基于动态机器学习的信用评估模型

Credit Evaluation Model Based on Dynamic Machine Learning

随着计算机技术的发展,利用机器学习算法构建自动化评估模型已经成为金融机构进行信用评估的重要手段。然而,目前信用评估模型仍存在一些问题:信用数据本身存在类别不平衡和高维特征的问题,并且不同的时间下外界环境的改变会影响信用主体的行为,即数据会产生概念漂移现象。为此,文中提出了一个动态的信用评估模型,通过集成学习在新的增量数据上训练基分类器,并对各个基分类器的权重进行动态调整来适应概念漂移,以实现模型的动态更新。当发生概念漂移时,会针对概念漂移的检测结果对高维不平衡的信用数据进行不同形式的均衡化和特征选择。特别地,针对特征选择,文中提出了结合历史代表性样本的增量特征选择算法,该算法能够进行高效准确的特征选择,从而使模型可以同时解决增量信用数据存在的高维不平衡和概念漂移问题。最后,文中选取了真实的增量高维信用数据集,验证了所提算法相比其他主流算法在准确率和效率上的优越性。

With the development of computer technology,using machine learning algorithms to build automated evaluation models has become an important tool to for the financial institutions to conduct credit evaluation.However,currently,the credit evaluation model is still facing challenges:credit data is class-imbalanced and high-dimensional,meanwhile,the behavior of customers can be influenced by the changeable external environment,namely,the concept drift will occur.As a result,this paper proposes a dynamic credit evaluation model,which can achieve the flexible model update by using ensemble learning algorithm to continuously add base classifiers trained on new incremental data,and dynamically adjusting the weight of each base classifier to adapt to concept drift.When concept drift occurs,according to the detection results of concept drift,the model is able to use different forms of equalization and feature selection on credit data.In particular,for feature selection,this paper proposes an incremental feature selection algorithm combining the choice of representative samples that makes the feature selection efficient and accurate,enabling the model to simultaneously process the high-dimensional imbalanced data and adapt the concept drift of incremental credit data.Finally,this paper manages to demonstrate that the proposed dynamic model is more efficient and accurate than other prevailing algorithms on real incremental high-dimensional credit datasets.