Challenges in determining attributes to generate models for estimation of residential water consumption based on consumer data

Abstract

Estimation of residential water consumption is not an easy task and can be considered as very challenging. Estimation conducted by water suppliers based on per capita consumption (PCC) has been found to vary significantly. Environmental, social and economic factors are identified in contributing to the high variation of domestic water consumption estimation. Hence, estimation methods based on data on per capita consumption may not be the best available methods to provide accurate estimation of residential water consumption. Therefore, it is timely for the development of new alternative methods that can provide better estimation of residential water consumption. This paper investigates the challenges in determining attributes that are essential in generation of prediction models for estimating domestic water consumption using consumer data. A case study is presented followed by discussion on the main issues and challenges in determining attributes for the estimation of water consumption.