• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Cybernetics and Information Technologies, Systems and Applications(CITSA2004) and 10th International Conference on Information Systems Analysis and Synthesis(ISAS2004) vol.3 >The Impact of Neural Network Selection on Audit Cost When Assessing Client Financial Viability
【24h】

The Impact of Neural Network Selection on Audit Cost When Assessing Client Financial Viability

机译：评估客户财务可行性时，神经网络选择对审计成本的影响

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The purpose of this paper is twofold. First, we provide evidence that relying on Type Ⅰ, Type Ⅱ and overall error rates to select a model for analyzing the financial health of audit clients can result in greater costs to auditors than using the alternative approach utilized in this paper. Second, we show that auditors who wish to use an artificial neural network (ANN) as a tool to analyze the financial viability of audit clients need to consider the underlying neural network paradigm before developing a model of financial health in order to minimize audit costs.rnOur results show that a categorical learning neural network minimizes the overall cost associated with the auditor examination of audit client financial health. This ANN outperforms both statistical techniques traditionally used to examine firm financial health, i.e., multivariate discriminant analysis and logit, and other ANN paradigms that may be suitable for forecasting firm financial viability, i.e., backpropagation and probabilistic neural networks. Consequently, auditors who wish to minimize the total costs associated with their audits should use a categorical learning neural network or similar type of ANN when assessing audit client financial health.
机译：本文的目的是双重的。首先，我们提供的证据表明，与使用本文中使用的替代方法相比，依靠Ⅰ类，Ⅱ类和总体错误率来选择一种模型来分析审计客户的财务状况可能会给审计师带来更大的成本。其次，我们表明，希望使用人工神经网络（ANN）作为分析审计客户财务可行性的工具的审计师，在开发财务健康模型以最小化审计成本之前，需要考虑底层的神经网络范式。 rn我们的结果表明，分类学习神经网络使与审计师检查客户财务状况相关的总成本最小化。该ANN优于传统上用来检查公司财务状况的统计技术（即多元判别分析和logit）以及其他适用于预测公司财务生存能力的ANN范例，即反向传播和概率神经网络。因此，希望最小化与审计相关的总成本的审计师在评估审计客户财务状况时应使用分类学习神经网络或类似类型的ANN。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号