Journal of Informatics Management and Information Technology

Sistem Pendukung Keputusan untuk Penentuan Investasi Cryptocurrency Menggunakan Metode Weighted Product

Aldi Dwi Saputra — 2025-07-11

The rapid growth of cryptocurrencies with diverse characteristics poses challenges for investors, especially beginners, in selecting optimal investment options. This study seeks to construct and develop a decision support system (DSS) utilizing the Weighted Product (WP) technique to deliver objective recommendations for cryptocurrency investments. The evaluation criteria were determined through questionnaires distributed to investors, identifying five main criteria: asset liquidity, daily transaction volume, market capitalization, price volatility, and current cryptocurrency price. The system was developed using PHP, CSS, and JavaScript with Visual Studio Code as the development environment. The calculation results indicate that Bitcoin ranks first with a score of 0.058263, followed by Ethereum (0.05240), and Solana (0.044023). The developed system effectively generates cryptocurrency asset rankings by considering weights and values for each criterion, assisting users in making more accurate and optimal investment decisions.

Implementasi K-Means Untuk Pengelompokan Kategori Penjualan Barang Berbasis Web

Shania Risky Agustin — 2025-07-11

Harto Joyo Store faces challenges in inventory management due to manual recording processes. The main issue in managing sales data lies in the difficulty of grouping products based on sales patterns to support marketing strategies. This research aims to design and develop a web-based system capable of clustering products using the K-Means Clustering algorithm. The system was developed using the System Development Life Cycle (SDLC) with the Waterfall model, utilizing a dataset of 1,630 sales records from February 2023 to January 2024. The data was processed through the Knowledge Discovery in Databases (KDD) stages, which include Data Selection, Data Preprocessing, Data Transformation, Data Mining, and Knowledge Interpretation/Evaluation. The clustering process resulted in three data groups (Cluster 1 with 9 records, Cluster 2 with 191 records, and Cluster 3 with 28 records), with the number of clusters determined using the Elbow method. Cluster 1 represents best-selling products that require a high stock level, Cluster 2 includes low-demand products with minimal stock needs, and Cluster 3 consists of moderately-selling products that require a balanced inventory level. Evaluation using the Davies-Bouldin Index (DBI) yielded a DBI score of 0.356 for K=3, indicating optimal clustering results as it approaches zero. Initial testing shows that the system accurately classifies products into several sales clusters and can be used as a basis for business decision-making. This research contributes by providing a sales analysis system that can be integrated with the company’s information system. The analysis reveals that low-selling products dominate the data, suggesting that Harto Joyo Store should implement marketing strategies such as discounts or promotions to boost sales.

Transformasi Digital Desa melalui Aplikasi Web Terpadu: Integrasi E-commerce dan Sistem Manajemen Inventaris

Rahma Assabilla — 2025-07-11

Sukamukti Village, located in Tanjungmedar District, Sumedang Regency, is grappling with a severe digital divide that necessitates immediate attention. Consequently, the village faces significant challenges posed by limited technological infrastructure and inadequate community knowledge regarding internet utilization, largely attributed to low digital literacy rates. This predicament threatens to impede various aspects of village development, encompassing economic growth, education, and administrative governance. To address this issue, a proposed solution involves leveraging digital transformation to foster MSME development through the integration of e-commerce platforms and web-based applications. These solutions aim to enhance inventory management efficiency, improve public services, and promote transparency. Research findings indicate that community members have demonstrated improved comprehension of digital technology. Implementation of this application has yielded more effective inventory management, mitigating the risk of asset misappropriation and streamlining public administrative services provided by the village government. Furthermore, the development of e-commerce features has empowered local MSME stakeholders to market their products digitally, expand their customer base, and increase revenue.

