In this study, the effectiveness of classical regression models to forecast the indicator of mass accumulation of waste was investigated. The economic and infrastructural variables were used as explanatory variables. The conducted studies show that applying regression models can produce forecasting models generating errors at an acceptable level although only for the municipalities of urban and urban-rural administrative type. For the models where the following were selected as explanatory variables: income indicator, mean number of persons living in a residential building, proportion of arable land in the structure of land use, percentage of buildings in the municipality covered by the waste collection scheme, and the functional type of municipality, the error in the forecast obtained for the test set amounted to 12%–14%. Using the same set of explanatory variables for the rural municipalities caused the models to display forecasting errors for the test set ranging from 35% to 50%. Also, applying another combination of input variables gathered in the course of the studies did not result in developing models of better quality. Therefore, further studies are necessary in the search for more effective methods or other variables describing the mass waste accumulation indicator in rural municipalities.
Citation rules
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.