, Volume 77, Issue 1, pp 19–42 | Cite as

Assessing the influence of marketing activities on customer behaviors: a dynamic clustering approach

  • Antonello MaruottiEmail author
  • Jan Bulla
  • Tanya Mark


This research presents an application of a mixed hidden Markov model to data from a multichannel retailer. The objective of this research is to develop a dynamic model of channel choice and purchasing behavior that accounts for consumer heterogeneity, changes in behavior over time, and the influence of marketing activities on managerially relevant consumer behaviors. The model allows marketers to reduce their direct mailing spending while controlling for potential negative effects on their sales. More specifically, we develop a model that captures the evolution of a consumer’s buying behavior over time across retail channels and compare our model to several other approaches. We find our model outperforms existing models including standard latent class models, including those belonging to the latent transition analysis framework. Using several criteria of model performance and fit, we find a hierarchical clustering structure in the data. Each cluster responds differentially to marketing activities. We find catalogs, on average, are an effective tool to keep consumers active whereas retail promotions are more likely to influence consumers to migrate to another channel.


Mixed hidden Markov models Omni-channel retailing Marketing promotions Customer classification Latent transition analysis Dynamic mixture models 


Supplementary material

40300_2019_150_MOESM1_ESM.pdf (33 kb)
Supplementary material 1 (pdf 32 KB)