Penerapan Metode MOORA Untuk Menentukan Shampoo Terbaik Bagi Kulit Berketombe Pada Perempuan

Yumni Syabrina Agustina Lubis — 2025-07-11

Scalp dandruff is a common problem experienced by women and can cause discomfort and lower self-confidence. The large number of shampoo products on the market often makes it difficult for consumers to choose the product that best suits their scalp condition. This study aims to apply the MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis) method to determine the best shampoo for women with dandruff. The problem faced is choosing an effective and safe shampoo for scalp dandruff, by considering various criteria such as price, active ingredients, and effectiveness in treating dandruff. This study uses predetermined criteria and calculates the weight of each criterion based on user preferences. Using the MOORA method, available shampoo alternatives are evaluated and ranked to find the optimal product. The results show that the MOORA method can provide objective and effective results in the decision-making process. With this system, it is hoped that consumers can more easily choose the appropriate shampoo, and assist manufacturers in improving product quality according to market needs. The research results show that the MOORA method can provide the right solution in choosing the best shampoo based on various factors, so that it can help consumers in making more informed and objective decisions.

Kombinasi Metode ARAS dan ENTROPY dalam Pemilihan Peserta Lomba Cerdas Cermat Tingkat Kabupaten

Lira Arum Kusumaning Thyas — 2025-07-11

Decision Support System (SPK) is one of the systems that can help someone in making an accurate decision and can be right on target. Many problems can be solved using SPK. Decision Support Systems (DSS) are usually used to support a problem or for an opportunity. Decision Support System applications are usually used in making a decision. The additive ratio assessment method (ARAS) is a method used for ranking criteria, and entropy is a method that can be used in finding weights.

Implementasi Gamifikasi Untuk Meningkatkan Keterampilan Bahasa Sunda Melalui Aplikasi Android dengan Extreme Programming

Prajoko — 2025-07-12

Sundanese is one of the local languages taught at the elementary school level in West Java. Unfortunately, students’ enthusiasm and ability especially in understanding undak-usuk basa or speech level variations in Sundanese remain relatively low. This issue is generally caused by the lack of interactive teaching approaches and the absence of digital media that allow students to learn independently outside school hours. This condition poses a threat to the preservation of local languages among the younger generation. To address this problem, this study developed an Android-based Sundanese learning application using a gamification approach and the Extreme Programming (XP) method, with the goal of increasing students’ interest and understanding of undak-usuk basa independently. The development process involved five main stages: Planning, Design, Coding, Testing, and Release. Key features of the application include interactive quizzes, a coin-based point system, level progression, rewards, traditional Sundanese music, and a user interface designed to suit children. The application was developed using Android Studio with Kotlin and utilized Firebase Realtime Database for storage. To evaluate its effectiveness, pre-tests and post-tests were conducted on third-grade elementary students. The results showed an increase in the average score from 34 to 88 after using the application. These findings indicate that implementing gamification in an educational app based on the XP method can significantly enhance students’ interest and competence in learning the Sundanese language.

Desain UI/UX Aplikasi Website Pemesanan Foto Studio Menggunakan Metode Design Thinking

Sutra Nurani — 2025-07-14

The advancement of digital technology has significantly transformed consumer behavior in accessing and booking services, including in the photography sector. Maka Studio, as a provider of professional photography services, requires a digital platform in the form of a website application that offers an intuitive user interface (UI) and an optimal user experience (UX). This study aims to design the UI/UX of a web-based photography service booking application using the Design Thinking method, which emphasizes a user-centered approach. The design process follows five key stages: empathize, define, ideate, prototype, and test. Data collection was carried out through interviews and observations to identify users’ pain points, which were then translated into visual solutions in the form of wireframes and interactive prototypes using Figma. The main features of the application include service exploration, schedule selection, booking, and payment simulation. The prototype was tested by ten respondents representing the target users to evaluate usability, user flow clarity, and visual satisfaction. The results indicated that the interface design successfully met user expectations, achieving an average System Usability Scale (SUS) score of 93.75, categorized as excellent. These findings affirm that a user-centered design approach is effective in producing functional, efficient, and user-preferred digital solutions.

