Analysis and Prediction of Universities’ Buildings’ Renovation Costs Using a Regression Model

The aim of this article is to create a model, based on regression analysis, that will calculate the predicted annual renovation costs in educational buildings. To find the correlation between different variables and the renovation costs, two phases of analysis were distinguished. The aim of the first phase was to find the correlations with different variables and the renovation costs on a selected, small package of data. The second phase was more detailed, the final database was wider, and the variables’ correlations based on the findings achieved in the first phase were used. In the second phase, 55 buildings, located in Cracow (Poland) and Lodz (Poland), have been analyzed and the costs of renovation were compared. The results of the research showed that maintenance costs for educational buildings can be predicted in the coming years by knowing the usable area and the period since the last major renovation until today, which needs to be expressed in years. To predict future cost expenditure, a cumulative year-on-year bivariate linear regression model was calculated. The trend line equation has been determined, which allows to predict the renovation costs in the accurate short term. The developed model can be used by owners and managers of public buildings in the proper planning of expenses related to the maintenance of facilities.