Research on the Combination Strategy of Marxist Ideology and Ideological and Political Education in Colleges and Universities Based on Data Fusion Modeling

With the rapid development of information technology, ideological education in colleges and universities is facing new challenges and opportunities. To cope with these challenges, this paper adopts a data fusion model to analyze the data related to ideological education in colleges and universities in depth through the weighted average method, Kalman filter method, and decision tree algorithm. The weighted average method is used to synthesize data from different sources to obtain a more accurate assessment of educational effects; the Kalman filter method can update the prediction of educational effects in real-time to provide dynamic support for decision-making, and the decision tree algorithm helps educators understand the potential laws behind the data through visualization and make more scientific educational decisions. This study examines the effects of data-driven educational intervention strategies on students’ motivation and overall performance. Students in the experimental group showed significant improvement in classroom interaction and online learning, with the participation rate in questions and discussions increasing from 70.1 to 92.5 in 10 weeks, the average viewing time of online learning increasing by 23%, and the course completion rate rising from 72% to 96%. Questionnaire feedback showed that the experimental group’s satisfaction rating increased from 3.5 to 4.7, indicating a significant increase in students’ approval of the content. In contrast, the control group, under the traditional teaching mode lacking data-driven interventions, showed limited improvement in learning outcomes, with classroom interaction ratings only slightly increasing from 68.9 to 71.8, and the online learning completion rate remaining at around 73%, indicating the limitations of the traditional mode. Statistical test results show that there is a high correlation between the educational intervention (experimental group) and the improvement of learning achievement (p < 0.01), and the effect value is significant. This provides data support for ideological education reform in higher education and emphasizes the importance of combining data analysis and educational intervention. This study provides a new perspective in the field of education, showing that data-driven interventions can effectively enhance students’ motivation and performance, and have good generalization value.