Peramalan Harga Minyak Mentah Indonesia dengan Model Hibrida ARIMA–FTS Cheng

Erin Jihan Wahyu Kusuma — 2025-07-21

Economic growth is a key indicator of successful economic activities, with adequate crude oil availability playing a crucial role in supporting a country's economic development. This study aims to forecast Indonesian crude oil prices using an Autoregressive Integrated Moving Average (ARIMA)–Fuzzy Time Series (FTS) Cheng hybrid model. The data utilized consists of monthly Indonesian crude oil prices from January 2013 to April 2023 for training and from May 2023 to December 2024 for testing. The training data is modeled using ARIMA, and the residuals from the ARIMA model are subsequently analyzed using the FTS Cheng approach. The hybrid ARIMA-FTS Cheng forecast is generated by combining the predictions from both the ARIMA and FTS Cheng models. The results of the study show that the hybrid ARIMA–FTS Cheng model produced an MAPE of 7.46% on the training data and 4.57% on the testing data. Therefore, the ARIMA–FTS Cheng hybrid model is considered suitable for forecasting Indonesia's crude oil prices.

Sistem Pendukung Keputusan Pemilihan Media Chatting Terbaik Menggunakan Metode MAUT

Mochamad Dedy Subekti Rahardjo — 2025-07-21

The development of technology is increasingly widespread so that it can make it easier for us to carry out all activities / activities. For example, such as communicating even though they are far away. By using media which is now very rapidly developing, the media are Whattsap, Instagram, Facebook and so on, but in the selection of chat media there is often confusion because there are too many features contained in the chat media. so in this study there are 5 criteria including Storage Media, Security, Application Features, Appearance / Interface, and Network Data Usage. So that in solving this problem, a decision support system is needed with the help of a method to get a fast and accurate final result. So in this study, with the title of selecting the best chat media, the best ranking results were found in A2, the name of the media Instagram with a total value of 0.1623.

Penerapan VLAN pada VAP Menggunakan Mikrotik CAPsMAN untuk Manajemen Bandwidth Berbasis PCQ

Devit Satria — 2025-07-23

This study uses the Network Development Life Cycle (NDLC) method to design and test a Mikrotik-based wireless network system in a fast-food restaurant environment. The system integrates CAPsMAN, Virtual Local Area Network (VLAN), Virtual Access Point (VAP), and Per Connection Queue (PCQ) technologies to create a centrally managed and efficient network. Two separate SSIDs are configured for internal Employee and external Consumer users, each allocated 7 Mbps and 13 Mbps of bandwidth out of a total of 20 Mbps. Test results show that the system is able to divide bandwidth fairly, assign IP addresses according to VLAN segments, and implement a time-based hotspot login for 1 hour. Connection success reached 100% without IP conflicts or traffic dominance. These results prove that the combination of CAPsMAN, VLAN, VAP, and PCQ is effective in dense user environments with temporary access needs.

Optimalisasi Model Jaringan Syaraf Untuk Pengenalan CAPTCHA dengan Metode LeNet-5

Rocky Putra A — 2025-07-23

In general, CAPTCHA is an image containing distorted letters or numbers. This test involves users typing the results of guessing letters or numbers in the distorted image as security before users can enter or access a website they want to go to. In this paper, a simulation of an automatic reader system for CAPTCHA has been created where the letters and numbers in the image are carried out in several stages. The initial stage involves training using the EMNIST dataset to train the model to recognize general letter and digit characters before recognition in the CAPTCHA image. Furthermore, the process of recognizing letters and numbers in different CAPTCHA images is carried out to read the text contained in the CAPTCHA. The Convolutional Neural Network (CNN) model of the LeNet-5 method is used as a method for reading distorted letters and numbers in CAPTCHA with a high level of accuracy, achieving 88.56%.

