Prediction of the efficiency in the water industry: An artificial neural network approach

Abstract

The measurement of efficiency of water utilities has been traditionally carried out using econometric methods or linear programming techniques. Alternatively, in this study a data mining non-parametric method is used, such as an artificial neural network (ANN) approach, to predict the efficiency of several water companies in England and Wales. The further use of a regression tree model allowed us to visualize and quantify the impact of operating characteristics on efficiency. The average efficiency score for the water industry was 0.411. Average scores for water only companies and water and sewerage companies were 0.210 and 0.626, respectively. Only one water company was identified as being fully efficient. This indicates that most of the English and Welsh water companies need to make substantial improvements in their managerial practices to catch-up with the most efficient ones in the industry. Several operating characteristics such as water leakage, water taken from different sources and population density were found to influence efficiency. The percentage of water leakage was identified as the most relevant operational variable influencing the efficiency of water companies. The findings of our study aim to support benchmarking analysis in regulated industries and to get a better insight on what drives efficiency.