Survey and Design of a Comprehensive Module for a Class Scheduling System using SVM

Abstract

An advanced class scheduling system leverages Support Vector Machine (SVM) technology to optimize timetable management in educational institutions. By analyzing factors such as teacher availability, classroom capacity, and student enrolment, the system efficiently allocates resources while preventing scheduling conflicts. The model processes scheduling data to generate well-structured timetables, adapting dynamically to any unforeseen changes. Additionally, automated notifications ensure that teachers and students receive real-time updates regarding their schedules. By reducing manual workload and minimizing errors, this system enhances efficiency, improves communication, and simplifies scheduling.

Introduction

The text explains the use of Support Vector Machines (SVM) for solving complex classification and scheduling problems, particularly in academic timetable optimization. SVM is a supervised machine learning algorithm that finds an optimal hyperplane to separate data into classes, using support vectors that define the decision boundary. It is especially effective for non-linear and high-dimensional data, making it suitable for real-world applications like scheduling.

The literature review highlights that SVM has been widely used for classification tasks such as prediction, performance analysis, and resource optimization in education. However, most existing studies focus on generic datasets or isolated classification problems and do not address real-time scheduling challenges or constraint-based optimization.

The research gap identifies that prior work does not effectively combine SVM with real-time scheduling constraints such as teacher availability, room allocation, and time conflicts. To address this, the proposed system integrates RBF-kernel SVM with Google OR-Tools, where SVM assigns feasibility scores to scheduling options and OR-Tools ensures hard constraints like conflict-free timetables.

The methodology describes a hybrid system where SVM (using SVC with an RBF kernel) evaluates candidate schedules based on multiple features, while OR-Tools performs final optimization. The system is evaluated using standard metrics like accuracy, precision, recall, and F1-score, and considers issues like underfitting and overfitting.

Overall, the proposed approach shifts SVM from a purely predictive model to a hybrid decision-support system for real-time timetable scheduling, improving efficiency, reducing conflicts, and enabling scalable academic resource management.

Conclusion

The conclusion establishes that the proposed SVM-based class scheduling system effectively addresses the challenges associated with manual timetable creation. By automating the allocation of classes, faculty, and resources, the system significantly reduces scheduling conflicts and administrative workload while ensuring optimal utilization of available resources. The integration of machine learning with constraint optimization forms the core strength of the system, as it combines intelligent decision-making with strict viable enforcement.

References

[1] Kumar, A., & Mishra, D. (2025). “Improving Support Vector Machine using Modified Kernel Function”. International Journal of Scientific Research and Modern Technology,4(5), 1-5. [2] Walter Zambrano-Romero, Ciro Rodriguez, Josselyn Pita-Valencia,Walter José Zambrano Romero, “Machine Learning in the Teaching Quality of University Teachers: Systematic Review of the Literature 2014–2024”, February 2025,16(3):181, DOI:10.3390/info16030181 [3] O. Zanevych, Vitaliy Kukharskyy, “Overview of machine learning methods for academic scheduling” October 2024, Electronics and Information Technologies 27(27), DOI:10.30970/eli. 27.8 [4] Quan, Z., Pu, L. “An improved accurate classification method for online education resources based on support vector machine (SVM): Algorithm and experiment.” Educ Inf Technol 28, 8097–8111 (2023). [5] Mustafa Abdullah, D., & Mohsin Abdulazeez, A. (2021). “Machine Learning Applications based on SVM Classification”, Qubahan Academic Journal, 1(2), 81–90. [6] Lijuan Yang, First published: 2021, “Research on the Realization Path of College English Education Based on the SVM Algorithm Model under the Background of Cloud Computing and Wireless Communication.” [7] Jair Cervantes a, Farid Lamont a, Lisbeth Rodríguez-Mazahua b, Asdrubal Lopez c, “A comprehensive survey on support vector machine classification: Applications, challenges and trends”, UAEMEX (Autonomous University of Mexico State), Texcoco, 56259, Mexico, Received 2 June 2019, Revised 24 August 2019, Accepted 1 October 2019, Available online 8 May 2020, Version of Record 24 August 2020.

Copyright

Copyright © 2026 Supriya Sawwashere, Gauri Raju Bhoyar, Kalyani Tayade, Shifa Abdullah Khan, Tanishka Jadhav. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.