Pengaruh Manajemen Bandwidth Terhadap Skalabilitas Akses Internet di Jaringan LAN

Betalia — 2025-07-23

The increasing intensity of internet usage in school environments demands optimal network management to ensure stable and high-quality connections. This study aims to evaluate the impact of bandwidth management implementation on the scalability of internet access within the Local Area Network (LAN) at SMKN 5 Seluma, Bengkulu Province. The research employed a descriptive quantitative method with an experimental approach, utilizing the Simple Queue feature on MikroTik devices. Data collection was conducted before and after the implementation, focusing on five key parameters: latency, bandwidth usage, packet loss, the ratio of active users to connection performance, and network availability. The test results showed significant improvements, including a reduction in latency from 144 ms to 52 ms, a decrease in packet loss from 2.58% to 0.5%, and an increase in availability from 94.5% to 99.48%. Statistical testing using the paired t-test confirmed that the differences were significant (p < 0.05). Therefore, the implementation of bandwidth management using the Simple Queue feature has proven effective in improving network efficiency and stability, even under high traffic conditions.

Rancangan Sistem Informasi Berbasis Web dengan Metode Rapid Application Development (RAD) Pada Perpustakaan Sekolah Menengah Kejuruan

Yusuf Bachtiar — 2025-07-24

The library information system plays a crucial role in supporting academic activities and literacy in educational institutions, including SMK Negeri 1 Babelan. Efficient management of member data, books, borrowing, and returns poses a major challenge when a manual system is still used, as is the case in this school library. This situation slows down the library's workflow and reduces student interest in visiting the library due to the perceived slow performance. The difficulty in locating books on the shelves, the availability of necessary books, and so on often lead to situations where students find that their needs cannot be met when they arrive. The role of information systems in various aspects, including libraries, gives them a competitive advantage. This research develops a desktop library application to facilitate data management from borrowing, returning, book searching, to member administration, aiming to improve operational efficiency and assist staff in daily tasks. The Rapid Application Development (RAD) method was chosen for its quick and iterative development, involving users at every stage. It begins with needs analysis, prototype creation, followed by testing and continuous refinement. This research also aims to simplify the library operating system, which has so far been done manually. The results of Blackbox testing and the outcomes of the program testing show that all functionalities of the buttons and menus on the website are functioning well with an average score of 4.55 from both validators, which falls into the 'very good' category.

Evaluasi Teknis Performa Linux Mint dan Windows dalam Pengelolaan Sistem IT

Yudhistira Damaryudha — 2025-07-24

This study aims to evaluate and compare the technical performance of the Linux Mint 21.3 operating system with Windows 11 in the context of desktop use at PT Tatalogam Lestari. The research method used is a quantitative approach with a comparative experimental design. Measured parameters include CPU usage, RAM, boot time, and software compatibility. Results show Linux Mint is more efficient in resource use and boot speed, while Windows 11 excels in business software compatibility. In-depth interviews revealed that Linux Mint is well accepted by users although it requires an adaptation period. In conclusion, Linux Mint can be an efficient solution for specific divisions that do not depend on Windows-only software, provided that training and technical assistance are available.

Pemodelan dan Prediksi Tingkat Pengangguran Menggunakan Pendekatan Hibrida GARCH dan BSTS

Ade Priyatna — 2025-07-26

This study aims to understand and predict the unemployment rate patterns based on educational background in Indonesia between 1986 and 2024, with a focus on university graduates. The data, which was initially complex, was successfully processed into a format ready for time series analysis, and the GARCH (Generalized Autoregressive Conditional Heteroskedasticity) model was applied to measure the volatility of unemployment. The evaluation results show that the GARCH model's assumption regarding the stability of the average unemployment rate is inaccurate, as evidenced by the large error values (RMSE 283209.26 and MAE 246252.37), indicating that this model does not fully capture the fluctuations in unemployment. The average coefficient (mu) is 436.50, and the log-likelihood is -284.05, with conditional volatility forecast values ranging from approximately 1.91e+11 to 2.79e+11. The Bayesian Structural Time Series (BSTS) model was also applied to decompose the data into long-term trend components and seasonal patterns, providing a clearer picture of unemployment movement. However, technical constraints in the implementation of BSTS using TensorFlow Probability resulted in predictions not being completed. Nevertheless, this analysis shows that the unemployment rate of university graduates is highly volatile, and improvements in the GARCH model, as well as resolution of the technical constraints in the BSTS model, are crucial for generating more accurate and reliable predictions.

