Predicting Multi-Type Talented Students in Secondary School Using Semi-Supervised Machine Learning

2025-08-31

AI Summary

Traditional talent identification in secondary education relies heavily on academic performance and manual assessment, leading to delayed interventions and neglect of non-academic potential. To address this, we propose TalentPredictor—a novel multimodal deep learning model that jointly predicts seven talent domains: academic achievement, physical fitness, artistic ability, leadership, volunteer engagement, technical proficiency, and holistic competence. TalentPredictor is the first to integrate Transformer, LSTM, and ANN architectures within a semi-supervised learning framework, leveraging non-traditional educational data—including award records and learning behavioral logs—to enable offline deployment. Evaluated on a dataset of 1,041 secondary students, the model achieves a classification accuracy of 0.908 and an ROC-AUC of 0.908. These results demonstrate significant improvements in early, comprehensive, and scalable talent identification, establishing a new paradigm for personalized educational intervention.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Talent identification plays a critical role in promoting student development. However, traditional approaches often rely on manual processes or focus narrowly on academic achievement, and typically delaying intervention until the higher education stage. This oversight overlooks diverse non-academic talents and misses opportunities for early intervention. To address this gap, this study introduces TalentPredictor, a novel semi-supervised multi-modal neural network that combines Transformer, LSTM, and ANN architectures. This model is designed to predict seven different talent types--academic, sport, art, leadership, service, technology, and others--in secondary school students within an offline educational setting. Drawing on existing offline educational data from 1,041 local secondary students, TalentPredictor overcomes the limitations of traditional talent identification methods. By clustering various award records into talent categories and extracting features from students' diverse learning behaviors, it achieves high prediction accuracy (0.908 classification accuracy, 0.908 ROCAUC). This demonstrates the potential of machine learning to identify diverse talents early in student development.

Problem

• Identifying multiple talent types in secondary students beyond academic achievement
• Overcoming limitations of manual and delayed talent identification methods
• Predicting seven diverse talent categories using educational behavior data

Innovation

• Semi-supervised multi-modal neural network
• Combines Transformer LSTM ANN architectures
• Predicts seven talent types using educational data