The Gamma/Weibull Customer Lifetime Model

Abstract

This paper proposes a new customer lifetime model: the Gamma/Weibull distribution (G/W). Similar to the Pareto/NBD model, we propose a G/W/NBD model by combining the G/W distribution with a negative binomial distribution (NBD) and study its properties such as (i) the probability that a customer to be alive at a time point; (ii) the expectation and variance of the number of transactions for a customer during a fixed time period; (iii) the conditional expectation and conditional variance of the number of future transactions for a customer during a fixed time period. Several simulation studies are conducted to investigate the forecasting accuracy and flexibility of the proposed model. A CDNOW data set is analyzed by the proposed model.

Keywords

Customer lifetime / Gamma distribution / Negative binomial distribution / Purchase history / Weibull distribution

References

[1] Schmittlein DC, Morrison DG, Colombo R. Counting your customers: Who are they and what will they do next?. Manag. Sci.. 1987, 33 1 1-24

[2] Fader PS, Hardie BGS, Lee KL. Counting your customers the easy way: an alternative to the Pareto/NBD model. Mark. Sci.. 2005, 24 2 275-284

[3] Bemmaor AC, Glady N. Modeling purchasing behavior with sudden death: a flexible customer lifetime model. Manag. Sci.. 2012, 58 5 1012-1021

[4] Reinartz WJ, Kumar V. On the profitability of long-life customer in a noncontractual setting: an empirical investigation and implications for marketing. J. Mark.. 2000, 64 4 17-35

[5] Jain D, Singh SS. Customer lifetime value research in marketing: a review and future directions. J. Interact. Mark.. 2002, 16 34-46

[6] Reinartz WJ, Kumar V. The impact of customer relationship characteristics on profitable lifetime duration. J. Mark.. 2003, 67 1 77-99

[7] Ho T-H, Park Y-H, Zhou Y-P. Incorporating satisfaction in to customer value analysis: optimal investment in lifetime value. Mark. Sci.. 2006, 25 3 260-277

[8] Jerath K, Fader PS, Hardie BGS. New perspectives on customer death using a generalization of the Pareto/NBD model. Mark. Sci.. 2011, 30 5 866-880

[9] Makoto A. Counting your customers one by one: a hierarchical Bayes extension to the Pareto/NBD model. Mark. Sci.. 2009, 28 3 541-553

[10] Jardine AKS, Anderson PM, Mann DS. Application of the Weibull proportional hazards model to aircraft and marine engine failure date. Qual. Reliab. Eng. Int.. 1987, 3 77-82

[11] Odell PM, Anderson KM, D’Agostino RB. Maximum likelihood estimation for interval-censored data using a Weibull-based accelerated failure time model. Biometrics. 1992, 48 3 951-959

[12] Sewalem, A., G. J. Kistemaker, F. Miglior, B. J. Van Doormaal.: Analysis of the relationship between type traits and functional survival in canadian holstein using a Weibull proportional hazard model. J. Dairy Sci. 87, 3938–3946 (2004)

[13] Casellas J. Bayesian inference in a piecewise Weibull proportional hazards model with unknown change points. J. Anim. Breed. Genet.. 2007, 124 176-184

[14] Carrasco JMF, Ortega EMM, Cordeiro GM. A generalized modified Weibull distribution for lifetime modeling. Comput. Stat. Data Anal.. 2008, 53 450-462

[15] Zhang Q, Hua C, Xu G. A mixture Weibull proportional hazard model for mechanical system failure prediction utilising lifetime and monitoring data. Mech. Syst. Signal Process.. 2014, 43 103-112

[16] Almalki SJ, Nadarajah S. Modifications of the Weibull distribution: a review. Reliab. Eng. Syst. Saf.. 2014, 124 32-55

[17] Sha N, Pan R. Bayesian analysis for step-stress accelerated life testing using Weibull proportional hazard model. Stat Papers. 2014, 55 715-726

[18] Kern EL, Cobuci JA, Costa CN, Ducrocq V. Survival analysis of productive life in Brazilian holstein using a piecewise Weibull proportional hazard model. Livest. Sci.. 2016, 185 89-96

[19] Ehrenberg, A.S.C.: Repeat Buying, North-Holland, Amsterdam (1972)

[20] Morrison DG. Analysis of consumer purchase data: a Bayesian approach. Ind. Manag. Rev.. 1968, 9 31-40

[21] Fader PS, Hardie BGS. Forecasting repeat sales at CDNOW: a case study. Part 2 of 2. Interfaces. 2001, 31 S94-S107

[22] Fader PS, Hardie BGS, Lee KL. RFM and CLV: using iso-value curves for customer base analysis. J. Mark. Res.. 2005, 42 4 415-430

Funding

National Natural Science Foundation of China(11165016)