cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Supiyandi
Contact Email
supiyandiyt@gmail.com
Phone
+628111261633
Journal Mail Official
ejocsaic@gmail.com
Editorial Address
Jl. Gurilla No. 2 Sidorejo Kec. Medan Tembung Kota Medan 20222
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer Science Artificial Intelligence and Communications
Published by CV. Raskha Media Group
ISSN : 31093981     EISSN : 31089828     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Earth & Planetary Sciences Engineering
Journal of Computer Science Artificial Intelligence and Communications is a multidisciplinary, peer-reviewed journal dedicated to advancing research in computer science, artificial intelligence (AI), and communication technologies. The journal publishes high-quality original articles, reviews, and case studies that explore the latest innovations, theories, algorithms, and applications shaping the digital world. Focused on the intersection of computational systems, intelligent automation, and seamless communication networks, JOCSAIC aims to foster collaboration and knowledge exchange among researchers, practitioners, and academics working across diverse sectors such as data science, machine learning, telecommunications, and intelligent systems. The journal is a key resource for cutting-edge developments and trends in these transformative fields.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 5 Documents
 1 
Search results for , issue "Vol 1 No 2 (2024): November 2024" : 5 Documents clear
Analysis of Historical Student Visit Data Using Time Series Algorithm Sri Ramadhany; Sahara Abdy; Alfiarini
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.16

Abstract

The analysis of historical student visit data plays a critical role in understanding student behavior, optimizing campus resources, and enhancing service delivery in educational institutions. This study presents an analytical approach to examine patterns and trends in student visitations using a time series algorithm. By leveraging historical datasets from campus access logs, we aim to identify periodic behaviors, peak visitation times, and anomalies that may reflect special events or system irregularities. The research employs time series methods such as moving average, exponential smoothing, and ARIMA (AutoRegressive Integrated Moving Average) to forecast future student visit patterns based on previous trends. Data preprocessing, normalization, and visualization techniques are applied to ensure data quality and interpretability. The results demonstrate that student visits tend to follow specific weekly and monthly patterns, with increased activity near academic deadlines or events. The ARIMA model, in particular, shows strong predictive accuracy with minimal error margin. This analysis not only provides insights for administrative planning—such as scheduling staff, managing facilities, or enhancing security—but also serves as a foundation for developing intelligent decision-support systems. In conclusion, applying time series algorithms to historical student visitation data proves effective in predicting future trends, thereby supporting data-driven decision-making processes within educational institutions.
Utilization of Sales Data Analysis for Product Recommendation Systems in E-Commerce Using the Apriori Algorithm Muhammad Noor Hasan Siregar; Furqan Khalidy; Rismayanti; Khairunnisa
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.17

Abstract

The rapid development of e-commerce has significantly increased the volume of sales transactions and customer interaction data. This presents an opportunity for businesses to leverage data mining techniques to extract valuable insights that support decision-making processes. One such application is the development of product recommendation systems, which play a crucial role in enhancing customer satisfaction and driving sales. This research focuses on utilizing sales transaction data to build a product recommendation system using the Apriori algorithm, a well-known method for association rule mining. The study begins with the collection and preprocessing of transaction data from an e-commerce platform. Through the application of the Apriori algorithm, frequent itemsets are identified, and association rules are generated based on specified support and confidence thresholds. These rules reveal purchasing patterns and relationships between products that are frequently bought together. The system then uses these patterns to recommend relevant products to users, aiming to improve cross-selling opportunities and personalize the shopping experience. The results demonstrate that the Apriori-based recommendation model is effective in identifying meaningful product combinations and can be implemented as a lightweight, interpretable alternative to more complex machine learning methods. Furthermore, the system helps e-commerce businesses optimize inventory management and marketing strategies by understanding customer buying behavior. This research concludes that the integration of the Apriori algorithm into recommendation systems provides tangible benefits for e-commerce platforms seeking data-driven personalization solutions.
Sentiment Analysis of Social Media Towards Public Services Using Naive Bayes and Text Mining Rusmin Saragih; Mardiah; Deni Apriadi
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.18

Abstract

The rapid development of information and communication technology has driven the increased use of social media as a means of interaction between the public and service providers. Social media has become a platform for the public to express their opinions on the quality of services they receive, whether in the form of praise, suggestions, or complaints. Therefore, sentiment analysis of social media data can be a strategic tool in evaluating the performance of public services. This research aims to analyze public sentiment towards public services by utilizing text mining techniques and the Naive Bayes Classifier algorithm. The data used was collected from social media platforms such as Twitter and Facebook, followed by a text preprocessing stage that included tokenizing, stopword removal, and stemming. Subsequently, the data was analyzed to classify sentiment into positive, negative, and neutral categories. The test results show that the Naive Bayes algorithm is capable of classifying data with a satisfactory level of accuracy, making it an efficient method for monitoring public perception in real-time. This research contributes to supporting decision-making by government agencies regarding the improvement of public service quality based on publicly available feedback from social media
Visualization and Analysis of Employee Performance Data Using a Power BI-based Business Intelligence Dashboard Imeldawaty Gultom; Eka Pandu Cynthia; Chinthia, Maulidania Mediawati
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.19

Abstract

In the current digital and competitive era, the utilization of Business Intelligence (BI) technology has become crucial in supporting data-driven decision-making. This research aims to develop and analyze a Power BI-based Business Intelligence dashboard focused on visualizing employee performance. This study was conducted by collecting performance data from the Human Resource Information System (HRIS), which was then processed and visualized in the form of key metrics such as attendance rates, individual target achievements, productivity per division, and periodic performance evaluations. Power BI was chosen for its ability to integrate various data sources and present interactive visualizations that are easy for management to understand. The methodology used involves the ETL (Extract, Transform, Load) process, data model design, and the development of visual reports that support descriptive and comparative analysis. The results of this study indicate that the use of BI dashboards significantly helps the company in monitoring employee performance in real-time, identifying trends in productivity decline, and designing data-driven improvement strategies. In addition, this dashboard also serves as an effective communication tool between management and the HR division. Thus, the use of Power BI as a tool for visualization and performance analysis adds significant value to the strategic and data-driven management of human resources
Classification of Customer Credit Risk Levels Using the Random Forest Method: A Case Study on Microfinance Institutions Damayanti, Fera; Arief Budiman; Siti Sundari; Theodora MV Nainggolan
Journal of Computer Science, Artificial Intelligence and Communications Vol 1 No 2 (2024): November 2024
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v1i2.20

Abstract

Credit risk classification plays a crucial role in supporting financial institutions, especially microfinance institutions, in assessing the ability of customers to repay loans. This study aims to develop a credit risk classification model using the Random Forest method, which is known for its accuracy and robustness in handling classification problems. The research uses a dataset obtained from a microfinance institution consisting of various customer attributes such as income, age, loan amount, repayment history, and employment status. The dataset is preprocessed and divided into training and testing sets to evaluate model performance. The Random Forest algorithm is then applied to build a classification model that categorizes customers into three credit risk levels: low, medium, and high. The results show that the Random Forest model achieves a high level of accuracy, with a classification precision of 89%, recall of 87%, and F1-score of 88%. These findings indicate that Random Forest is an effective technique for credit risk classification and can be implemented by microfinance institutions to support better decision-making in credit approval processes. This research also highlights the potential of machine learning techniques in enhancing credit risk management and minimizing non-performing loans.

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 2 No 2 (2025): November 2025 Vol 2 No 1 (2025): May 2025 Vol 1 No 2 (2024): November 2024 Vol 1 No 1 (2024): May 2024