Abstract Household monthly electricity consumption pattern mining is to discover different energy use patterns of households in a month from their daily electricity consumption data. In this study, we develop an improved fuzzy clustering model for the monthly electricity consumption pattern mining of households. First, the background of clustering and fuzzy c-means clustering is introduced. Then a process model of household electricity consumption pattern mining and an improved fuzzy c-means clustering model are provided. Three key aspects of the improved fuzzy c-means clustering model, namely fuzzifier selection, cluster validation and searching capability optimization, are discussed. Finally, the daily electricity consumption data of 1200 households in Jiangsu Province, China, during a month from December 1, 2014 to December 31, 2014 are used in the experiment. With the proposed model, 938 valid households are successfully divided into four and six groups respectively, and the characteristics of each group are extracted. The results revealed the different electricity consumption patterns of different households and demonstrated the effectiveness of the clustering-based model. The customer segmentation based on consumption pattern mining in electric power industry is of great significance to support the development of personalized and targeted marketing strategies and the improvement of energy efficiency.