A combinatorial model for natural gas industrial customer value portrait based on value assessment and clustering algorithm

Abstract

Frequent geopolitical events have reduced the stability of natural gas supply and caused drastic price fluctuations, which poses a new challenge to the natural gas consumer market. To improve the anti-risk ability of the natural gas industrial market, this study constructs a new customer value portrait framework to discern the industrial customer value based on different types of behavioral features and the emerging trends of the natural gas market. Specifically, we rediscover the value composition of natural gas industrial customers and establish a set of indicators to reflect the customer value in different dimensions with mixed data types. Then, a visualizable customer value classification model has been established by combining Gower’s dissimilarity coefficient with the PAM clustering algorithm. To ensure the accuracy of the clustering results, the optimal number of clusters is determined by gap statistics and elbow point, and the average silhouette method is used to detect the clustering effect as well as used in misclassified sample identification. To verify the applicability of the model, we used a certain amount of natural gas industrial customer data from a large state-owned oil and gas enterprise for application analysis and effectively divided customer value into three groups, demand-serving, demand-potential, and demand-incentive, according to their value characteristics and behavioral features. The results indicate that the framework proposed in this study can reasonably reflect and better characterize natural gas industrial customers’ value with different types of behavioral feature data, which can provide technical support for big data smart natural gas consumer marketing.