Scientific Journal of Information System

APPLICATION OF DATA MINING TECHNIQUES TO ANALYZE ATTENDANCE AND IMPROVE THE QUALITY OF CHINESE LEARNING

2025-04-22T07:47:17+00:00

In the era of globalization, learning Chinese is increasingly important, but challenges such as low student attendance and learning quality are still significant problems. This article discusses the application of data mining techniques as a solution to analyze student attendance and improve the quality of Chinese learning. By collecting and analyzing attendance data from 200 students for one semester, through classification and visualization methods, this article identifies patterns that affect student attendance. The analysis results show that 65% of students who followed the interactive teaching method attended more than 80% of the total meetings, compared to only 40% of students who followed the traditional teaching method. In addition, it was found that 75% of students who received additional material for difficult topics experienced a 20% increase in average test scores compared to pre-intervention scores. Recommendations for improvement were made based on these findings, including adaptation of teaching methods and provision of supplementary materials. Through a case study of an educational institution that has successfully implemented this technique, this article shows that data mining can not only improve student attendance, but also significantly improve the quality of learning. This research is expected to encourage educational institutions to adopt data mining technology in an effort to improve students' learning experience.

HOW TECHNOLOGY AFFECTING RESEARCHERS IN THE ERA OF GENERATIVE AI

2025-04-28T01:43:09+00:00

In the rapidly evolving research landscape, generative AI is emerging as a transformative force. This study explores the multifaceted impacts of generative AI on researchers across various disciplines. By automating routine tasks, enhancing data analysis, and generating novel hypotheses, AI tools are significantly boosting productivity and opening new avenues for innovation. However, these advancements also present challenges, including ethical considerations, the need for transparency, and the potential for bias in AI-generated results. Moreover, the integration of AI into research demands the development of new skill sets, presenting both opportunities and risks for researchers. Drawing on recent studies, this article provides a comprehensive overview of how generative AI is reshaping the research landscape and highlights the critical dynamics researchers must navigate in this new era.

THE ROLE OF GREEN IT ON ENHANCING ENERGY EFFICIENCY IN ORGANIZATIONS

2025-03-21T02:06:04+00:00

Green IT is a cutting-edge information technology strategy designed to lessen the negative environmental effects of using IT infrastructure and devices. This study uses a qualitative methodology to investigate how Green IT is being adopted in different enterprises, emphasizing its advantages, difficulties, and practical implementation techniques. Document analysis and literature reviews from a range of sources pertaining to the adoption of green IT were used to gather data. According to the research, companies who use green IT see improvements in operational sustainability, lower carbon emissions, and increased energy efficiency. However, there are a number of significant obstacles to its adoption, including high upfront expenditures, ignorance, and reluctance to adopt new technologies. This report also emphasizes how crucial laws and rules are to encouraging the use of green IT. The study's conclusion highlights how putting Green IT into practice helps build a more sustainable and ecologically friendly technology ecosystem. As a result, companies must create all-encompassing plans for implementing Green IT, which should include purchasing energy-efficient equipment and increasing organizational understanding. This study helps policymakers, practitioners, and scholars better understand and support the future adoption of green IT.

OPTIMIZATION OF INDOMARET'S BUSINESS STRATEGY IN JAKARTA THROUGH DATA MINING AND INFORMATION SYSTEM TECHNOLOGY

2025-04-22T07:48:04+00:00

This study aims to analyze the number of Indomaret outlets in Jakarta by utilizing information
systems technology and data mining techniques. Using quantitative data from 500 Indomaret
locations, the analysis was conducted to identify distribution patterns and the factors influencing
outlet growth. Clustering and linear regression methods were employed to evaluate the relationship
between the number of outlets and demographic and economic variables, such as population density,
per capita income, and distance from the city center. The analysis results indicate a significant
relationship between population density and the number of Indomaret outlets, with a regression
coefficient of 0.75 (p < 0.01), meaning that every increase of 1,000 people in population density is
associated with the addition of 3 Indomaret outlets. Clustering analysis also identified three strategic
location groups with high growth potential. The main contribution of this research lies in integrating
data mining methods with spatial analysis to understand modern retail expansion in urban areas—an
approach that is still rarely explored in previous studies. These findings not only enrich the literature
on data-driven retail location analysis but also provide practical insights for industry players in
formulating data-based expansion strategies. This research offers valuable insights for Indomaret’s
management in making strategic decisions regarding expansion and store placement, demonstrating
that the use of information systems and data mining is effective in supporting quantitative analysis
for business development in the retail sector.

A COMPARATIVE REVIEW OF CLUSTERING AND CLASSIFICATION ALGORITHMS FOR BIG DATA ANALYTICS

2025-05-06T09:26:09+00:00

These days, there's so much data being created all the time. It’s honestly getting hard to keep up.
That’s where data mining comes in. Basically, people use it to make sense of all this huge amount of
information, and there are two main ways to do it: clustering and classification. I found that there are
a bunch of algorithms for both, like K-Means, DBSCAN, and Hierarchical Clustering for clustering,
and then there’s Decision Tree, Naïve Bayes, SVM, and Random Forest for classification. Each of
these has its own strengths and weaknesses depending on the data you’re working with. The point of
this paper was really to see how these algorithms perform and to give people an idea of which one
might work best depending on the situation. What we found is that no algorithm is perfect for
everything. So, choosing the right one really comes down to understanding the data and figuring out
what you're trying to get out of it.