论文部分内容阅读
提出了适合于上市公司而建立的基于ANN技术的企业经济综合指标短期预警系统的构建方案.该系统是一个人机相结合的反馈式预警系统,包括危机判定、财务指标预测、预警知识获取和报警四个子系统.该系统将定性分析与定量分析结合起来,既突出人的作用,又充分发挥了人工神经网络的在预测方面的技术,使得两者有机的结合在一起.其中,预警指标预测子系统体现了ANN技术在时间序列预测方面的应用,而知识获取子系统和报警子系统则体现了ANN技术在回归预测方面的应用,两者都有很好的理论基础.同时,该系统建立的程序比较规范,具有普适性,易于操作,比较容易实现.最后,还对该系统进行了实证模拟分析,并与专家意见结果进行了对比,验证了其有效性.
This paper presents a scheme of short-term early-warning system based on ANN technology, which is suitable for listed companies, and it is a feedback early-warning system combining human-machine interaction, including crisis judgment, financial index forecasting, early warning knowledge acquisition and Alarm four subsystems.The system combines qualitative analysis and quantitative analysis, both to highlight the role of people, but also give full play to the artificial neural network in the prediction of the technology, making the two organic combination of which the early warning index forecast The subsystem embodies the application of ANN technology in time series prediction, and the knowledge acquisition subsystem and alarm subsystem embody the application of ANN technology in regression prediction, both of which have a good theoretical basis. At the same time, the system is established Is more general, easier to operate and easier to implement.Finally, the system is also empirically simulated and compared with the results of expert opinion to verify the effectiveness of the system.