分布式强化学习算法在异常财务数据分析中的应用

Application of distributed reinforcement learning algorithm in abnormal financial data analysis

针对现代财务数据分析智能化的需求,文中对分布式强化学习理论进行了研究,构建了智能化的财务数据预警模型。该模型基于中央强化学习体系结构,使用多个执行模块增强单智能体强化学习算法的运算与泛化能力;在强化学习算法的选择上,引入了瞬时差分算法。该算法可以在学习中同步之前迭代状态的经验,且不依赖于最终的预测值,大幅度节约了存储开销;在财务数据分析指标体系的建立上,文中综合考虑了企业的运营、发展、偿债等多个方面的能力,保证了指标体系的完整性与合理性。为了评估算法的性能,文中以真实的财务数据作为样本,使用BP神经网络进行对比实验。测试结果表明,该模型的识别正确率在各个实验场景下均优于BP神经网络,其中实验三的识别正确率提升了4.6%。

In response to the needs of modern financial data analysis and intelligence,this paper studies distributed reinforcement learning theory and builds an intelligent financial data early warning model.The model is based on the central reinforcement learning architecture and uses multiple execution modules to enhance the calculation and generalization capabilities of the single agent reinforcement learning algorithm;in the selection of reinforcement learning algorithms,this paper introduces the instantaneous difference algorithm,which can be used in The experience of the previous iteration state in the synchronization does not depend on the final predicted value,which greatly saves storage costs;in the establishment of the financial data analysis index system,this article comprehensively considers the capabilities of the company’s operations,development,and debt repayment.To ensure the integrity and rationality of the index system.In order to evaluate the performance of the algorithm,this paper takes real financial data as a sample and uses BP neural network to conduct comparative experiments.The test results show that the recognition accuracy of this model is better than BP neural network in various experimental scenarios.Among them,in experiment 3,the recognition accuracy rate increased by 4.6%.