Using feature construction to improve the performance of neural networks

Management Science

Volumn 44, Issue 3, 1998, Pages 416-430

  Piramuthu, Selwyn ^a   Ragavan, Harish ^a   Shaw, Michael J ^a  

^a NONE

Author keywords

Feature Construction; Financial Credit Risk Evaluation; Learning Difficulty; Neural Networks

Indexed keywords

ALGORITHMS; FINANCE; LEARNING SYSTEMS; PERFORMANCE; RISK ASSESSMENT;

FEATURE CONSTRUCTION; FINANCIAL CREDIT RISK EVALUATION; LEARNING DIFFICULTY; NEURAL NETWORK ALGORITHM;

NEURAL NETWORKS;

EID: 0032021890     PISSN: 00251909     EISSN: None     Source Type: Journal    
DOI: 10.1287/mnsc.44.3.416     Document Type: Article

References (44)

1. Abdel-Khalik, A. R. and K. M. El-Sheshai, "Information Choice and Utilization in an Experiment on Default Prediction," J. Accounting Res., Autumn (1980), 325-342.
2. Ang, J. and K. Patel, "Bond Rating Methods: Comparison and Validation," J. Finance, 30, 2 (1975), 631-640.
3. Becker, S. and Y. Le Cun, "Improving the Convergence of Back-Propagation Learning with Second-Order Methods," Proc. 1988 Connectionist Models Summer School, Morgan-Kaufman, San Mateo, CA, 1988, 29-37.
4. Breiman, L., J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees, Wadsworth, Belmont, CA, 1984.
5. Business Week, "Where Neural Networks Are Already at Work," November 2 (1992), 136-137.
6. Carter, C. and J. Cartlett, "Assessing Credit Card Applications Using Machine Learning," IEEE Expert, Fall (1987), 71-79.
7. Collins, E., S. Ghosh, and C. Scofield, "An Application of a Multiple Neural Network Learning System to Emulation of Mortgage Underwriting Judgements," IEEE International Conf. on Neural Networks, 2 (1988), IEEE Press, San Diego, CA, 459-466.
8. Currim, I. S., R. J. Meyer, and N. T. Le, "Disaggregate Tree-Structured Modeling of Consumer Choice Data," J. Marketing Res., August (1988), 253-265.
9. Deprit, E., "Implementing Recurrent Back-Propagation on the Connection Machine," Neural Networks, 2 (1989), 295-314.
10. Dutta, S. and S. Shekhar, "Bond Rating: A Non-conservative Application of Neural-Networks," International Joint Conf. on Neural Networks 2 (1988), IEEE Press, San Diego, CA, 443-450.
11. The Economist, "More in a Cockroach's Brain Than Your Computers Dream Of," April 15-21 (1995), 75-77.
12. Fahlman, S. E., "Faster-Learning Variations on Back-Propagation: An Empirical Study," Proc. 1988 Connectionist Models Summer School, Morgan-Kaufman, San Mateo, CA, 1988, 38-51.
13. Fisher, D. H. and K. B. McKusick, "An Empirical Comparison of ID3 and Back-Propagation," Proc. Eleventh IJCAI, Morgan-Kaufman, San Mateo, CA, 1989, 788-793.
14. Hansen, J. V., J. B. McDonald, and J. D. Stice, "An Empirical Test on Two Audit Decision-Making Domains," Decision Sci., May-June, 23, 3 (1992), 708-723.
15. Hinton, G. E., "Learning in Parallel Networks," BYTE, April (1985), 265-273.
16. Hopfield, J. J. and D. Tank, "Computing with Neural Circuits: A Model," Science, 233 (1986), 624-633.
17. Hornik, K., M. Stinchcombe, and H. White, "Multilayer Feedforward Networks Are Universal Approximators," Neural Networks, 2 (1989), 359-366.
18. Kimoto, T., K. Asakawa, M. Yoda, and M. Takeoka, "Stock Market Prediction System with Modular Neural Networks," Proc. International Joint Conf. on Neural Networks, San Diego, CA, IEEE Press, Piscataway, NJ, June 1990, 1.1-1.6.
19. Kung, S. Y., J. Vlontzos, and J. N. Hwang, "VLSI Array Processors for Neural Network Simulation," J. Neural Network Computing (1990), 5-20.
20. Langley, P., J. M. Zytkow, H. A. Simon, and G. L. Bradshaw, "The Search for Regularity: Four Aspects of Scientific Discovery," Machine Learning: An Artificial Intelligence Approach, Vol. II, Morgan Kaufman, Los Altos, CA, 1986, 425-470.
21. Matheus, C. J. and W. E. Hohensee, "Learning in Artificial Neural Systems," Computational Intelligence, 3, 4 (1987), 283-294.
