A Methodology for Neural Spatial Interaction Modeling

Fischer, Manfred M. and Reismann, Martin (2002): A Methodology for Neural Spatial Interaction Modeling. Published in: Geographical Analysis , Vol. 34, No. 3 (2002): pp. 207-228.

Abstract

This paper attempts to develop a mathematically rigid and unified framework for neural spatial interaction modeling. Families of classical neural network models, but also less classical ones such as product unit neural network ones are considered for the cases of unconstrained and singly constrained spatial interaction flows. Current practice appears to suffer from least squares and normality assumptions that ignore the true integer nature of the flows and approximate a discrete-valued process by an almost certainly misrepresentative continuous distribution. To overcome this deficiency we suggest a more suitable estimation approach, maximum likelihood estimation under more realistic distributional assumptions of Poisson processes, and utilize a global search procedure, called Alopex, to solve the maximum likelihood estimation problem. To identify the transition from underfitting to overfitting we split the data into training, internal validation and test sets. The bootstrapping pairs approach with replacement is adopted to combine the purity of data splitting with the power of a resampling procedure to overcome the generally neglected issue of fixed data splitting and the problem of scarce data. In addition, the approach has power to provide a better statistical picture of the prediction variability, Finally, a benchmark comparison against the classical gravity models illustrates the superiority of both, the unconstrained and the origin constrained neural network model versions in terms of generalization performance measured by Kullback and Leibler’s information criterion.

• Item Type: MPRA Paper
• Language: English
• Keywords: n.a.
• Subjects: C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics

References

Bergkvist, E. (2000). “Forecasting Interregional Freight Flows by Gravity Models.” Jahrbuch für Regionalwissenschaft 20, 133-48.

Bergkvist, E. and L. Westin (1997). Estimation of Gravity Models by OLS Estimation, NLS Estimation, Poisson and Neural Network Specifications. CERUM Regional Dimensions, Working Paper No. 6.

Bia, A. (2000). A Study of Possible Improvements to the Alopex Training Algorithm. In Proceedings of the VIth Brazilian Symposium on Neural Networks, pp. 125-130. IEEE Computer Society Press.

Black, W.R. (1995). “Spatial Interaction Modelling Using Artificial Neural Networks.” Journal of Transport Geography 3(3), 159-66.

Cover, T.M. (1965). “Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition.” IEEE Transactions on Electronic Computers 14, 326-34.

Efron B (1982). The Jackknife, the Bootstrap and Other Resampling Plans. Philadelphia: Society for Industrial and Applied Mathematics.

Fischer, M.M. and S. Gopal (1994). “Artificial Neural Networks: A New Approach to Modelling Interregional Telecommunication Flows.” Journal of Regional Science 34(4), 503-27.

Fischer, M.M. and Y. Leung (1998). “A Genetic-Algorithms Based Evolutionary Computational Neural Network for Modelling Spatial Interaction Data.” The Annals of Regional Science 32(3), 437-58.

Fischer, M.M. and Y. Leung (eds.) (2001). GeoComputational Modelling: Techniques and Applications. Berlin, Heidelberg and New York: Springer.

Fischer, M.M. and M. Reismann (2000). Evaluating Neural Spatial Interaction Modelling by Bootstrapping. Paper Presented at the 6th World Congress of the Regional Science Association International, Lugano, Switzerland [accepted for publication in Networks and Spatial Economics].

Fischer, M.M., K. Hlavackova-Schindler and M. Reismann (1999). “A Global Search Procedure for Parameter Estimation in Neural Spatial Interaction Modelling.” Papers in Regional Science 78, 119-34.

Fischer, M.M., M. Reismann and K. Hlavackova-Schindler (2001). Neural Network Modelling of Constrained Spatial Interaction Flows, Paper Presented at the 41th Congress of the European Regional Science Association, Zagreb, Croatia [accepted for publication in the Journal of Regional Science].

Fotheringham, A.S. and M.E. O’Kelly (1989). Spatial Interaction Models: Formulations and Applications. Dordrecht, Boston and London: Kluwer.

Giles, C. and T. Maxwell (1987). “Learning, Invariance, and Generalization in High-Order Neural Networks.” Applied Optics 26(23), 4972-8.

Gopal, S. and M.M. Fischer (1993). Neural Net Based Interregional Telephone Traffic Models. In Proceedings of the International Joint Conference on Neural Networks IJCNN 93 Nagoya, Japan, October 25-29, pp. 2041-4.

Gopal, S. and M.M. Fischer (1996). “Learning in Single Hidden-Layer Feedforward Network Models: Backpropagation in a Spatial Interaction Context.” Geographical Analysis 28(1), 38-55.

Kullback, S. and R.A. Leibler (1951). “On Information and Sufficiency.” Annals of Mathematical Statistics 22, 78-86.

Longley, P.A., S.M. Brocks, R. McDonnell and B. MacMillan (eds.) (1998). Geocomputation: A Primer. Chichester: John Wiley.

Mozolin, M., J.-C. Thill and E.L. Usery (2000). “Trip Distribution Forecasting with Multilayer Perceptron Neural Networks: A Critical Evaluation.” Transportation Research B 34, 53-73.

Nijkamp, P., A. Reggiani and T. Tritapepe (1996). Modelling Intra-Urban Transport Flows in Italy. TRACE Discussion Papers TI 96-60/5, Tinbergen Institute, The Netherlands.

Openshaw, S. (1993). “Modelling Spatial Interaction Using a Neural Net.” In Geographic Information Systems, Spatial Modeling, and Policy Evaluation, edited by M.M. Fischer and P. Nijkamp, pp. 147-64. Berlin, Heidelberg and New York: Springer.

Press, W.H., S.A. Teukolsky, W.T. Vetterling and B.P. Flannery (1992). Numerical Recipes in C: The Art of Scientific Computing. Cambridge: University Press.

Reggiani, A. and T. Tritapepe (2000). “Neural Networks and Logit Models Applied to Commuters’ Mobility in the Metropolitan Area of Milan.” In Neural Networks in Transport Applications, edited by V. Himanen, P. Nijkamp and A. Reggiani, pp. 111-29. Aldershot: Ashgate.

Rumelhart, D.E., R. Durbin R., R. Golden and Y. Chauvin (1995). “Backpropagation: The Basic Theory.” In Backpropagation: Theory, Architectures and Applications, edited by Y. Chauvin and D.E. Rumelhart, pp. 1-34. Hillsdale [NJ]: Lawrence Erlbaum Associates.

Thill, J.-C. and M. Mozolin (2000). ”Feedforward Neural Networks for Spatial Interaction: Are they Trustworthy Forecasting Tools?” In Spatial Economic Science: New Frontiers in Theory and Methodology, edited by A. Reggiani, pp. 355-81. Berlin, Heidelberg and New York: Springer.

Young, T.Y. and T.W. Calvert (1974). Classification, Estimation and Pattern Recognition. Amsterdam: Elsevier.