Evaluation of quality and generalization processes in neural network sets used to forecast the value of space

• Autorzy: Wisniewski R.
• Języki publikacji: EN

Abstrakty

EN

Forecasting the value of real estate is an essential element that should be taken into account by the investor in the process of financing an investment. A similar situation can be observed in the process of land management. In such cases, the reliability of the model used for real estate value prediction becomes a key issue. The geostatic model is designed to be used for diagnosing the land market system in the past and in the present (at the moment the forecast is generated). It then becomes a prognostic geostatic model used for forecasting. Geostatic models can be developed based on a set of artificial neural networks. A set of neural networks is a set of many trained monolithic neural networks, which are combined into one set to eliminate faults assigned to single network models, as well as to improve generalization capability and resistance. The aim of the present study was to develop and test in practice a set of measures enabling to evaluate the quality of a forecasting model as well as its generalization capability.

Słowa kluczowe

EN

generalization; forecast; quality evaluation; space value; neural network set

• Wydawca: -
• Czasopismo: Electronic Journal of Polish Agricultural Universities. Series: Geodesy and Cartography
• Rocznik: 2006
• Tom: 09
• Numer: 2
• Opis fizyczny: http://www.ejpau.media.pl

Twórcy

autor

Wisniewski R.

• University of Warmia and Mazury in Olsztyn, Olsztyn, Poland

Bibliografia

• 1. Brooks Ch. 2002. Introductory Econometrics for Finance. Cambridge University Press. [in English]
• 2. Gately E. 1999. Sieci neuronowe. Prognozowanie finansowe i projektowanie systemów transakcyjnych. [Neural Networks for Financial Forecasting]. WIG PRESS, Warszawa. [in Polish]
• 3. Grasa A. A. 1989. Econometric Model Selection: A New Approach. Dordrecht: Kluwer Academic Publishers. [in English]
• 4. Lula P. 1999. Jednokierunkowe sieci neuronowe w modelowaniu zjawisk ekonomicznych [Feed-forward Neural Networks in the Modeling of Economic Phenomena]. Wydawnictwo Akademii Ekonomicznej w Krakowie. [in Polish]
• 5. Masters T. 1995. Neural, Novel & Hybrid Algorithms for Time Series Prediction. Wiley, John & Sons. [in English]
• 6. Masters T. 1996. Sieci neuronowe w praktyce. Programowanie w języku C++ [Practical Neural Network Recipes in C++]. Wydawnictwo Naukowo-Techniczne, Warszawa. [in Polish]
• 7. StatSoft, Inc. 2004. STATISTICA (data analysis software system), version 6. www.statsoft.com. [in Polish]
• 8. Wiśniewski R. 1999. Metodyczne i praktyczne aspekty zastosowania sztucznej inteligencji w taksacji powszechnej [Methodic and practice aspects of implementation artificial intelligence in mass appraisal]. PhP thesis. [in Polish]
• 9. Wiśniewski R. 2005. Wpływ redukcji wymiaru przestrzeni danych wejściowych na jakość oraz błędy generalizacji zespołów sieci neuronowych [Influence of reduction input data dimension on the quality and generalization processes in neural network sets]. Materiały V Konferencji CMS’05 Computer Methods and Systems. AGH University of Science and Technology, Jagiellonian University and Cracow University of Technology, str. 319-324. Kraków. [in Polish]
• 10. Wykorzystanie sztucznych sieci neuronowych w modelowaniu ekonomicznym [Use artificial neural networks in economic modelling], red. J. Siedleckiego. 2001. Wydawnictwo Akademii Ekonomicznej im. O. Langego we Wrocławiu, Wrocław. [in Polish]