index. The Llama 3.1:8b model is used to generate generative responses. The results of the study show that the application of RAG can reduce model bias and improve the quality of chatbot responses. Evaluation using metrics such as Mean Reciprocal Rank (MRR) 93%, Faithfullness 62%, Answer Relevancy 57%, and Semantic Similarity 81% showed good performance in providing accurate and relevant answers according to context. With this approach, chatbots are able to provide more accurate and contextual information according to user needs, and can reduce the risk of hallucinations in the information provided. This research contributes to the development of more reliable health chatbot technology, especially in the digestive health domain, and opens up opportunities for further application in other health fields

Implementation of Usability Scale System in Tiktok Usability Evaluation

Silvia — 2025-01-24

The development of information technology has brought significant changes to how humans interact, one of which is through social media. TikTok has become one of the popular social media applications with various attractive features that support users' creativity and self-expression. This study aims to evaluate the usability level of the TikTok application using the System Usability Scale (SUS) method. This method assesses user experience based on 10 statements rated on a Likert scale ranging from "strongly disagree" to "strongly agree." Data were collected through questionnaires distributed in online. The analysis results showed an average SUS score of 73.4, indicating that TikTok has a good and acceptable usability level. This study provides insights into TikTok's strengths and weaknesses in meeting user needs and offers recommendations for further development.

Customer Satisfaction Prediction on E-government Services Using Decision Tree Algorithm

Indah Permatasari — 2025-01-24

The Online Licensing Service Information System (SIPPERI) implemented by DPMPTSP Palembang City aims to enhance efficiency, transparency, and accountability in public services. However, several challenges were reported by users, including unintuitive navigation, slow system responses, and inaccurate information. These challenges impact the level of user satisfaction with the service. This study uses the decision tree algorithm to evaluate user satisfaction based on data obtained through questionnaires with a Likert scale assessment involving 100 respondents. The analysis process uses the Python programming language. The dimensions analyzed include Efficiency (E), Trust (T), Reliability (R), Service (CS), Usability (U), Information Availability (I), and Interaction (SI). The analysis results show that the decision tree algorithm achieves an accuracy rate of 95%. The highest-scoring dimensions were recorded in the indicators Download Speed of Forms (R1: 392) and Accuracy of Instructions (E4: 392). Conversely, the lowest-scoring dimensions were Intuitive Navigation (E1: 300) and Information Availability (I1: 314). This study provides strategic recommendations for DPMPTSP Palembang City to improve dimensions with low scores to enhance user experience and strengthen public trust in e-government services.

Flutter-Based Mobile Application Design for IoT Sensor Data Monitoring: Solutions for Temperature and Humidity Management

Arif Setia Sandi Ariyanto — 2025-01-25

This study developed a mobile application based on Flutter to monitor Internet of Things (IoT) sensor data for real-time measurement of temperature and humidity. The system utilizes a DHT22 sensor connected to an ESP32 microcontroller, transmitting data via the MQTT protocol. The data is stored in a MySQL database hosted on a designated server. The mobile application offers an interactive interface to display real-time data, historical graphs, and automatic notifications when environmental parameters exceed predefined thresholds. Testing was conducted using the User Acceptance Testing (UAT) method involving 20 respondents. The results indicate a high level of application success, with an average user satisfaction rate of 93% for ease of login, 90% for the interface, 90% for data processing speed, and 93% for notification accuracy. By integrating IoT, Flutter, and MySQL technologies, this application provides an efficient digital solution for environmental management, with potential for development across various industrial sectors requiring such capabilities.

Implementation of Agile SCRUM in E-Commerce Design E-Commerce

Paisal — 2025-01-31

E-Commerce is an application that supports buying and selling activities using internet media so that many people can access it. the development of complex e-commerce systems requires an effective project management approach to produce products that meet user needs and are completed optimally. Agile methods, especially SCRUM, are becoming an increasingly popular choice in software development, including for e-commerce projects. The SCRUM method is applied in several sprints, which include planning, development, testing, and evaluation stages. After several sprints were completed, Integration Testing was conducted to evaluate system performance and integration between modules, such as user login, product management, shopping cart, checkout, and payment gateway. Based on the results of Integration Testing, the e-commerce system developed with the SCRUM method shows a success rate of 91%.