James V. Hansen

Control and audit of electronic data interchange

Electronic data interchange (EDI) is the movement of information electronically between a buyer and seller for purposes of facilitating a business transaction. EDI represents a powerful application of computer-communications technology. Its value includes such benefits as reduced paperwork, elimination of data entry overheads, improved accuracy, timely information receipt, accelerated cash flow, and reduced inventories. EDI brings with it, however, new and important control considerations. This article discusses, in a non-technical fashion, the control architectures and concerns associated with EDI. Audit considerations in the EDI environment, as well as related audit tools, are also outlined.

Neural networks and traditional time series methods: a synergistic combination in state economic forecasts

Ever since the initial planning for the 1997 Utah legislative session, neural-network forecasting techniques have provided valuable insights for analysts forecasting tax revenues. These revenue estimates are critically important since agency budgets, support for education, and improvements to infrastructure all depend on their accuracy. Underforecasting generates windfalls that concern taxpayers, whereas overforecasting produces budget shortfalls that cause inadequately funded commitments. The pattern finding ability of neural networks gives insightful and alternative views of the seasonal and cyclical components commonly found in economic time series data. Two applications of neural networks to revenue forecasting clearly demonstrate how these models complement traditional time series techniques. In the first, preoccupation with a potential downturn in the economy distracts analysis based on traditional time series methods so that it overlooks an emerging new phenomenon in the data. In this case, neural networks identify the new pattern that then allows modification of the time series models and finally gives more accurate forecasts. In the second application, data structure found by traditional statistical tools allows analysts to provide neural networks with important information that the networks then use to create more accurate models. In summary, for the Utah revenue outlook, the insights that result from a portfolio of forecasts that includes neural networks exceeds the understanding generated from strictly statistical forecasting techniques. In this case, the synergy clearly results in the whole of the portfolio of forecasts being more accurate than the sum of the individual parts.

Marketplace and technology standards for B2B e-commerce: progress, challenges, and the state of the art

We have examined standards required for successful e-commerce (EC) architectures and evaluated the strengths and limitations of current systems that have been developed to support EC. We find that there is an unfilled need for systems that can reliably locate buyers and sellers in electronic marketplaces and also facilitate automated transactions. The notion of a ubiquitous network where loosely coupled buyers and sellers can reliably find each other in real time, evaluate products, negotiate prices, and conduct transactions is not adequately supported by current systems. These findings were based on an analysis of mainline EC architectures: EDI, company Websites, B2B hubs, e-Procurement systems, and Web Services. Limitations of each architecture were identified. Particular attention was given to the strengths and weaknesses of the Web Services architecture, since it may overcome some limitations of the other approaches.

Time Series Prediction With Genetic‐Algorithm Designed Neural Networks: An Empirical Comparison With Modern Statistical Models

Neural networks whose architecture is determined by genetic algorithms outperform autoregressive integrated moving average forecasting models in six different time series examples. Refinements to the autoregressive integrated moving average model improve forecasting performance over standard ordinary least squares estimation by 8% to 13%. In contrast, neural networks achieve dramatic improvements of 10% to 40%. Additionally, neural networks give evidence of detecting patterns in data which remain hidden to the autoregression and moving average models. The consequent forecasting potential of neural networks makes them a very promising addition to the variety of techniques and methodologies used to anticipate future movements in time series.

Genetic search methods in air traffic control

Of primary importance to the efficient operation and profitability of an airline is adherence to its flight schedule. This paper examines that segment of air traffic control, termed traffic management adviser (TMA), which is charged with the complex task of scheduling arriving aircraft to available runways in a manner that minimizes delays and satisfies safety constraints. In particular, we investigate the effectiveness and efficiency of using genetic search methods to support the scheduling decisions made by TMA.Four different genetic search methods are tested on TMA problems suggested by recent work at the NASA Ames Research Center. For problems of realistic size, optimal or near-optimal assignments of aircraft to runways are achieved in real time.

