ISSN:1055-615X    

DOI:10.1002/j.1099-1174.1993.tb00030.x

出版商:Wiley    

年代:2014

数据来源: WILEY

摘要:

AbstractRecently there has been an increasing interest in applying inductive learning algorithms to generate rules/patterns from a given example set. While such approaches serve as an efficient way of resolving the knowledge‐acquisition bottleneck, their predictive accuracy, which is the popular measure of performance, varies widely. This paper contrasts major inductive‐learning algorithms and examines their performance with two performance measures: the predictive accuracy and the representation language. Experiments involved three inductive‐learning algorithms and five different managerial tasks in construction project assessment and bankruptcy‐prediction domains. The test results indicate that the model performance is dependent on tasks with an exception of the neural network model and that there is a an effect of group proportion in the example set used to construct the model. The neural network approach presents relatively stable predictive power across different task domains, although it is difficult to interpret its representation.

ISSN:1055-615X    

DOI:10.1002/j.1099-1174.1993.tb00031.x

出版商:Wiley    

年代:2014

数据来源: WILEY

摘要:

AbstractExperts claim that artificial neural network (ANN) technology can outperform standard statistical methods when applied to examine actual financial data. Researchers have used ANNs to analyze bankruptcy prediction, bond rating and the going‐concern problem. Financial firms have employed ANNs commercially to predict commercial bank failures, detect credit card fraud and verify signatures. For accounting and auditing problems, however, application of ANN technology has been limited. Preliminary experiments tested whether an ANN offered improved performance in recognizing material misstatements during the analytical review process of auditing. Four years of audited financial data from a medium‐sized distributor were input as data streams to calibrate the ANN across fifteen financial accounts. Researchers compared a presumed lack of actual errors and certain seeded material errors with signals from the ANN analytical review process to evaluate performance. Results were compared to analyses where financial ratios and regression methods were employed as analytical review techniques. Results tentatively suggest that the ANN method recognized patterns within financial accounts more effectively than did financial ratio and regression methods. ANNs applied as a forecasting tool seem useful for identifying patterns that can indicate potential investigations of a firm's unaudited financial data in the current year.

ISSN:1055-615X    

DOI:10.1002/j.1099-1174.1993.tb00032.x

出版商:Wiley    

年代:2014

数据来源: WILEY

摘要:

AbstractThis paper describes our approach to the problem of automated knowledge acquisition from large databases of examples using an information‐theoretic approach. Our previous research has resulted in practical algorithms (ITRULE) for the automatic induction of rules from large example databases. Utilizing these algorithms, the raw data can be transformed into a set of human readable IF THEN rules, thus giving insight into the knowledge hidden within the data. These rules can then be automatically loaded into an expert system shell. Alternatively, they can be used to build a new type of parallel inference system—a rule‐based neural network. This process enables a prototype expert system to be automatically generated and up and running in a matter of minutes, compared with months using a manual knowledge‐acquisition approach. The resulting expert system can then be used as a sophisticated search and analysis tool to query the original database capable of reasoning with uncertain and incomplete data.

ISSN:1055-615X    

DOI:10.1002/j.1099-1174.1993.tb00033.x

出版商:Wiley    

年代:2014

数据来源: WILEY

摘要:

AbstractThis paper investigates the effectiveness of a multi‐layered neural network as a tool for forecasting in a managerial time‐series setting. To handle noisy data of limited length we adopted two different neural network approaches. First, the neural network is used as a pattern classifier to automate the ARMA model‐identification process. We tested the performance of multi‐layered neural networks with two statistical feature extractors: ACF/PACF and ESACF. We found that ESACF provides better performance, although the noise in ESACF patterns still caused the classification performance to deteriorate. Therefore we adopted the noise‐filtering network as a preprocessor to the pattern‐classification network, and were able to achieve an average of about 89% classification accuracy. Second, the neural network is used as a tool for function approximation and prediction. To alleviate the overfitting problem we adopted the structure of minimal networks and recurrent networks. The experiment with three real‐world time series showed that the prediction by Elman's recurrent network outperformed those by the ARMA model and other structures of multi‐layered neural networks, especially when the time series contained significant noise.

ISSN:1055-615X    

DOI:10.1002/j.1099-1174.1993.tb00034.x

出版商:Wiley    

年代:2014

数据来源: WILEY