面向财经类高校的数据挖掘课程,针对专业教学与价值引领割裂的问题,构建“知识点—思政点”映射与“四维目标”（知识、能力、素质、价值）教学方案。研究基于两班教学实践与数据证据,采用混合式教学、案例驱动与项目化评价等方法,形成“知识点映射—案例引导—价值升华”的实施路径。以会计学2023-3/4两个班级为样本,量化对比总评均值、优良率与标准差,并辅以学生教学质量评价的多维指标分析。优良率与总体满意度显著提升,学生在数据诚信、社会责任与科技伦理等维度的感知增强;同时发现班级差异与思政融入自然度不足等问题。研究提出基于财经情境的案例库建设、互动式课堂组织与“三维评价”（知识—能力—价值）优化建议,为数据挖掘课程的思政融入与教学提质提供可复制的路径与证据。

For data mining courses in finance and economics universities, this study addresses the disconnection between professional teaching and value-oriented education by constructing a “knowledge point-ideological element” mapping and a "four-dimension" teaching scheme covering knowledge, competence, quality, and values. Based on teaching practices and data evidence from two classes, a blended teaching approach integrating case-driven learning and project-based evaluation is adopted to establish an implementation path of "knowledge mapping - case guidance - value enhancement". Using Accounting majors from classes 2023-3 and 2023-4 as samples, the study quantitatively compares overall scores, excellence rates, and standard deviations, supplemented by multidimensional indicators from teaching quality evaluations. The findings indicate significant improvements in excellence rates and overall satisfaction, with enhanced student awareness in data integrity, social responsibility, and technological ethics. However, issues such as class differences and insufficient natural integration of ideological elements are also observed. The study proposes constructing a case library based on financial contexts, adopting interactive classroom organization, and optimizing a "three-dimension evaluation" system (knowledge - competence - values), thereby providing a replicable path and evidence for integrating ideological education into data mining courses and improving teaching quality.