Metafraud: a meta-learning framework for detecting financial fraud

Financial fraud can have serious ramifications for the long-term sustainability of an organization, as well as adverse effects on its employees and investors, and on the economy as a whole. Several of the largest bankruptcies in U.S. history involved firms that engaged in major fraud. Accordingly, there has been considerable emphasis on the development of automated approaches for detecting financial fraud. However, most methods have yielded performance results that are less than ideal. In consequence, financial fraud detection continues as an important challenge for business intelligence technologies. In light of the need for more robust identification methods, we use a design science approach to develop MetaFraud, a novel meta-learning framework for enhanced financial fraud detection. To evaluate the proposed framework, a series of experiments are conducted on a test bed encompassing thousands of legitimate and fraudulent firms. The results reveal that each component of the framework significantly contributes to its overall effectiveness. Additional experiments demonstrate the effectiveness of the meta-learning framework over state-of-the-art financial fraud detection methods. Moreover, the MetaFraud framework generates confidence scores associated with each prediction that can facilitate unprecedented financial fraud detection performance and serve as a useful decision-making aid. The results have important implications for several stakeholder groups, including compliance officers, investors, audit firms, and regulators.

Genetic programming for prevention of cyberterrorism through dynamic and evolving intrusion detection

Because malicious intrusions into critical information infrastructures are essential to the success of cyberterrorists, effective intrusion detection is also essential for defending such infrastructures. Cyberterrorism thrives on the development of new technologies; and, in response, intrusion detection methods must be robust and adaptive, as well as efficient. We hypothesize that genetic programming algorithms can aid in this endeavor. To investigate this proposition, we conducted an experiment using a very large dataset from the 1999 Knowledge Discovery in Database (KDD) Cup data, supplied by the Defense Advanced Research Projects Agency (DARPA) and MITs Lincoln Laboratories. Using machine-coded linear genomes and a homologous crossover operator in genetic programming, promising results were achieved in detecting malicious intrusions. The resulting programs execute in real time, and high levels of accuracy were realized in identifying both positive and negative instances.

Expert systems for decision support in EDP auditing

The complexities of computer auditing have created a need for decision support for the EDP auditor. Traditional statistical techniques have proven valuable; however, there are important qualitative components which must be incorporated in the analysis. More importantly, there is a need for decision aids which not only produce analysis and probability estimates-but are able to explain their analysis and conclusions. Recent developments in artificial intelligence have made possible the development of expert systems which provide these capabilities. In this paper we present the motivation, framework, and development strategy for a decision support system for EDP auditing.

Forecasting and recombining time-series components by using neural networks

Operations and other business decisions often depend on accurate time-series forecasts. These time series usually consist of trend-cycle, seasonal, and irregular components. Existing methodologies attempt to first identify and then extrapolate these components to produce forecasts. The proposed process partners this decomposition procedure with neural network methodologies to combine the strengths of economics, statistics, and machine learning research. Stacked generalization first uses transformations and decomposition to pre-process a time series. Then a time-delay neural network receives the resulting components as inputs. The outputs of this neural network are then input to a backpropagation algorithm that synthesizes the processed components into a single forecast. Genetic algorithms guide the architecture selection for both the time-delay and backpropagation neural networks. The empirical examples used in this study reveal that the combination of transformation, feature extraction, and neural networks through stacked generalization gives more accurate forecasts than classical decomposition or ARIMA models. Scope and Purpose. The research reported in this paper examines two concurrent issues. The first evaluates the performance of neural networks in forecasting time series. The second assesses the use of stacked generalization as a way of refining this process. The methodology is applied to four economic and business time series. Those studying time series and neural networks, particularly in terms of combining tools from the statistical community with neural network technology, will find this paper relevant.

Data mining of time series using stacked generalizers

Abstract Data mining is the search for valuable information in large volumes of data. Finding patterns in time series databases is important to a variety of applications, including stock market trading and budget forecasting. This paper reports on an extension of neural network methods for planning and budgeting in the State of Utah. In particular, historical time series are analyzed using stacked generalization, a methodology devised to aid in developing models that generalize well to future time periods. Stacked generalization is compared to ARIMA and to stand-alone neural networks. The results are consistent and suggest promise for the stacked generalization method in other time series domains.