22. _ and L. Rendell, "Constructive Induction in Decision Trees," Proc. Eleventh IJCAI, Morgan-Kaufman, San Mateo, CA, 1989, 645-650.
23. Michaelsen, R. H., "An Expert System for Tax Planning," Expert Systems, October (1984), 149-167.
24. Miller, G. F., P. M. Todd, and S. U. Hegde, "Designing Neural Networks Using Genetic Algorithms," Proc. Third International Conf. on Genetic Algorithms, Morgan-Kaufman, San Mateo, CA, 1989, 379-384.
25. Montana, D. J. and L. Davis, "Training Feedforward Neural Networks Using Genetic Algorithms," Proc. Eleventh International Joint Conf. on Artificial Intelligence, Morgan-Kaufman, San Mateo, CA, 1989, 762-767.
26. Mooney, R., J. Shavlik, G. Towell, and A. Gove, "An Experimental Comparison of Symbolic and Connectionist Learning Algorithms," Proc. Eleventh IJCAI, Morgan-Kaufman, San Mateo, CA, 1989, 775-780.
27. Pagallo, G., "Learning DNF by Decision Trees," Proc. Eleventh IJCAI, Morgan-Kaufman, San Mateo, CA, 1989, 639-644.
28. Parker, D. B., "Optimal Algorithms for Adaptive Networks: Second Order Back-Propagation, Second Order Direct Propagation, and Second Order Hebbian Learning," Proc. IEEE International Conf. on Neural Networks, IEEE Press, San Diego, CA, 1987, 593-600.
29. Quinlan, J. R., "Induction of Decision Trees," Machine Learning, 1, 1 (1986), 81-106.
30. Ragavan, H. and S. Piramuthu, "The Utility of Feature Construction in Back-Propagation," Proc. Twelfth IJCAI, Morgan-Kaufman, San Mateo, CA, 1991, 844-848.
31. _, L. Rendell, M. Shaw, and A. Tessmer, "Complex Concept Acquisition Through Directed Search and Feature Caching, and Practical Results in a Financial Domain," Proc. Thirteenth International Joint Conf. on Artificial Intelligence, Morgan-Kaufman, San Mateo, CA, 1993, 946-951.
32. Rangwala, S. S. and D. A. Dornfeld, "Learning and Optimization of Machine Operations Using Computing Abilities of Neural Networks," IEEE Trans. on Systems, Man, and Cybernetics, 19, 2 (1989), 199-214.
33. Rendell, L. and R. Seshu, "Learning Hard Concepts Through Constructive Induction: Framework and Rationale," Computational Intelligence, 6, 4 (1990), 247-270.
34. Rumelhart, D. E., J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing - Explorations in the Microstructure of Cognition, Volume I: Foundations, MIT Press, Cambridge, MA, 1986.
35. Sejnowski, T. J. and C. M. Rosenberg, "Parallel Networks That Learn to Pronounce English Text," Complex Systems, 1, 1 (1987), 145-168.
36. Shaw, M. J. and J. Gentry, "Inductive Learning for Risk Classification," IEEE Expert, February (1990), 47-53.
37. Singleton, J. C. and A. J. Surkan, "Modelling the Judgement of Bond Rating Agencies: Artificial Intelligence Applied to Finance," 1990 Midwest Finance Association Meeting, Chicago, IL, February 1990.
38. Smith, M., "Loan Underwriting by a Neural Network," Neural Networks, 1 (Suppl. 1) (1988), 468.
39. Tam, K. Y. and M. Y. Kiang, "Managerial Applications of Neural Networks: The Case of Bank Failure Predictions," Management Sci., 38, 7 (1992).
40. Towell, G. G., J. W. Shavlik, and M. O. Noordewier, "Refinement of Approximate Domain Theories by Knowledge-Based Neural Networks," Proc. Eighth National Conf. on Artificial Intelligence, MIT Press, Cambridge, MA, 1990, 861-866.
41. Waltrous, R. L., "Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization," Proc. IEEE International Conf. on Neural Networks, 1987, 619-627.
42. Weiss, S. M. and I. Kapouleas, "An Empirical Comparison of Pattern Recognition, Neural Nets, and Machine Learning Classification Methods," Proc. Eleventh IJCAI, Morgan-Kaufman, San Mateo, CA, 1989, 781-787.
43. Yang, D-S., L. Rendell, and G. Blix, "A Scheme for Feature Construction and a Comparison of Empirical Methods," Proc. Twelfth IJCAI, Sydney, Australia, Morgan-Kaufman, San Mateo, CA, 1991, 699-704.
44. Zahedi, F., Intelligence Systems for Business - Experts Systems with Neural Networks, Wadsworth Publishing Co., CA, 1993.