This paper studies a Markov network model for unbalanced data, aiming to solve the problems of classification bias and insufficient minority class recognition ability of traditional machine learning models in environments with uneven class distribution. By constructing joint probability distribution and conditional dependency, the model can achieve global modeling and reasoning optimization of sample categories. The study introduced marginal probability estimation and weighted loss optimization strategies, combined with regularization constraints and structured reasoning methods, effectively improving the generalization ability and robustness of the model. In the experimental stage, a real credit card fraud detection dataset was selected and compared with models such as logistic regression, support vector machine, random forest and XGBoost. The experimental results show that the Markov network performs well in indicators such as weighted accuracy, F1 score, and AUC-ROC, significantly outperforming traditional classification models, demonstrating its strong decision-making ability and applicability in unbalanced data scenarios. Future research can focus on efficient model training, structural optimization, and deep learning integration in large-scale unbalanced data environments and promote its wide application in practical applications such as financial risk control, medical diagnosis, and intelligent monitoring.

翻译：本文研究了一种面向不平衡数据的马尔可夫网络模型，旨在解决传统机器学习模型在类别分布不均衡环境下存在的分类偏差及少数类识别能力不足的问题。该模型通过构建联合概率分布与条件依赖关系，能够实现样本类别的全局建模与推理优化。研究引入了边际概率估计与加权损失优化策略，结合正则化约束与结构化推理方法，有效提升了模型的泛化能力与鲁棒性。在实验阶段，选取了真实的信用卡欺诈检测数据集，并与逻辑回归、支持向量机、随机森林及XGBoost等模型进行了对比。实验结果表明，该马尔可夫网络在加权准确率、F1分数及AUC-ROC等指标上表现优异，显著优于传统分类模型，展现了其在不平衡数据场景下较强的决策能力与适用性。未来研究可聚焦于大规模不平衡数据环境下的高效模型训练、结构优化及与深度学习的融合，推动其在金融风控、医疗诊断、智能监控等实际应用中的广泛落地。