Penerapan UML dan Metode Waterfall pada Sistem Pelacakan Sertifikat Tanah Berbasis Web

Harry Setya Hadi — 2025-07-26

Land certificate administration services at the ATR/BPN Mentawai Islands Office still face various obstacles, especially in terms of transparency and tracking of the application process which is carried out manually. This can cause uncertainty of information for the public. To overcome these problems, a web-based land certificate administration tracking information system was designed that can be accessed online. This system aims to make it easier for the public to monitor the progress of land certificate applications efficiently, quickly, and transparently.The system design was carried out using the System Development Life Cycle (SDLC) Waterfall model approach, which consists of the stages of needs analysis, design, implementation, testing, and maintenance. In system modeling, Unified Modeling Language (UML) tools were used, including use case diagrams, activity diagrams, class diagrams, and sequence diagrams. Sequence diagrams are used to describe the interactions between objects in the system, such as the flow of tracking certificate applications between users and the system.The system was developed using the PHP programming language on the server side and MariaDB as a database management system. The results of this study are in the form of a web application that can be used by the public and officers to track and manage land certificate applications digitally, effectively, and in a structured manner.

Design and Development of a Student Assessment Application Based on Android Using the Waterfall Model

Muhammad Zulfikar Sachori Putra — 2025-07-26

SD Negeri Samudra Jaya 01 in Kramat Village, Tarumajaya Subdistrict, Bekasi, implements the 2013 curriculum and currently assesses students using Excel. However, manual data processing and no integrated system slow the process and increase errors. Motivated by these limitations, this research developed an Android?based student assessment application with Java and XML in Android Studio. It employs a MySQL database on Serv00.com with PHP?APIs and JSON. UML diagrams ensured a structured system architecture, while development followed the Waterfall methodology and the interview method with the school principal and teachers. Functionality was validated with BlackBox testing, achieving a 99.8% data accuracy rate, API response times under two seconds, and 92% teacher satisfaction during User Acceptance Testing. AES encryption secures both data at rest and in transit, ensuring enhanced security and compliance with the 2013 curriculum. Compared to the previous spreadsheet?based system, the app reduced administrative workload by 40%, enabling teachers to input grades, calculate scores, generate automated reports, and share results via smartphones before report card distribution. Stakeholders now enjoy instant digital access to student progress. The app also provides dynamic reporting dashboards and mobile notifications, filling gaps in existing systems that lack real?time reporting and mobile integration. Data collection involved literature review, observation, and staff interviews. Overall, the application streamlines grading processes, ensures real?time updates, and significantly improves accuracy and efficiency.

Rancang Bangun Aplikasi Pembukuan Koperasi Simpan Pinjam Berbasis Web Menggunakan Metode Extreme Programming

I Komang Yoga Gangga Putra — 2025-07-28

The development of digital technology has significantly impacted the efficiency of financial management, including in savings and loan cooperatives. However, the Bali Provincial Health Department Cooperative still faces challenges such as manual bookkeeping, which is prone to errors, delays in data processing, and difficulties in presenting accurate financial reports. This study aims to design and implement a web-based accounting application using the Laravel framework and MySQL database to automate loan calculations, data storage, and real-time report generation. The system development adopts the Extreme Programming (XP) methodology, which emphasizes short iterations, intensive user communication, continuous testing, and the application of simple design principles to ensure software quality. Testing results indicate that the application can reduce bookkeeping errors, accelerate report generation, and provide cooperative members with quick and accurate access to financial information. The contribution of this study is to offer a digital solution that enhances accuracy, efficiency, and transparency in cooperative financial management, while also supporting the development of local microenterprises.

