Multi-Intelligent Decision-Making Model for Quality Monitoring in Liberal Arts Talent Training Based on Machine Learning and Optimization Algorithms

Traditional research on the quality monitoring of liberal arts talent training has problems such as a single evaluation dimension, a lack of a dynamic adjustment mechanism and a centralized decision-making body, which lead to limited monitoring results that cannot fully reflect the multi-faceted needs of students, thus affecting the continuous improvement of education quality. To this end, this paper develops a new quality monitoring system based on a multi-intelligent decision-making, which integrates information from multiple parties to achieve dynamic optimization. The system integrates multi-source data such as the student management system and teaching platform, and uses real-time data stream processing technology to monitor and analyze students’ learning progress, classroom participation and other information. Based on this, the system employs a range of machine learning and optimization algorithms. Support vector machine (SVM) is utilized to predict students’ learning patterns and provide a dynamic adjustment basis for teaching by analyzing students’ historical learning data; the random forest algorithm is used to comprehensively evaluate students’ academic performance and ability, improve prediction accuracy through ensemble learning and provide personalized feedback for teachers. Then, the particle swarm optimization (PSO) algorithm is utilized to optimize students’ learning paths and the choice of paths is continuously adjusted according to the learning progress; the genetic algorithm (GA) is utilized to further optimize the choice of learning paths. In addition, the system also combines dimensions such as social adaptability, innovation ability and interdisciplinary literacy and evaluates students’ comprehensive quality by designing modules such as social practice, volunteer service and corporate internship. The experimental results demonstrate that the new system effectively improves the quality of liberal arts talent training. The experimental group’s average final exam score is 82.5 points, which is significantly higher than the 75.4 points of the control group ([Formula: see text]). There is also a significant improvement in innovation ability and interdisciplinary literacy, which effectively promotes the continuous improvement of education quality.