LEARNING ANALYTICS FOR IMPROVING EDUCATIONAL OUTCOMES: A DATA- DRIVEN FRAMEWORK FOR ENHANCING STUDENT PERFORMANCE AND ACADEMIC SUCCESS

This study employs a quantitative descriptive-correlational research design to examine the effectiveness of learning analytics in improving educational outcomes. The descriptive component is utilized to assess the current level of learning analytics implementation in educational institutions, while the correlational component is used to determine the relationship between learning analytics implementation and educational outcomes, particularly in terms of academic performance, student engagement, student retention, and learning achievement. This research design is appropriate because it allows for the systematic collection, measurement, and analysis of quantitative data, enabling the researcher to identify patterns, describe existing conditions, and establish the degree of association between the study variables. Furthermore, the findings will serve as the basis for developing a Learning Analytics Educational Improvement Framework (LAEIF) that can support evidence-based decision-making and continuous educational improvement.本研究采用定量描述性-相关性研究设计，以考察学习分析（Learning Analytics）在提升教育成效方面的应用有效性。本研究的描述性维度用于评估教育机构内学习分析的当前实施水平，相关性维度则用于明确学习分析实施与教育成果之间的关联关系，具体涵盖学业表现、学生参与度、学生留存率及学习成就四个方面。该研究设计适配本次研究，因其可实现定量数据的系统化采集、测量与分析，能够帮助研究者识别数据规律、刻画现有现状，并明确研究变量间的关联程度。此外，本研究的成果将作为构建学习分析教育改进框架（Learning Analytics Educational Improvement Framework，LAEIF）的基础，该框架可支撑循证决策与持续性教育优化工作。