Perancangan Sistem Informasi Absensi Siswa Berbasis Android Menggunakan Metode Waterfall

Ahmad Fatih — 2025-07-29

Student attendance is a crucial component of school administration, directly linked to discipline and attendance evaluation. At MA Nurul Falah, attendance recording is still conducted manually, which takes approximately ±10 minutes per class. This method is not only time-consuming but also prone to recording errors, negligence, and data loss. These issues can affect the accuracy of attendance data, which in turn impacts academic assessment and student discipline evaluation. This study aims to design and develop an Android-based student attendance information system that enhances the efficiency and accuracy of attendance recording. The research employs a Research and Development (R&D) approach using the Waterfall development model, which is suitable for building systems in a structured and systematic manner. The application is developed using Java and PHP programming languages, with MySQL as the database and Android Studio as the development environment. System testing is carried out using the BlackBox method to ensure all functionalities work as expected, along with a usability evaluation using the System Usability Scale (SUS) to measure user satisfaction and ease of use. The testing results show that the application reduces attendance recording time to approximately ±2 minutes per class (an efficiency improvement of around 80%), with a 100% success rate in functionality across various Android devices. This system offers a digital solution that is effective, efficient, and modern for managing student attendance. It is expected that the system can be further adopted and expanded by other educational institutions as a reference in implementing digital-based administrative processes in schools.

Analisis Sentimen Terhadap Data Komentar Publik Mengenai Isu UU Pilkada 2024 Menggunakan Metode Naïve Bayes dan K-Nearest Neighbor

Sebastianus Adi Santoso Mola — 2025-07-29

The 2024 Regional Head Election Law (UU Pilkada) has become an important issue widely discussed in Indonesia, especially on the social media platform X. Various public comments related to this issue contain positive, negative, and neutral sentiments, reflecting public perceptions. This study aims to analyze the sentiment of public comments on the 2024 UU Pilkada using two machine learning methods: Naïve Bayes and K-Nearest Neighbor (K-NN). The dataset consists of 3864 comments divided into three sentiment classes: 1477 negative comments, 1385 neutral comments, and 1002 positive comments, all of which have undergone text preprocessing. Evaluation was conducted using k-fold cross-validation (k=10). The test results show that the Naïve Bayes method achieves the highest accuracy of 63.47%, while K-NN reaches 56.73%. The precision for negative sentiment is 56.84%, meaning that about 43% of the comments predicted as negative by the model are actually not negative. The recall for negative sentiment is 45.45%, indicating that the model only captures less than half of the actual negative comments. For neutral sentiment, the precision of 60.71% and recall of 66.23% suggest that the model performs fairly well in recognizing neutral comments, although there is still a 39.29% error. For positive sentiment, the precision of 55.55% and recall of 57.63% indicate errors in classifying positive comments. Overall, while the model can correctly classify a portion of the data, there is potential to improve accuracy for both the negative and positive classes.

Sistem Informasi Berita Online Berbasis Web Untuk Penyebaran Informasi Publik dengan Menggunakan Metode SDLC

Muhammad Randy Janitra — 2025-07-29

This research aims to design and develop a web-based information system that simplifies the process for users to search for and access news content online. The study is motivated by the growing need for public information to be disseminated quickly, accurately, and without restrictions of time or location. The system was developed using the WordPress platform and is presented through a website called Koran Pengawas Korupsi (KPK), designed with a responsive interface, intuitive navigation, and an effective search function. The development process employed the Software Development Life Cycle (SDLC) using an iterative approach, allowing for flexible and incremental system development based on user feedback. Data collection methods included surveys and interviews to better understand user needs and guide the design of relevant features. The resulting website includes functionalities such as news search, categorization, user comments, and an administrative dashboard for content management. Testing results indicate that most users are satisfied with the user interface, search capabilities, and visual layout. However, suggestions for improvement were noted, including better content relevance and further design enhancements. In conclusion, this study contributes to the development of user-friendly and efficient web-based information systems that support effective news dissemination to the public.

