cover
Contact Name
Sugeng Santoso
Contact Email
icitjournal@raharja.info
Phone
+6281319701122
Journal Mail Official
icitjournal@raharja.info
Editorial Address
Jl. Jenderal Sudirman No. 40 Modern Cikokol Tangerang - Banten 15117 Indonesia
Location
Kota tangerang,
Banten
INDONESIA
ICIT (Innovative Creative and Information Technology) Journal
Published by UNIVERSITAS RAHARJA
ISSN : 23565195     EISSN : 26548704     DOI : 10.33050/icit
ICIT (Innovative Creative and Information Technology) Journal adalah wadah publikasi ilmiah dalam bidang riset Business Intelligence (BI), bidang riset Information Engineering dan bidang riset TIK secara umum bagi Dosen dan Mahasiswa Pascasarjana Magister Teknik Informatika (MTI) dan juga artikel ilmiah dari luar Pascasarjana MTI UNIVERSITAS RAHARJA yang merupakan hasil riset ataupun review artikel. ICIT Journal diterbitkan sebanyak 2 kali dalam setahun, yaitu bulan Februari dan Agustus
Articles 218 Documents
Coffee Buyer Segmentation using PCA Model and K-Means Algorithm on Coffee Customers Suharmanto; Muhammad Faisal; Janu Ilham Saputro; Wiranti Sri Utami
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4330

Abstract

Coffee is a plant that originates from the agricultural industry which is produced and made into a drink through coffee beans and a series of processes such as roasting and grinding it into coffee powder which will be brewed. Currently, many countries have cultivated coffee plants and there are two generally well-known coffees, namely Robusta coffee and Arabica coffee. Each buyer has different characteristics in enjoying coffee drinks, including the time of purchase, the product purchased from the coffee shop, and the location of the coffee shop. Therefore, research is needed to develop a marketing strategy that suits the needs of the buyer segment.  To support this research the author uses the PCA (Principal Component Analysis) model and the K-Means method to group customer characteristics. Standard deviation is used to determine the average value of each cluster in coffee shop outlets, with a PCA value on product_id of 0.99986001 and unit_price of 0.01673209 from a total of 96% of clusters. This research can be used as a good reference for students, researchers, and can also be used as a marketing strategy medium.
Development and Evaluation of An Android-Based Student Attendance System Using Qr-Code and Waterfall Method at the Global Institute Alfiah Khoirunisa; Triono; Alinda Rahma Nur’aini; Tri Astuti
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4370

Abstract

Student presence plays a crucial role in the learning process at the Bina Sarana Global Institute of Technology and Business. However, lecturers face challenges in manually processing paper-based attendance, which is time-consuming (taking 15–20 minutes per class session) and prone to data scattering. This study aims to develop and evaluate an Android-based Student Attendance System, named Global Academic Information System (GAIS), integrated with QR-Code technology. The system was developed using the Waterfall model and designed with Unified Modeling Language (UML). To evaluate the software's functionality and performance, Black-box testing and User Acceptance Testing (UAT) were conducted. The Black-box testing yielded a 100% success rate across all core modules, including login, QR scanning, and attendance data management. Furthermore, the UAT result reached an acceptance score of 87.5% from students and lecturers, confirming that the GAIS application significantly eliminates manual processing time and improves data logging efficiency.
SVM-Based Sentiment Analysis for Bug Tracking Priority Scale Lutfi Hibatullah Dwi Putra; Deden Rustiana; Nina Rahayu
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4385

Abstract

The rapid expansion of mobile applications in Indonesia creates a massive density of user reviews, making manual categorization of technical bugs highly inefficient for development teams. This research develops an automated bug tracking system powered by sentiment analysis to address these constraints. Utilizing a dataset of 1,200 reviews extracted from the Google Play Store (2023-2024), the study compares the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel against the Naive Bayes classifier. The methodology encompasses automated scraping, text preprocessing via the Sastrawi stemming library, and TF-IDF feature weighting to handle semantic ambiguities in informal Indonesian text. Evaluation results demonstrate that SVM achieves a superior accuracy of 86.25% and an F1-score of 0.86, significantly outperforming Naive Bayes which stands at 77.50%. McNemar’s test yields a p-value of 0.006, statistically validating SVM’s effectiveness in reducing False Negatives. While highly successful in rule-based priority scaling, the architecture automatically classified the actionable technical bug reports into 150 Critical, 200 Major, and 50 Minor urgency categories. Operationally, the automated system processes data 99.8% faster than manual methods, cutting down the identification period from 12 hours to just 85 seconds. These findings imply that embedding SVM into bug tracking architectures facilitates real-time mitigation of critical stability issues. While highly successful, future studies should focus on overcoming linguistic limitations regarding sarcasm detection through advanced deep sequential processing.
The Use of Artificial Intelligence in Business Intelligence to Support Data-Driven Decision-Making Using Descriptive Analytics Aulia Suci Ramadhanty; Thalita Anisa Maharani; Sandro Alfeno
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4430

