Research on Student Performance Prediction Based on SVM Optimized by Hybrid SSA.

Saved in:

Bibliographic Details
Title:	Research on Student Performance Prediction Based on SVM Optimized by Hybrid SSA.
Authors:	Xiaoling Guo¹ 175666832@qq.com, Rui Wang¹ 33403408@qq.com, Xinghua Sun² 1030704295@qq.com, Qiyue Zhang³ 3205735627@qq.com
Source:	IAENG International Journal of Computer Science. Jul2025, Vol. 52 Issue 7, p2256-2266. 11p.
Subjects:	Random numbers, Kernel functions, Poisson distribution, Sine function, Gaussian distribution
Abstract:	A student performance prediction model based on support vector machine optimized by the hybrid sparrow search algorithm is proposed. Firstly, the basic Sparrow Search Algorithm is enhanced through hybrid improvements. During the discovery search process, levy flight and a golden sine function strategy are introduced to expand the search area for discoverers. Additionally, a t-distribution perturbation strategy is incorporated to adjust the position of discoverers, thereby enhancing both flexibility and effectiveness. In the warning search phase, a normally distributed random number is utilized. The variance of this normal distribution decreases progressively with population size, which enhances the algorithm's local development capability. Simultaneously, a random number following Poisson distribution is introduced, its expected value and variance increase with iterations to bolster global search ability. Subsequently, the hybrid improved algorithm is employed to optimize parameters of support vector machine aimed at determining the optimal combination of penalty factor and kernel function. This established student performance prediction model is applied for forecasting student outcomes. Final conclusions indicate that compared to traditional SVM model, Neural Network and SSA-SVM algorithm, the HSSA-SVM algorithm significantly improves accuracy and precision in predicting student performance, providing decision-making basis for teacher teaching and student learning behavior. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	A student performance prediction model based on support vector machine optimized by the hybrid sparrow search algorithm is proposed. Firstly, the basic Sparrow Search Algorithm is enhanced through hybrid improvements. During the discovery search process, levy flight and a golden sine function strategy are introduced to expand the search area for discoverers. Additionally, a t-distribution perturbation strategy is incorporated to adjust the position of discoverers, thereby enhancing both flexibility and effectiveness. In the warning search phase, a normally distributed random number is utilized. The variance of this normal distribution decreases progressively with population size, which enhances the algorithm's local development capability. Simultaneously, a random number following Poisson distribution is introduced, its expected value and variance increase with iterations to bolster global search ability. Subsequently, the hybrid improved algorithm is employed to optimize parameters of support vector machine aimed at determining the optimal combination of penalty factor and kernel function. This established student performance prediction model is applied for forecasting student outcomes. Final conclusions indicate that compared to traditional SVM model, Neural Network and SSA-SVM algorithm, the HSSA-SVM algorithm significantly improves accuracy and precision in predicting student performance, providing decision-making basis for teacher teaching and student learning behavior. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X