Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)

Strategic Framework for Implementing Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) for Personalized AI in Informatics Engineering: A Case Study of Malikussaleh University Abil Khairi; Wahyu Fuadi; Yesy Afrillia
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study develops a strategic framework for integrating Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to support personalized Artificial Intelligence (AI) applications within the Informatics Engineering Department at Malikussaleh University. By utilizing localized datasets, the framework aims to enhance research productivity and improve educational outcomes while prioritizing data privacy and security. The study examines the opportunities and challenges associated with embedding these technologies into the university’s existing infrastructure, proposing a phased approach to adoption. Emphasis is placed on the modernization of academic practices through AI-driven tools that cater to local educational and research needs. The findings offer insights into implementing advanced AI systems that could serve as a model for similar educational settings focused on sustainable AI adoption.
Application of the Naïve Bayes Method in Optimizing Marketing Performance at PT. Semen Indonesia Mahesa Reglisalo; Dahlan Abdullah; Yesy Afrillia
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study examines the application of the Naïve Bayes method to improve marketing performance at PT. Semen Indonesia. In an increasingly competitive business environment, effective data management is crucial for strategic decision-making. Currently, PT. Semen Indonesia utilizes the SAP system to manage sales and financial data, but it lacks an automated system to analyze marketing performance. This research aims to develop a Naïve Bayes-based classification system to monitor marketing performance, considering attributes such as profit, market share, sales volume, and customer satisfaction. The Naïve Bayes method was chosen for its accuracy in handling large-scale data and its ability to provide fast and efficient predictions. Marketing performance data is processed using this method to categorize marketing performance as “good” or “poor.” The analysis results show that the developed system achieves a classification accuracy of 43.75% for the “good” category and 56.25% for the “poor” category. This system assists management in designing more effective marketing strategies by leveraging historical data to predict trends and market needs. Keywords: Naïve Bayes, marketing performance, PT. Semen Indonesia, data analysis, classification system, profit, market share