  1. 1.
    Abhishek, V., Fader, P., Hosanagar, K.: The Long Road to Online Conversion: A Model of Multi-channel Attribution. working paper (2011)
  2. 2.
    Ailawadi, K.L., Neslin, S.A.: The effect of promotion on consumption: buying more and using it faster. J. Mark. Res. 35(3), 390–398 (1998)Google Scholar
  3. 3.
    Aitkin, M.: A general maximum likelihood analysis of overdispersion in generalized linear models. Stat. Comput. 6(3), 251–262 (1996)MathSciNetGoogle Scholar
  4. 4.
    Altman, R.M.: Mixed hidden markov models: an extension of the hidden Markov model to the longitudinal data setting. J. Am. Stat. Assoc. 102(477), 201–210 (2007)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Ansari, A., Mela, C.F., Neslin, S.A.: Customer channel migration. J. Mark. Res. 45(1), 60–76 (2008)Google Scholar
  6. 6.
    Ascarza, E., Hardie, B.: A joint model of usage and churn in contractual settings. Mark. Sci. 32(4), 570–590 (2013)Google Scholar
  7. 7.
    Bartolucci, F., Farcomeni, A., Pennoni, F.: Latent Markov models for longitudinal data. CRC Press, Boca Raton (2013)zbMATHGoogle Scholar
  8. 8.
    Bartolucci, F., Farcomeni, A., Pennoni, F.: Latent Markov models: a review of a general framework for the analysis of longitudinal data with covariates. Test 23(3), 433–465 (2014)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Bartolucci, F., Montanari, G.E., Pandolfi, S.: Three-step estimation of latent Markov models with covariates. Comput. Stat. Data Anal. 83, 287–301 (2015).
  10. 10.
    Bartolucci, F., Pennoni, F., Vittadini, G.: Assessment of school performance through a multilevel latent Markov Rasch model. J. Educ. Behav. Stat. 36, 491–522 (2011)Google Scholar
  11. 11.
    Bartolucci, F., Pennoni, F., Vittadini, G.: Causal latent Markov model for the comparison of multiple treatments in observational longitudinal studies. J. Educ. Behav. Stat. 41, 146–179 (2016)Google Scholar
  12. 12.
    Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37, 1554–1563 (1966)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat. 41, 164–171 (1970)MathSciNetzbMATHGoogle Scholar
  14. 14.
    DiMari, R., Oberski, D.L., Vermunt, J.K.: Bias-adjusted three-step latent markov modeling with covariates. Struct. Equ. Model. Multidiscip. J. 23(5), 649–660 (2016). MathSciNetGoogle Scholar
  15. 15.
    Dinner, I.M., van Heerde, H.J., Neslin, S.A.: Driving online and offline sales: the cross-channel effects of digital versus traditional advertising. Tuck School of Business Working Paper No. 2012-103. (2011)
  16. 16.
    Fader, P.S., Hardie, B.G.S.: Customer-base valuation in a contractual setting: the perils of ignoring heterogeneity. Mark. Sci. 29(1), 85–93 (2010)Google Scholar
  17. 17.
    Fader, P.S., Hardie, B.G.S., Chun-Yao, H.: A dynamic changepoint model for new product sales forecasting. Mark. Sci. 23(1), 50–65 (2004)Google Scholar
  18. 18.
    Hauser, J.R., Wisniewski, K.J.: Dynamic analysis of consumer response to marketing strategies. Manag. Sci. 28(5), 455–486 (1982)Google Scholar
  19. 19.
    Ho, T.H., Li, S., Park, S.E., Shen, Z.J.M.: Customer influence value and purchase acceleration in new product diffusion. Mark. Sci. 31(2), 236–256 (2012)Google Scholar
  20. 20.
    Horsky, D., Misra, S., Nelson, P.: Observed and unobserved preference heterogeneity in brand-choice models. Mark. Sci. 25(4), 322–335 (2006)Google Scholar
  21. 21.
    Huang, C.Y.: Excess loyalty in online retailing. Int. J. Electron. Commun. 16(2), 115–134 (2011)Google Scholar
  22. 22.
    Iyengar, R., Jedidi, K.: A conjoint model of quantity discounts. Mark. Sci. 31(2), 334–350 (2012)Google Scholar
  23. 23.
    Iyengar, R., Bulte, CVd, Valente, T.W.: Opinion leadership and social contagion in new product diffusion. Mark. Sci. 30(2), 195–212 (2011)Google Scholar
  24. 24.
    Kalwani, M.U., Yim, C.K., Rinne, H.J., Sugita, Y.: A price expectations model of customer brand choice. J. Mark. Res. 27(3), 251–262 (1990)Google Scholar
  25. 25.
    Kumar, V., Venkatesan, R., Bohling, T., Beckmann, D.: The power of clv: managing customer lifetime value at IBM. Mark. Sci. 27(4), 585–599 (2008)Google Scholar
  26. 26.
    Lagona, F., Jdanov, D., Shkolnikova, M.: Latent time-varying factors in longitudinal analysis: a linear mixed hidden Markov model for heart rates. Stat. Med. 33(23), 4116–4134 (2014)MathSciNetGoogle Scholar
  27. 27.
    Langeheine, R.S., van de Pol, F.: State mastery learning: dynamic models for longitudinal data. Appl. Psychol. Meas. 18(3), 277–291 (1994)Google Scholar
  28. 28.
    Lanza, S.T., Cooper, B.R.: A new sas procedure for latent transition analysis: transitions in dating and sexual risk behavior. Dev. Psychol. 44(2), 446–456 (2008). Google Scholar
  29. 29.
    Lanza, S.T., Cooper, B.R.: Latent class analysis for developmental research. Child Dev. Perspect 10(1), 59–64 (2016). Google Scholar
  30. 30.
    Lee, S., Zufryden, F., Drèze, X.: A study of consumer switching behavior across internet portal web sites. Int. J. Electron. Commun. 7(3), 39–63 (2003)Google Scholar
  31. 31.
    Lewis, M.: Research note: a dynamic programming approach to customer relationship pricing. Manag. Sci. 51(6), 986–994 (2005)zbMATHGoogle Scholar
