Predicting future consumer purchases in grocery retailing with the condensed Poisson lognormal model

Abstract To identify the effect of marketing actions on consumer purchasing, analysts must disentangle the dynamic component of purchasing from expected period-to-period stochastic fluctuations. This is done by comparing marketplace observations to the conditional expectation of future purchasing. Current methods of deriving the conditional expectation contain systematic bias and rely on certain unrealistic modelling assumptions. We therefore propose a new model to predict future consumer purchases in grocery retailing. The new model is a mixture of Erlang-2, Poisson and lognormal distributions or a condensed Poisson lognormal model (CPLN). Using two grocery retailing datasets from the UK, we demonstrate that the CPLN model predicts future consumer purchases well with error of 7% and 9%, respectively. Compared with the previous benchmark model, the condensed Negative Binominal Distribution (CNBD), the CPLN model reduces error by 50% (7% versus 14%) and 67% (9% versus 27%), respectively. Theoretical and practical implications for retailers are discussed.

[1]  J. Wilkinson,et al.  Can the negative binomial distribution predict industrial purchases , 2016 .

[2]  J. Aitchison,et al.  The Lognormal Distribution. , 1958 .

[3]  T. Fahidy.  Electrochemical horizons for the Poisson-lognormal distribution of probability theory , 2005 .

[4]  Flexible Purchase Frequency Modeling , 1996 .

[5]  D. Hensher.  The valuation of commuter travel time savings for car drivers: evaluating alternative model specifications , 2001 .

[6]  P. Lenk,et al.  Nonstationary Conditional Trend Analysis: An Application to Scanner Panel Data , 1993 .

[7]  Cam Rungie,et al.  Predicting future purchases with the Poisson log-normal model , 2014 .

[8]  R. Cassie.  Frequency Distribution Models in the Ecology of Plankton and Other Organisms , 1962 .

[9]  J. Herniter.  A Probablistic Market Model of Purchase Timing and Brand Selection , 1971 .

[10]  So Young Sohn,et al.  A comparative study of four estimators for analyzing the random event rate of the poisson process , 1994 .

[11]  Sunil Gupta,et al.  Stochastic Models of Interpurchase Time with Time-Dependent Covariates , 1991 .

[12]  K. Train.  Halton Sequences for Mixed Logit , 2000 .

[13]  D. Bellwood,et al.  Testing species abundance models: a new bootstrap approach applied to Indo-Pacific coral reefs. , 2009, Ecology.

[14]  Yuxin Chen,et al.  Modeling Credit Card Share of Wallet: Solving the Incomplete Information Problem , 2012 .

[15]  A. Ehrenberg.  The Pattern of Consumer Purchases , 1959 .

[16]  Andrew Ehrenberg,et al.  Conditional Trend Analysis: A Breakdown by Initial Purchasing Level , 1967 .

[17]  Andrew Ehrenberg,et al.  Progress on a Simplified Model of Stationary Purchasing Behaviour , 1966 .

[18]  L. Lockshin,et al.  Purchasing behaviour of ethnicities: Are they different? , 2020 .

[19]  David C. Schmittlein,et al.  Predicting Future Random Events Based on Past Performance , 1981 .

[20]  Rob Kaas,et al.  Ordering claim size distributions and mixed Poisson probabilities , 1995 .

[21]  Fundamental basket size patterns and their relation to retailer performance , 2020 .

[22]  Richard Mizerski,et al.  An investigation into gambling purchases using the NBD and NBD–Dirichlet models , 2009 .

[23]  Fred S. Zufryden,et al.  A Composite Heterogeneous Model of Brand Choice and Purchase Timing Behavior , 1977 .

[24]  Tarek Sayed,et al.  Accident prediction models with random corridor parameters. , 2009, Accident; analysis and prevention.

[25]  Dick Mizerski,et al.  The Stochastic Nature of Purchasing a State'S Lottery Products , 2004 .

[26]  E. Tsionas.  Bayesian Analysis of Poisson Regression with Lognormal Unobserved Heterogeneity: With an Application to the Patent-R&D Relationship , 2010 .

[27]  B. Kahn,et al.  Shopping trip behavior: An empirical investigation , 1989 .

[28]  Bill Page,et al.  Fundamental patterns of in-store shopper behavior , 2017 .

[29]  M. Greenwood,et al.  An Inquiry into the Nature of Frequency Distributions Representative of Multiple Happenings with Particular Reference to the Occurrence of Multiple Attacks of Disease or of Repeated Accidents , 1920 .

[30]  Donald G. Morrison,et al.  Prediction of Future Random Events with the Condensed Negative Binomial Distribution , 1983 .

[31]  Svetlana Bogomolova,et al.  The fallacy of the heavy buyer: Exploring purchasing frequencies of fresh fruit and vegetable categories , 2020, Journal of Retailing and Consumer Services.

[32]  Couchen Wu,et al.  Counting your customers: Compounding customer's in-store decisions, interpurchase time and repurchasing behavior , 2000, Eur. J. Oper. Res..

[33]  Sunil Gupta.  Impact of Sales Promotions on when, what, and how Much to Buy , 1988 .

[34]  M. Uncles,et al.  Understanding brand performance measures: using Dirichlet benchmarks , 2004 .

[35]  Florian Heiss,et al.  Discrete Choice Methods with Simulation , 2016 .

[36]  Liping Fu,et al.  Alternative Risk Models for Ranking Locations for Safety Improvement , 2005 .

[37]  Raymond J. Lawrence,et al.  The Lognormal Distribution of Buying Frequency Rates , 1980 .

[38]  Bill Page,et al.  Comparing two supermarket layouts: The effect of a middle aisle on basket size, spend, trip duration and endcap use , 2019, Journal of Retailing and Consumer Services.

[39]  L. Lockshin,et al.  How country of origins of food products compete and grow , 2019, Journal of Retailing and Consumer Services.

[40]  R. Winkelmann.  Econometric Analysis of Count Data , 1997 .

[41]  M. Bulmer.  On Fitting the Poisson Lognormal Distribution to Species-Abundance Data , 1974 .

[42]  E. Crow,et al.  Lognormal Distributions: Theory and Applications , 1987 .

[43]  Chien-Wei Wu,et al.  A consumer purchasing model with learning and departure behaviour , 2000, J. Oper. Res. Soc..

[44]  Jerome Spanier,et al.  Quasi-Random Methods for Estimating Integrals Using Relatively Small Samples , 1994, SIAM Rev..

[45]  C. Bhat.  Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model , 2001 .

[46]  G. J. Goodhardt,et al.  A Consumer Purchasing Model with Erlang Inter-Purchase Times , 1973 .

[47]  Jenni Romaniuk,et al.  Systematic response errors in self-reported category buying frequencies , 2017 .

[48]  Malcolm J. Wright,et al.  Regularities in the consumption of a subscription service , 2011 .

[49]  Fred S. Zufryden,et al.  An Empirical Evaluation of a Composite Heterogeneous Model of Brand Choice and Purchase Timing Behavior , 1978 .

[50]  David C. Schmittlein,et al.  Generalizing the NBD Model for Customer Purchases: What Are the Implications and Is It Worth the Effort? , 1988 .

[51]  Frank M. Bass,et al.  A Multibrand Stochastic Model Compounding Heterogeneous Erlang Timing and Multinomial Choice Processes , 1980, Oper. Res..

[52]  David C. Schmittlein,et al.  Technical Note---Why Does the NBD Model Work? Robustness in Representing Product Purchases, Brand Purchases and Imperfectly Recorded Purchases , 1985 .

[53]  J. Halton.  On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals , 1960 .