面向银行业务的交易监控可视化系统设计与实现

来源期刊:中南大学学报(自然科学版)2018年第10期

论文作者:段桂华 任立男 谭荻 王建新

文章页码:2490 - 2498

关键词:交易日志;实时监控;交易量预测;可视化分析

Key words:transaction log; real-time monitoring; trading volume forecasting; visual analysis

摘    要:针对银行日益增长的异构交易系统产生的海量交易日志结构复杂、提取困难、分析效率低以及不能及时发现交易异常等问题,设计与实现一个面向银行业务的交易实时监控系统,并提供交易数据的可视化分析。首先,系统对交易日志中关键共性指标进行采集并结构化存储;然后,通过机器学习方法对交易量进行实时预测,提供交易量异常告警;最后,通过可视化方式对异构交易系统实时监控,并对交易数据提供多角度的可视化分析。研究结果表明:该系统界面美观、交互良好、性能优异,能很好地满足银行工作人员的业务分析需求。

Abstract: Due to the complex structure, difficulty of extraction, low efficiency of analysis and the failure of timely detection of transaction abnormalities caused by the growing heterogeneous bank transaction system, a real-time transaction monitoring system for banking business that provides the visual analysis of transaction data was designed and realized. Firstly, the system collected the key common indicators from the transaction log and stored them in a structured way, and then predicted the volume of transactions through machine learning and provided alerts of abnormal volume, and finally heterogeneous trading systems were monitored in real time through visualization and multi-perspective visual analysis of transaction data were provided. The system has a beautiful interface, good interaction and excellent performance, which can well meet the analyst''''s needs of banking analysis.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号