基于概念漂移检测的大数据交易过程模型优化方法

通过大数据交易过程模型优化，实现对大数据交易过程的精确建模，对于构建稳定、鲁棒和精确的交易平台至关重要.然而，大数据交易流程随时间而变化，传统的静态模型优化方法无法反映现实流程模型的时态变化特征.为此，本文提出一种基于概念漂移的大数据交易模型优化方法，在概念漂移点检测和定位的基础上，设计大数据交易日志分割算法，演算日志精准分割点，构建具有时变特性的大数据交易分段模型，实现基于日志分割的模型优化.该方法在天元大数据交易平台的应用实践表明，优化模型在拟合度和精确度方面均优于静态模型，对大数据交易演化过程的适配性更强.

Optimization of Big Data Transaction Process Model Based on Concept Drift Detection

Through the optimization of big data transaction process model,the accurate modeling of big data transaction process is realized,which is significant for building a stable,robust and accurate transaction platform.However,the big data transaction process changes over time,and traditional static model optimization methods cannot reflect the characteristics of time-varying changes in real-world process models.For this reason,this paper proposes an optimization approach of big data transaction model.Based on the detection and location of concept drift points,the approach designs a big data transaction log segmentation algorithm and calculates log precise segmentation points to build a large data transaction time-varying segmented model and to realize model optimization.The proposed approach has got used in Tianyuan Big Data Transaction Platform,which shows that the optimization model has an advantage over the static model in fitness,precision and adaptation to the big data transaction process.