Abstract

This study investigates how Business Intelligence (BI) utilises Artificial Intelligence (AI) to support data-driven decision-making using Descriptive Analytics methods. The research reviewed twelve selected articles, identified from an initial pool of 47 articles retrieved from the PubMed, Scopus, and Web of Science databases (2020–2026). A Systematic Literature Review (SLR) approach was employed, in conjunction with the PRISMA protocol, and the methodological quality of the eligible articles was assessed using the Critical Appraisal Skills Programme (CASP) checklist. The results of the review indicate that the integration of AI and BI enhances the efficiency of data analysis, with CRISP-DM-based descriptive analysis reducing data processing time from six hours to thirty minutes. According to the research, Descriptive Analytics is a strategic step towards a Data-Driven Decision Making (DDDM) ecosystem. However, issues such as high costs and labour shortages still need to be addressed.
The Application of Business Intelligence for Analysis and Prediction of Obesity Rates using The Decision Tree Method Elsa Mutiarasari; Dina Auliya Rahmadani; Sandro Alfeno
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4431

Abstract

Obesity is a health issue influenced by diet, physical activity intensity, and lifestyle. This study aims to apply Business Intelligence (BI) to analyze and estimate the prevalence of obesity using the RapidMiner-based Decision Tree method and interactive visualization through Google Looker Studio. The dataset used consists of the Obesity Dataset, containing 1,610 entries and using 15 attributes. The model was tested using a 10-fold cross-validation approach and successfully achieved an accuracy of 71.55% ± 3.18%. The results of this study emphasize that height, age, and physical activity are the most important factors in obesity classification. In addition, the Google Looker Studio dashboard can present interactive data visualization, allowing users to easily explore obesity patterns related to lifestyle and health conditions. This study suggests that the combination of Decision Tree and Business Intelligence can increase efficiency in health data analysis.
Designing and Analyzing B2B European Sales Performance Using an Interactive Google Looker Studio Dashboard Agung Wiguna; Yasyfi Al-Ghifari; Sandro Alfeno
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4468

Abstract

This study aims to design and implement a dashboard that displays sales data using Google Looker Studio as a tool for analyzing company performance. The data used includes 1,001 sales transactions from 2019 to 2020, with a total revenue of EUR 112,741,144.68 and a profit of EUR 18,892,500.11. The approach used is Descriptive Analytics using interactive data visualization techniques. The analysis was conducted from three perspectives: product category, country region, and type of device used to access the data. The study shows that the Clothing category provides the largest revenue. Portugal makes the largest contribution to sales, accounting for 24.66%. Also, PC devices are the most commonly used for transactions, with a share of 78.02%. The dashboard that was made can show data in a visual and interactive way, which helps people make decisions based on data more quickly and accurately.
Design of A Water Level Sensor System for Water Tanks in Internet of Things-Based Companies Yunita Wulansari; Mochamad Al Ghoniyu Oka; Farell Havids Abdillah
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4474

Abstract

Water reservoir management in company facilities requires water level monitoring that can provide fast information and help prevent empty or overflow conditions. This study designs and simulates an Internet of Things (IoT)-based water reservoir monitoring and filling system using NodeMCU ESP32, HC-SR04 ultrasonic sensor, LCD, LED, buzzer, relay, and Blynk. Different from studies that report the implementation of physical devices, this study is limited to Wokwi simulations so that the results cannot be considered as field validation. The experimental design uses five reference distance points, namely 200, 150, 100, 50, and 2 cm, with 200 cm as the empty reference condition and 2 cm as the full reference condition. Evaluation is carried out using absolute difference, mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE), as well as Black Box functional testing of connections, sensor readings, indicators, pump control, and data transmission to Blynk. The simulation results show an MAE of 0.056 cm, an RMSE of 0.066 cm, and a MAPE of 0.337%. The system also demonstrates monitoring and control functions according to the simulation scenario. The contribution of this research is not in the novelty of the components, but rather in the integration of the monitoring-control flow tailored to the company's reservoir monitoring needs, the definition of measurement reference points, and quantitative evaluation during the simulation stage. Subsequent validation needs to be carried out using a physical prototype, repeated measurements, latency testing, packet loss, and operational resilience.
Design and Usability Evaluation of the "EL-Nyurat" Website-Based Automatic Letter Generation System Using the Prototyping Method Karunia Suci Lestari; Muhammad Noval Aryansah; Fhia Amelia
ICIT (Innovative Creative and Information Technology) Journal Vol. 12 No. 02 (2026): August 2026
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/icit.v12i02.4482

Abstract

The digitalization of administration has become a necessity to improve the efficiency of correspondence management within student organizations. However, the letter creation process is still largely carried out manually using Microsoft Word by modifying existing documents, which has the potential to cause writing errors, inconsistent formatting, and less optimal archive management. This study aims to develop a prototype of a web-based automatic letter generation system without writing any program code, namely EL-Nyurat, to support a faster, more consistent, and more efficient correspondence administration process. The system was designed using the Prototype method, which consists of the stages of requirement gathering, prototype design, prototype evaluation, development, testing, and implementation. System evaluation was conducted through Black Box Testing to examine system functionality and the System Usability Scale to measure the level of usability. The testing results indicate that all major system features function according to the specified functional requirements. Furthermore, the usability evaluation achieved an average SUS score of 92, which falls into the Excellent, Acceptable, and Grade A categories. The functional and empirical testing results demonstrate that EL-Nyurat possesses good functionality and a high level of usability, thereby showing the potential to support the digitalization of correspondence administration in student organizations, outperforming previous manual correspondence methods while offering a faster, more adaptive, and less error-prone administrative experience for end users.