Pemanfaatan Aplikasi Digital dalam Operasional Kedai Sembako Indah Untuk Perluasan Pasar dan Peningkatan Pelayanan

Indah Sari — 2025-07-31

Digital transformation is one of the key factors in increasing the competitiveness of Micro, Small, and Medium Enterprises (MSMEs) in the industrial era 4.0. Kedai Sembako Indah, as one of the MSMEs in the staple food trading sector, faces challenges in operational efficiency, financial recording, and marketing. This study aims to analyze the use of digital applications in supporting the daily operational activities of Kedai Sembako Indah, including stock management, sales transactions, and marketing strategies. The method used is a descriptive qualitative study with a case study approach. Data were collected through interviews, direct observation, and documentation during the implementation process of digital applications such as cashier applications (point of sale), e-wallet platforms, and social media. The results of the study show that the use of digital applications has a positive impact on time efficiency, accuracy of transaction recording, and increased interaction with customers. In addition, the use of social media also helps expand market reach. The main obstacles faced are limited digital literacy and initial adaptation to new technologies. In conclusion, operational digitalization through simple applications can be a strategic initial step in strengthening the performance and sustainability of MSMEs such as Kedai Sembako Indah. Continuous assistance is needed so that technology adoption can run optimally.

Model Hibrida ARIMA-Neural Network untuk Peramalan Kasus Tuberkulosis

Arriza Agung Setyabudi — 2025-07-31

Tuberculosis (TB) remains a significant public health challenge in Surakarta City, necessitating accurate forecasting methods to support effective and planned control strategies. This study aims to evaluate the performance of the Autoregressive Integrated Moving Average-Neural Network (ARIMA-NN) hybrid model in forecasting monthly TB cases in the Surakarta region. The performance of this hybrid model is further compared with the ARIMA model. The research data used consists of monthly TB case data from January 2019 to September 2024 obtained from the Surakarta City Health Department. The data is divided into two sets: training data from January 2019 to December 2023 and testing data from January 2024 to September 2024. The ARIMA(0,1,1) model was identified as the best model for capturing the linear component of the data, yielding a Mean Absolute Percentage Error (MAPE) of 14.52% on the training data and 16.55% on the testing data. The residuals from the ARIMA(0,1,1) model were then further modeled using a Neural Network with 5 hidden neuron architecture, period lookback 6, and a learning rate of 0.1, to capture the remaining non-linear patterns. The developed ARIMA(0,1,1)-NN hybrid model showed better forecasting performance, with a MAPE value of 14.34% on the training data and 14.48% on the testing data. These results indicate that the ARIMA-NN hybrid approach offers the potential for improved accuracy compared to the ARIMA model in the context of TB case forecasting in Surakarta.

Klasifikasi Produk Iphone dengan Menggunakan Algoritma XGBoost

Stevi Freshia Sihombing — 2025-07-31

The iPhone has become a symbol of advanced technology and a modern lifestyle that is highly sought after by the global community, including in Indonesia. Known for its stable and exclusive iOS operating system, this product offers seamless cross-device integration, consistent system updates, and high performance through the support of the latest generation of processors. The iPhone also has a visual appeal through a minimalist and elegant design, as well as superior features such as professional camera quality, high-level data security, and power efficiency. The high popularity of the iPhone makes it one of the most competitive products in the smartphone market. However, the diversity of models, features, and prices of each iPhone series causes user preferences to be diverse and complex. In an effort to understand these preferences, an accurate classification method is needed to group products according to consumer appeal. This study adopts the XGBoost algorithm which is known to be effective in handling complex and large data. By utilizing iPhone product sales transaction data in the Indonesian market, this model is designed to identify purchasing patterns and user segmentation. The classification results are expected to provide deeper insights for manufacturers and marketers in formulating more targeted data-based marketing strategies.

Sistem Klasifikasi Kelayakan Penerima Bantuan Langsung Tunai Menggunakan Metode K-Nearest Neighbor (KNN) Berbasis Website

