Abstract
Rolling credit facilities secured on trade debt present a risk of financial loss to a lender; their client may defraud them e.g. by presenting fictitious debt. Attempts to minimise losses due to this risk involve the lender in detection and mitigation activities which are expensive in terms of staff cost, and may be inconsistently performed. This paper explores the possibility of reducing both the cost of risk management, and the percentage of loan monies lost, by means of the introduction of Artificial Intelligence support for these risk management activities.
A data sample drawn from a lending organisation’s operational databases is analysed by decision tree induction, in order to identify case features associated with instances of loss. A k-nearest neighbour algorithm is then devised, using these features both to rank cases in order of risk, and to enable case-based reasoning support to the formulation of a risk mitigation plan.
A proposal is presented, for the trial implementation of the risk management support tools which have been created. This proposal provides for the critical evaluation and assessment of these tools, both against each other and against the status quo.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Refnes, A. (Ed.) Neural Networks in Financial Engineering: Proceedings of the Third International Conference on Neural Networks in the Capital Markets, World Scientific.
Alici, Y. (1996) “Neural Networks in Corporate Failure Prediction: The UK Experience” in Refines A. (Ed.) Neural Networks in Financial Engineering: Proceedings of the Third International Conference on Neural Networks in the Capital Markets, World Scientific.
Kerling, M. (1996) “Corporate Distress Diagnosis — An International Comparison” in Refnes A. (Ed.) Neural Networks in Financial Engineering: Proceedings of the Third International Conference on Neural Networks in the Capital Markets, World Scientific.
Tyree, E.W. and Long, J.A. (1996) “Assessing Financial Distress with Probabilistic Neural Networks” in Refnes A. (Ed.) Neural Networks in Financial Engineering: Proceedings of the Third International Conference on Neural Networks in the Capital Markets, World Scientific.
Land, L. (1995) KBS Usage: Benefits, Experience and Lessons Learned, McGraw Hill.
Elliott, J. and Curet, 0. (1998) “Invoice Discounting — A Strategic Analysis Using Case-Based Reasoning” in Milne, R., Macintosh, A. and Bramer, M. (Eds.) Applications and Innovations in Expert Systems VI, Springer-Verlag, London.
Watson, I. (1998) “Is CBR a Technology or a Methodology?” in Miles R., Moulton M. and Bramer M. (Eds.) Research and Development in Expert Systems XV, Springer-Verlag, London.
McSherry, D. (1998) “Strategic Induction of Decision Trees” in Miles R., Moulton M. and Bramer M. (Eds.) Research and Development in Expert Systems XV, Springer-Verlag, London.
Basden, A. (1998) “Coping with Poorly Understood Domains. The Example of Internet Trust” in Miles R., Moulton M. and Bramer M. (Eds.) Research and Development in Expert Systems XV, Springer-Verlag, London.
Aamodt, A. and Plaza, E. (1994) “Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches” in AI Communications, 7 (i), 39–59.
Watson, I. (1997) “Applying Case-Based Reasoning: Techniques for Enterprise Systems”, Morgan Kaufmann, California
Schaffer, C. (1993) “Selecting a Classification Method by Cross-Validation” in Machine Learning, 13, 135–143 (1993) Kluwer Academic Publishers.
Cupit, J. and Shadbolt, N. (1996) “Knowledge Discovery in Databases: Exploiting Knowledge-Level Redescription” in Proceedings of European Knowledge Acquisition Workshop ‘86, Lecture Notes in Artificial Intelligence 1076, Springer-Verlag, London.
Murphy, P.M. and Aha, D. “UCI Repository of Machine Learning Databases”, Technical Report, University of California, Irvine.
Tumey, P. (1995) “Technical Note: Bias and the Quantification of Stability” in Machine Learning, 20, 23–33 (1995), Kluwer Academic Publishers.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag London
About this paper
Cite this paper
Dalton, S. (2000). Applied Artificial Intelligence: A risk management problem in trade finance. In: Ellis, R., Moulton, M., Coenen, F. (eds) Applications and Innovations in Intelligent Systems VII. Springer, London. https://doi.org/10.1007/978-1-4471-0465-0_15
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0465-0_15
Publisher Name: Springer, London
Print ISBN: 978-1-85233-230-3
Online ISBN: 978-1-4471-0465-0
eBook Packages: Springer Book Archive