Forecast of consumer behaviour based on neural networks models comparison
The aim of this article is comparison of accuracy level of forecasted values of several artificial neural network models. The comparison is performed on datasets of Czech household consumption values. Several statistical models often resolve this task with more or fewer restrictions. In previous wor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mendel University Press
2012-01-01
|
| Series: | Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis |
| Subjects: | |
| Online Access: | https://acta.mendelu.cz/60/2/0437/ |
| _version_ | 1818488704938803200 |
|---|---|
| author | Michael Štencl Ondřej Popelka Jiří Šťastný |
| author_facet | Michael Štencl Ondřej Popelka Jiří Šťastný |
| author_sort | Michael Štencl |
| collection | DOAJ |
| description | The aim of this article is comparison of accuracy level of forecasted values of several artificial neural network models. The comparison is performed on datasets of Czech household consumption values. Several statistical models often resolve this task with more or fewer restrictions. In previous work where models’ input conditions were not so strict and model with missing data was used (the time series didn’t contain many values) we have obtained comparably good results with artificial neural networks. Two views – practical and theoretical, motivate the purpose of this study. Forecasting models for medium term prognosis of the main trends of Czech household consumption is part of the faculty research design grant MSM 6215648904/03/02 (Sub-task 5.3) which defines the practical purpose. Testing of nonlinear autoregressive artificial neural network model compared with feed-forward neural network and radial basis function neural network defines the theoretical purpose. The performance metrics of the models were evaluated using a combination of common error metrics, namely Correlation Coefficient and Mean Square Error, together with the number of epochs and/or main prediction error. |
| first_indexed | 2024-12-10T16:54:37Z |
| format | Article |
| id | doaj.art-b078ad2671f64da1993dbb829595ebfd |
| institution | Directory Open Access Journal |
| issn | 1211-8516 2464-8310 |
| language | English |
| last_indexed | 2024-12-10T16:54:37Z |
| publishDate | 2012-01-01 |
| publisher | Mendel University Press |
| record_format | Article |
| series | Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis |
| spelling | doaj.art-b078ad2671f64da1993dbb829595ebfd2022-12-22T01:40:46ZengMendel University PressActa Universitatis Agriculturae et Silviculturae Mendelianae Brunensis1211-85162464-83102012-01-0160243744210.11118/actaun201260020437Forecast of consumer behaviour based on neural networks models comparisonMichael Štencl0Ondřej Popelka1Jiří Šťastný2Ústav informatiky, Mendelova univerzita v Brně, 613 00 Brno, Česká republikaÚstav informatiky, Mendelova univerzita v Brně, 613 00 Brno, Česká republikaÚstav informatiky, Mendelova univerzita v Brně, 613 00 Brno, Česká republikaThe aim of this article is comparison of accuracy level of forecasted values of several artificial neural network models. The comparison is performed on datasets of Czech household consumption values. Several statistical models often resolve this task with more or fewer restrictions. In previous work where models’ input conditions were not so strict and model with missing data was used (the time series didn’t contain many values) we have obtained comparably good results with artificial neural networks. Two views – practical and theoretical, motivate the purpose of this study. Forecasting models for medium term prognosis of the main trends of Czech household consumption is part of the faculty research design grant MSM 6215648904/03/02 (Sub-task 5.3) which defines the practical purpose. Testing of nonlinear autoregressive artificial neural network model compared with feed-forward neural network and radial basis function neural network defines the theoretical purpose. The performance metrics of the models were evaluated using a combination of common error metrics, namely Correlation Coefficient and Mean Square Error, together with the number of epochs and/or main prediction error.https://acta.mendelu.cz/60/2/0437/artificial neural networksforecasting methodscustomer behaviour |
| spellingShingle | Michael Štencl Ondřej Popelka Jiří Šťastný Forecast of consumer behaviour based on neural networks models comparison Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis artificial neural networks forecasting methods customer behaviour |
| title | Forecast of consumer behaviour based on neural networks models comparison |
| title_full | Forecast of consumer behaviour based on neural networks models comparison |
| title_fullStr | Forecast of consumer behaviour based on neural networks models comparison |
| title_full_unstemmed | Forecast of consumer behaviour based on neural networks models comparison |
| title_short | Forecast of consumer behaviour based on neural networks models comparison |
| title_sort | forecast of consumer behaviour based on neural networks models comparison |
| topic | artificial neural networks forecasting methods customer behaviour |
| url | https://acta.mendelu.cz/60/2/0437/ |
| work_keys_str_mv | AT michaelstencl forecastofconsumerbehaviourbasedonneuralnetworksmodelscomparison AT ondrejpopelka forecastofconsumerbehaviourbasedonneuralnetworksmodelscomparison AT jiristastny forecastofconsumerbehaviourbasedonneuralnetworksmodelscomparison |