  32. 32.
    Marino, M.F., Alfò, M.: Gaussian quadrature approximations in mixed hidden Markov models for longitudinal data: a simulation study. Comput. Stat. Data Anal. 94, 193–209 (2016)MathSciNetzbMATHGoogle Scholar
  33. 33.
    Mark, T., Bulla, J., Niraj, R., Bulla, I., Schwarzwällere, W.: Catalogue as a tool for reinforcing habits: empirical evidence from a multichannel retailer. Int. J. Res. Mark. (2019). Google Scholar
  34. 34.
    Mark, T., Lemon, K.N., Vandenbosch, M., Bulla, J., Maruotti, A.: Capturing the evolution of customer-firm relationships: how customers become more (or less) valuable over time. J. Retail. 89(3), 231–245 (2013)Google Scholar
  35. 35.
    Maruotti, A.: Mixed hidden markov models for longitudinal data: an overview. Int. Stat. Rev. 79(3), 427–454 (2011)zbMATHGoogle Scholar
  36. 36.
    Maruotti, A., Rocci, R.: A mixed non-homogeneous hidden markov model for categorical data, with application to alcohol consumption. Stat. Med. 31(9), 871–886 (2012)MathSciNetGoogle Scholar
  37. 37.
    Maruotti, A., Rydén, T.: A semiparametric approach to hidden Markov models under longitudinal observations. Stat. Comput. 19(4), 381–393 (2009)MathSciNetGoogle Scholar
  38. 38.
    Moe, W.W., Fader, P.S.: Capturing evolving visit behavior in clickstream data. J. Interact. Mark. 18(1), 5–19 (2004)Google Scholar
  39. 39.
    Montoya, R., Netzer, O., Jedidi, K.: Dynamic allocation of pharmaceutical detailing and sampling for long-term profitability. Mark. Sci. 29(5), 909–924 (2010)Google Scholar
  40. 40.
    Naik, P.A., Petersm, K.: A hierarchical marketing communications model of online and offline media synergies. J. Interact. Mark. 23(4), 288–299 (2009)Google Scholar
  41. 41.
    Netzer, O., Lattin, M., Srinivasan, V.: A hidden Markov model of consumer relationship dynamic. Mark. Sci. 27(2), 185–204 (2008)Google Scholar
  42. 42.
    Netzer, O., Ebbes, P.T., Bijmolt, H.: Hidden Markov models in marketing. In: Leeflang, P., Wieringa, J., Bijmolt, T., Pauwels, K. (eds.) Advanced Methods for Modeling Markets, International Series in Quantitative Marketing, vol. 14, pp. 405–449. Springer, Cham (2017)Google Scholar
  43. 43.
    Niculescu, M.F., Shin, H., Whang, S.: Underlying consumer heterogeneity in markets for subscription-based it services with network effects. Inform. Syst. Res. 23(4), 1322–1341 (2012)Google Scholar
  44. 44.
    Park, S., Gupta, S.: A regime-switching model of cyclical category buying. Mark. Sci. 30(3), 469–480 (2011)Google Scholar
  45. 45.
    Pongsapukdee, V., Sukgumphaphan, S.: Goodness of fit of cumulative logit models for ordinal response categories and nominal explanatory variables with two-factor interaction. Silpakorn U Sci. Technol. J. 1(2), 29–38 (2007)zbMATHGoogle Scholar
  46. 46.
    Schmiege, S.J., Meek, P., Bryan, A.D., Petersen, H.: Latent variable mixture modeling: a flexible statistical approach for identifying and classifying heterogeneity. Nurs. Res. 61(3), 204–212 (2012)Google Scholar
  47. 47.
    Schweidel, D.A., Bradlow, E.T., Fader, P.S.: Portfolio dynamics for customers of a multiservice provider. Manag. Sci. 57(3), 471–486 (2011)Google Scholar
  48. 48.
    Sen, S., Raghu, T.S., Vinze, A.: Demand heterogeneity in it infrastructure services: modeling and evaluation of a dynamic approach to defining service levels. Inf. Syst. Res. 20(2), 258–276 (2009)Google Scholar
  49. 49.
    Shachat, J., Wei, L.: Procuring commodities: first-price sealed-bid or english auctions? Mark. Sci. 31(2), 317–333 (2012)Google Scholar
  50. 50.
    Shin, S., Misra, S., Horsky, D.: Disentangling preferences and learning in brand choice models. Mark. Sci. 31(1), 115–137 (2012)Google Scholar
  51. 51.
    Singh, V.P., Hansen, K.T., Blattberg, R.C.: Market entry and consumer behavior: an investigation of a wal-mart supercenter. Mark. Sci. 25(5), 457–476 (2006)Google Scholar
  52. 52.
    Thomas, J.S., Sullivan, U.: Managing marketing communications with multichannel customers. J. Mark. 69(4), 239–251 (2005)Google Scholar
  53. 53.
    Valentini, S., Montaguti, E., Neslin, S.A.: Decision process evolution in customer channel choice. J. Mark. 75(6), 72–86 (2011)Google Scholar
  54. 54.
    Visser, I.: Seven things to remember about hidden Markov models: a tutorial on Markovian models for time series. J. Math. Psychol. 55(6), 403–415 (2011)MathSciNetzbMATHGoogle Scholar
  55. 55.
    Wiesel, T., Pauwels, K., Arts, J.: Practice prize paper—marketing’s profit impact: quantifying online and off-line funnel progression. Mark. Sci. 30(4), 604–611 (2011)Google Scholar
  56. 56.
    Zucchini, W., MacDonald, I.L., Langrock, R.: Hidden Markov Models for Time Series: An Introduction Using R, 2nd edn. Chapman & Hall, Boca Raton (2016)zbMATHGoogle Scholar

Copyright information

© Sapienza Università di Roma 2019

Authors and Affiliations

  1. 1.Dipartimento di Giurisprudenza, Economia, Politica e Lingue ModerneLibera Università Maria Ss. AssuntaRomeItaly
  2. 2.Department of MathematicsUniversity of BergenBergenNorway
  3. 3.Department of Psychiatry and PsychotherapyUniversity RegensburgRegensburgGermany
  4. 4.College of Business and EconomicsUniversity of GuelphGuelphCanada

Personalised recommendations