Abstract
Neural nets of the multilayer perceptron (MLP) type possess excellent approximation and forecasting capabilities as many empirical business studies demonstrate. On the other hand, MLPs are often criticized for their black box character because as a rule no single parameter of a MLP indicates the direction of the effect of any predictor. By this property MLPs differ from (general) linear models. We distinguish MLPs for regression analysis, market share analysis and choice modeling. We suggest two different interpretation aids allowing to gain insight into predictors’ effects which both require that parameters of the MLP have already been estimated.
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
AGRAWAL, D. and SCHORLING, C. (1996): Market Share Forecasting. An Empirical Comparison of Artificial Neural Networks and Multinomial Logit Model. Journal of Retailing, 72, 383–407.
ANDERS, U. und SCZESNY, A. (1998): Prognose von Insolvenzwahrscheinlichkeiten mit Hilfe logistischer neuronaler Netzwerke. Schmalenbachs Zeitschrift für betriebswirtschaftliche Forschung, 892–915.
BAETGE, J. and UTHOFF, C. (1998): Development of a Credit-Standing-Indicator for Companies Based on Financial Statements and Business Information with Backpropagation-Networks. In: G. Bol (Ed.): Risk Measurement, Econometrics and Neural Networks. Physica, Heidelberg, 17–38.
BARRON, A.R. (1993): Universal Approximation Bounds for Superpositions of a Sigmoidal Function. IEEE Transasctions on Information Theory, 39, 930–945.
BISHOP, C.M. (1995): Neural Networks for Pattern Recognition. Clarendon Press, Oxford.
COOPER, L.G. and NAKANISHI, M. (1988): Market-Share Analysis. Kluwer Academic Publishers, Boston.
DONALDSON, R.G. and KAMSTRA, M. (1997): An Artificial Neural Network-GARCH Model for International Stock Return Volatility. Journal of Empirical Finance, 4, 17–46.
GARCIA, R. and GENCAY, R. (2000): Pricing and Hedging Derivative Securities with Neural Networks and a Homogeneity Hint. Journal of Econometrics, 94, 93–115.
GUADAGNI, P.M. and LITTLE, J.D.C. (1983): A Logit Model of Brand Choice Calibrated on Scanner Data. Marketing Science, 2, 203–238.
HANSSENS, D.M., PARSONS, L.J., and SCHULTZ, R.L. (1990): Market Response Models. Econometric and Time Series Analysis. Kluwer Academic Publishers, Boston.
HEIMEL, J.P., HRUSCHKA, H., NATTER, M., and TAUDES, A. (1998): Konnexionistische Kaufakt-und Markenwahlmodelle. Zeitschrift für betriebswirtschaftliche Forschung, 596–613
HORNIK, K., STINCHCOMBE, M., and WHITE, H.(1989): Multilayer Feedforward Networks are Universal Approximators. Neural Networks, 3, 359–366.
HRUSCHKA, H. (1993): Determining Market Response Functions by Neural Network Modeling. A Comparison to Econometric Techniques. European Journal of Operational Research, 66, 27–35.
HRUSCHKA, H. (1996): Marketing-Entscheidungen. Vahlen, München.
HRUSCHKA, H. (1999): Neuronale Netze. In: A. Herrmann and C. Homburg (Eds.): Marktforschung. Gabler, Wiesbaden, 661–683.
HRUSCHKA, H. (2001): An Artificial Neural Net Attraction Model (ANNAM) to Analyze Market Share Effects of Marketing Instruments. Schmalenbach Business Review-zfbf, 27–40.
HRUSCHKA, H. and NATTER, M. (1999): Comparing Performance of Feedforward Neural Nets and K-Means for Cluster-Based Market Segmentation. European Journal of Operational Research, 114, 346–353.
HRUSCHKA, H., FETTES, W., und PROBST, M. (2002): Die Bewährung von Ankerpreismodellen bei der Erklärung der Markenwahl. Zeitschrift für betriebswirtschaftliche Forschung, 426–441.
HRUSCHKA, H., FETTES, W., und PROBST, M. (2004): An Empirical Comparison of the Validity of a Neural Net Based Multinomial Logit Choice Model to Alternative Model Specifications. European Journal of Operational Research, 159, 166–180.
JONES, L.K. (1992): A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit and Neural Network Training Annals of Statistics, 20, 608–613.
LUTHER, R.K. (1998): An Artificial Neural Network Approach to Predicting the Outcome of Chapter 11 Bankruptcy. Journal of Business and Economic Studies, 4, 57–73.
MAZANEC, J.A. (1999): Marketing Applications of Neural Networks. Journal of Retailing and Consumer Services, 6, 182–261.
MCFADDEN, D. (1973): Conditional Logit Analysis of Qualitative Choice Behavior. In: P. Zarembka (Ed.): Frontiers in Econometrics. Academic Press, New York, 105–142.
QI, M. (1999): Nonlinear Predictability of Stock Returns Using Financial and Economic variables. Journal of Business & Economic Statistics, 17, 419–429.
WEST, P.M., BROCKETT, P.L., and GOLDEN, L.L. (1997): A Comparative Analysis of Neural Networks and Statistical Methods for Predicting Consumer Choice. Marketing Science, 16, 370–391.
WINER, R.S. (1988): Behavioral Perspective on Pricing, In: T.M. Devinney (Ed.): Issues in Pricing. Lexington Books, Lexington, MA, 35–57.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin · Heidelberg
About this chapter
Cite this chapter
Hruschka, H. (2005). Interpretation Aids for Multilayer Perceptron Neural Nets. In: Baier, D., Decker, R., Schmidt-Thieme, L. (eds) Data Analysis and Decision Support. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-28397-8_7
Download citation
DOI: https://doi.org/10.1007/3-540-28397-8_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26007-3
Online ISBN: 978-3-540-28397-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)