Customer information system data pre-processing with feature selection techniques for non-technical losses prediction in an electricity market

Non-technical losses (NTL) identification and prediction are important tasks for many utilities. Data from customer information system (CIS) can be used for NTL analysis. However, in order to accurately and efficiently perform NTL analysis, the original data from CIS need to be pre-processed before any detailed NTL analysis can be carried out. In this paper, we propose a feature selection based method for CIS data pre-processing in order to extract the most relevant information for further analysis such as clustering and classifications. By removing irrelevant and redundant features, feature selection is an essential step in data mining process in finding optimal subset of features to improve the quality of result by giving faster time processing, higher accuracy and simpler results with fewer features. Detailed feature selection analysis is presented in the paper. Both time-domain and load shape data are compared based on the accuracy, consistency and statistical dependencies between features.

The antecedents and consequences of customer emotions in collective hedonic services: An exploratory study

The investigation of the antecedents that influence positive and negative customer emotions and how these emotions influence service outcomes has not been studied in the context of collective hedonic services. In addition, the possibility of moderating effects has not been explored. This paper reports the findings of a qualitative exploratory study that sought to understand the antecedents and consequences of customer emotions in the context of collective hedonic services. This study involved five focus group interviews of customers that attended sporting, performing arts and popular concert events. The findings have important implications for managers and for managing the service process of collective hedonic services.