Dewi Sriwani — 2025-07-31

Poverty is the condition of a person's inability to fulfill the basic needs of life, which is often measured by income that is lower than the average in a region. In Indonesia, the poverty rate, including in Kabupaten Jombang, continued to increase from 2012 to 2017, with various government efforts to overcome this through social programs such as BLT (Direct Cash Assistance), Community Health Insurance, and the Family Hope Program (PKH). However, despite these programs, the data collection process for beneficiaries in some areas, such as Tanah Periuk Village, is still done manually, causing inaccurate targeting in the provision of assistance. For this reason, a more efficient solution is needed in determining the eligibility of beneficiaries. One of the technologies that can be used is data mining, especially the classification method, to analyze beneficiary data based on certain criteria. This research uses the K-Nearest Neighbor (K-NN) algorithm to build a classification system for the eligibility of direct cash transfer recipients in Tanah Periuk Village, with the aim of improving accuracy and efficiency in the beneficiary selection process. This system is web-based, which allows ease of processing and updating data centrally. The results of this study provide eligibility scores for BLT (Direct Cash Assistance) recipients based on the criteria provided. The criteria that are assessed are: House Condition, Income, Occupation and Number of Dependents. One of the families who “DESERVE” to receive assistance is Martina with semi-permanent house conditions, an income of IDR 1,000,000/month, a housewife's job, and 3 dependents.

Penerapan Teknologi Digital untuk Operasional dan Layanan UMKM Florist

Rena Rindiany — 2025-07-31

Florist MSMEs face challenges in managing operations and reaching a broader customer base. This study aims to analyze the use of digital technology to improve operational efficiency and service quality at Rndyaniii Florist, an MSME located in Rantauprapat. The research method used is a case study with a descriptive qualitative approach through observation, interviews, and documentation. Rndyaniii Florist utilizes various digital platforms such as Instagram, Facebook, TikTok, and WhatsApp Business for promotion, communication, and product ordering. In addition, the store also uses a website based on Google Sites as a digital catalog to facilitate customer access to product information. This study is important to examine how digital technologies such as social media, communication applications, and simple websites can be effectively implemented in the context of florist MSMEs. Preliminary findings indicate that consistent use of digital platforms can accelerate the ordering process, enhance customer interaction, and expand market reach. Digitalization also supports daily operational efficiency and builds a more professional business image. This research provides a concrete overview of digitalization strategies that can be applied by other florist MSME owners, especially in facing increasingly technology-based market competition.

Segmentasi Produk Fashion Berdasarkan Harga, Ukuran, dan Merek Menggunakan K-Means di Rapidminer

Ival Sanjaya — 2025-07-31

Tight competition and product diversity are the hallmarks of the fashion industry, especially in terms of price variation, size, and brand. To help the process of making more accurate business decisions, product segmentation is needed to identify the characteristics of each group. This study utilizes the K-Means Clustering algorithm to group fashion products based on these attributes. The implementation is carried out using the RapidMiner platform, starting with the data normalization stage and the transformation of categorical attributes into numeric form. The optimal number of clusters is determined through the elbow method approach, which shows a significant decrease in the average distance between data in the cluster. The clustering results show the formation of product groups with different characteristics, which can be utilized in stock planning and marketing strategies. This study confirms that the K-Means algorithm is effective in analyzing the distribution of fashion products based on the main attributes they have.

Pemanfaatan Algoritma K-Means Clustering Pada Sistem Rental Mobil

Sri Wulandari Maesaroh — 2025-07-31

PT. Station Armada Indonesia is one of the companies engaged in the car rental service sector. With the many types of car choices offered, it is not uncommon for many customers to feel confused in choosing what type of car suits their needs. This problem is often experienced by customers who are confused by the many choices of car types available. In this study, the k-means algorithm was used to group cars based on several attributes. The k-means algorithm can be used to group car type data to help provide recommendations for choosing a car type. The purpose of this study is to make it easier for customers to choose the type of car that is most in demand and as material for PT. Station Armada Indonesia to respond better to market changes and achieve better results. Grouping car rental fleets based on rental prices and mileage by utilizing the k-means algorithm can help PT. Station Armada Indonesia group car types. From the grouping results, two cluster groups were obtained with the character of the first cluster being less in demand by customers and the second cluster group being the most in demand by customers. So that the company can easily prepare the type of fleet that is most in demand. In the application of data mining methods using k-means is very helpful and makes it easier for PT. Station Armada Indonesia to develop more effective marketing and offering strategies. By grouping car types with the implementation of k-means can facilitate customer knowledge in choosing car types based on customer needs.