DESIGN AND DEVELOPMENT OF A PREDICTIVE ANALYTICS AND VISUALIZATION SYSTEM ON A POWER BI DASHBOARD USING AN INTEGRATED MACHINE LEARNING MODEL: A CASE STUDY OF ADMISSIONS DATA, FACULTY OF SCIENCE, UBON RATCHATHANI UNIVERSITY
Keywords:
Power BI Dashboard, Machine Learning, Predictive analytics, VisualizationAbstract
This research aimed to design and develop a predictive analytics and data visualization system on a Power BI dashboard using an integrated machine learning model, and to investigate user satisfaction with the system. The resulting system consists of six interactive and dynamic dashboards: admissions statistics, admission confirmations, planned versus actual applications, regional distribution of confirmed applicants, trend forecasting using a linear regression model, and analysis of major selection using a random forest model. A key feature of the system is its integration of predictive analytics through machine learning with interactive dashboards to support strategic decision-making. The overall user satisfaction was rated as high, with a mean score of 4.38 and a standard deviation of 0.58, indicating that users found the system both beneficial and appropriate. Furthermore, the performance evaluation of the machine learning models revealed that the linear regression model for forecasting admission numbers achieved an overall Mean Absolute Error (MAE) of 1.11 persons. Meanwhile, the random forest model for major classification achieved an accuracy of 71.8%. These results demonstrate the system's potential to effectively support strategic decision-making.
References
Breiman L. Random forests. Machine Learning. 2001;45(1):5–32.
Ezhilarasi, Dr. T., & S, J. M. (2024). A Study on Implementation of Power Bi Dashboards to Streamline Business Processes. International Journal for Research in Applied Science and Engineering Technology, 12(7), 1548–1551.
Hanifah, S., Akbar, F., & Santi, R. P. (2022). Implementasi Business Intelligence dan Prediksi Menggunakan Regresi Linear pada Data Penjualan dan Breakage di PT XYZ. Jurnal Nasional Teknologi Dan Sistem Informasi, 8(3), 144–152.
Kim, J., Lee, J., Kim, D., Choi, C., Lee, M., & Kim, H. S. (2019). Developing a Prediction Model (Heavy Rain Damage Occurrence Probability) Based on Machine Learning. Journal of the Korean Society of Hazard Mitigation, 19(6), 115–127.
Ladeira, P. P., de Lima, L. M., & Krohling, R. A. (2022). A visualization tool for data analysis on higher education dropout: a case study at UFES (arXiv:2201.12637v1).
Lopes, M. R. (2023). Transformando dados em informações: a ferramenta Power BI e a elaboração de Dashboard sobre o corpo discente da FCTE – Faculdade de Ciências, Tecnologia e Educação da UNESP, Câmpus de Ourinhos.
Santhosh Kumar, B. (2023). Introductory Chapter: Data Integrity and Data Governance. IntechOpen. doi: 10.5772/intechopen.110399
Schonlau, M., & Zou, R. Y. (2020). The random forest algorithm for statistical learning. The Stata Journal: Promoting Communications on Statistics and Stata, 20(1), 3-29.
Shreyas, S. (2021). Design and Development of IIoT Dashboard for Overall Equipment Effectiveness Monitoring of CNC Machine Tools. International Journal for Research in Applied Science and Engineering Technology, 9(12), 1603–1612.
Vemula, S. R., & Moraes, M. (2024). Learning Analytics Dashboards for Advisors — A Systematic Literature Review (arXiv:2402.01671).
สุกัญญา ประมงค์กิจ. (2562) การวิเคราะห์ข้อมูลของผู้สมัครที่เข้าศึกษาต่อระดับปริญญาตรี มหาวิทยาลัยบูรพา ด้วยระบบ TCAS โดยใช้การวิเคราะห์เชิงสถิติ (รายงานการวิจัย). สำนักคอมพิวเตอร์ มหาวิทยาลัยบูรพา.
สำนักข่าวอินโฟเควสท์. (2566). มหาวิทยาลัยไทยเจอปัญหาขาดคนเรียน ผู้เชี่ยวชาญชี้อัตราเกิดต่ำเป็นเหตุ. สืบค้นเมื่อ 10 ธันวาคม 2568, จาก https://www.infoquest.co.th/2023/313112#:~:text=200
