如何有效满足连续型消费且消费量呈周期性波动的客户需要,是生产供应商急需解决的现实问题。本研究对连续型客户日消费量的时间序列数据,首次利用谱分析方法进行消费量的波动特征分析,再根据客户不同波动指标经过分层聚类分析以及判别分析,构建了判别函数方程。基于WE销售公司在江苏省的用气客户的日消费量数据进行了分析验证,研究发现,客户消费的波动特征可以通过谱分析得出的13项指标进行刻画反映,并根据这些波动指标对广大客户进行分类,以便供应商针对不同波动类别的客户采取不同的调峰手段,为供应商优化调峰方案提供分析基础,特别是根据新用户未来用气波动需求进行判别归类,有利于生产供应商提前主动地采取有效措施解决新用户的消费波动问题。
It is a realistic problem for the production suppliers that how to effectively meet the demand of customers who have continuous consumption and the consumption are cyclically fluctuated. Based on the customers' daily natural gas consumption time series data, the spectral methods are applied to analyze the fluctuation characteristics of consumption. Then, the discriminant function equation is constructed using hierarchical clustering analysis and discriminant analysis according to the volatility indicators. Based on the Jiangsu Province customers' daily consumption data of "WE" natural gas sales company, this paper found that: The fluctuation characteristics can be depicted by 13 indicators derived from spectral methods analysis. The customers can be classified by those fluctuation indicators and adopt different pitch-peaking method for different categories of customers. An analysis foundation for natural gas suppliers optimizing their pitch-peaking project is provided. In addition, this method can be used on new customers' segmentation according to their future natural gas demand fluctuation so that the suppliers can proactively take effective measures to solve the problem of consumption fluctuations of new customers.
[1] Cronin Jr J J, Brady M K, Hult G T M. Assessing the effects of quality, value, and customer satisfaction on consumer behavioral intentions in service environments[J]. Journal of Retailing, 2000,76(2), 193-218.
[2] Subramanian U, Raju J S, Zhang Z J. The strategic value of high-cost customers [J].Management Science, 2014,60(2):494-507.
[3] Bas D V, Jong M D,Modeling CLV: A test of competing models in the insurance industry [J]. Quantitative Marketing & Economics,2007,5(2):163-190.
[4] Brusco M J, Steinley D, Cradit J D, et al. Emergent clustering methods for empirical OM research [J]. Journal of Operations Management,2012,30(6), 454-466.
[5] Rogers D F, Kulkarni S S. Optimal bivariate clustering and a genetic algorithm with an application in cellular manufacturing [J]. European Journal of Operational Research,2005,160(2),423-444.
[6] Han Shuihua, Lu Shuixiu, Leung S C H. Segmentation of telecom customers based on customer value by decision tree model[J]. Expert Systems with Applications,2012,39(4),3964-3973.
[7] Brusco M, Doreian P, Steinley D, Satornino C B.Multi-objective block modeling for social network analysis [J]. Psychometrika, 2013,78(3):498-525.
[8] Day M, Magnan G M, Moeller M M.Evaluating the bases of supplier segmentation: A review and taxonomy [J]. Industrial Marketing Management,2010,39(4),625-639.
[9] Zeng F, Yang Zhilin, Li Yongqiang, et al. Small business industrial buyers' price sensitivity: Do service quality dimensions matter in business markets? [J]. Industrial Marketing Management,2011,40(3): 395-404.
[10] Shankarmahesh M N, Olsen H W, Honeycutt Jr E D.A dominant product-dominant country framework of industrial export segmentation[J]. Industrial Marketing Management, 2005,34(3),203-210.
[11] Liu Ying, Ram S, Lusch R F, et al.Multi-criterion market segmentation: A new model, implementation, and evaluation[J]. Marketing Science,2010,29(5):880-894.
[12] Faure C, Natter M.New metrics for evaluating preference maps[J]. International Journal of Research in Marketing, 2010,27(3),261-270.
[13] Knox G, Eliashberg J. The consumer's rent vs. buy decision in the rentailer[J]. Social Science Electronic Publishing,2008,26(2):125-135.
[14] Rezaei J, Ortt R.Supplier segmentation using fuzzy logic[J].Industrial Marketing Management,2013,42(4),507-517.
[15] Kim S, Fong D K H, Desarbo W S. Model-based segmentation featuring simultaneous segment-level variable selection [J]. Journal of Marketing Research,2012,49(5):725-736.
[16] Kim S, Blanchard S J, Desarbo W S, et al. Implementing managerial constraints in model-based segmentation: Extensions of Kim, Fong, and DeSarbo with an application to heterogeneous perceptions of service quality [J]. Journal of Marketing Research, 2012,50(5): 664-673.
[17] Box G E, Jenkins G M, Reinsel G C. Time series analysis: Forecasting and control[M].New Jersey: John Wiley & Son,2008.
[18] Cryer J D, Chan K S. Time series analysis with applications in R[M]. Berlin:Springer,2008.
[19] Pinsky M A.Introduction to fourier analysis and wavelets[M]. New York:Thomson Learning,2002.
[20] Johnson R A, Wichern D W. Applied multivariate statistical analysis[M]. New Jersey:Pearson Education, 2007.
[21] Trefethen L N. Spectral methods in MATLAB[M]. Beijing: Tsinghua University Press,2000.
