James R. Coakley

Artificial neural networks in accounting and finance: modeling issues

This article reviews the literature on artificial neural networks (ANNs) applied to accounting and finance problems and summarizes the ‘suggestions’ from this literature. The first section reviews the basic foundation of ANNs to provide a common basis for further elaboration and suggests criteria that should be used to determine whether the use of an ANN is appropriate. The second section of the paper discusses development of ANN models including: selection of the learning algorithm, choice of the error and transfer functions, specification of the architecture, preparation of the data to match the architecture, and training of the network The final section presents some general guidelines and a brief summary of research progress and open research questions. Copyright

Logistics Organization and the Information System

Information technology is changing the nature of logistics organization. It is reducing the cost of transactions and redefining organizations and their interconnections. This paper examines the impact through the concept of transaction costs. This leads to discussion of current trends toward electronic integration and outsourcing of logistics services. The use of advanced information technology is redefining the role of the logistics manager.

The Analytic Hierarchy Process: A Tutorial for Use in Prioritizing Forest Road Investments to Minimize Environmental Effects

Abstract The prioritization of road maintenance projects is an important forest engineering task due to limited budgets and competing investment needs. Large investments are made each year to maintain and upgrade forest road networks to meet economic and environmental goals. Many models and guidelines are available for single-criteria analysis of forest roads, however we have found no method for multi-criteria analysis. Additionally, even single criteria approaches often rely on expert judgment to inform models of user preferences and priorities. These preferences are used to make tradeoffs between alternatives that contain data that are physical and biological, quantitative and qualitative, and measured on many different scales. The Analytic Hierarchy Process (AHP) has the potential to provide a consistent approach to the ranking of forest road investments based on multiple criteria. AHP was specifically developed to provide a consistent, quantifiable approach to problems involving multi-criteria analysis, but it has not been applied to road management. AHP is composed of four steps: the hierarchical decomposition of a problem into a goal, objectives, and sub-objectives; the use of a pairwise comparison technique to determine user preferences; the scaling of attribute values for each of the alternatives; and the ranking of alternatives. The road investment problem differs from traditional AHP applications in that potentially thousands of alternatives are compared at one time. We discuss the AHP methodology including the foundations, assumptions, and potential for use in prioritizing forest road investments to meet economic and environmental goals, drawing from an example from the Oregon State University College Forests.

Using pattern analysis methods to supplement attention directing analytical procedures

Abstract How might the application of analytical procedures be improved given the inherent shortcomings of traditional analytic techniques and the apparent difficulties auditors have in combining all critical cues when evaluating the results of the analytical procedures? This research attempts to improve analytical methods by applying a new technology, Artificial Neural Networks (ANNs), to perform pattern recognition of the investigation signals generated by analytical procedures. ANNs, a type of artificial intelligence technology, are able to recognize patterns in data even when the data is noisy, ambiguous, distorted or variable. Four years of audited financial data from a medium-sized distributor were used to calculate five commonly applied financial ratios. The performance of these ratios, applied independently and in combinations, was evaluated using a presumed lack of actual errors and certain seeded material errors. The ANN method evaluated the information content of the combinations of financial ratios using an entropy cost function derived from information theory. This exploratory study suggests that the use of an ANN to analyze patterns of related fluctuations across numerous financial ratios provides a more reliable indication of the presence of material errors than either traditional analytic procedures or pattern analysis, as well as providing insight to the plausible causes of the error. Preliminary results suggest that the use of pattern analysis methods as a supplement to traditional analytical procedures will offer improved performance in recognizing material misstatements within the financial accounts.

Using a Computer-Based Version of the Beer Game: Lessons Learned:

Multiperson board games are being used in both business and academia to enhance education and training. These games compress time and space to enable the players to experience the consequences of their decisions. The dynamic interactions between multiple players create a complex and unpredictable business scenario that is difficult to replicate with other exercises. However, most board games are difficult to administer and require the players to concentrate on detailed rules and procedures in addition to the primary decisions required at each move. This article describes the lessons learned from the use of a computer-based implementation of a popular business board game: the Beer Game.