The TRB Share Prediction model is best suited for FMCG products where adoption of products is reflected in consumers’ willingness to continue buying. For these products the development of brand loyalty through repeat purchases is the measure of the success of a brand, and this is a function of RBR and trial rate.
In the case of products like consumer durables that are infrequently purchased, trial is a reflection of adoption. For such products, where the consumer’s inter-purchase interval extends into years, innovation diffusion models may be used to predict sales.
The Bass diffusion model is one of the most thoroughly researched models in market forecasting. Published in 1969, the model has proven to be versatile in representing the different patterns of adoption of products — from “sleepers”, where the sales pick up is gradual, to the “blockbusters”. It works well for a very wide range of categories and application fields within sectors like consumer durables, computers and technology products, medicine and medical services, agricultural innovations and services, prestige personal care, movies, books and so on.
The underlying assumption is that adoption by potential customers is triggered by two types of behaviour: innovation and imitation. “Innovation” is driven via influences such as advertising that are not dependent on the decisions of others in the social system. Its impact is more pronounced during the early stages of the product life cycle. “Imitation” is the influence of prior adopters through positive word-of-mouth.
The model further assumes:
The basic model is represented by the following equations:
$$ n(t)=adopters\,via\,innovation+adopters\,via\,imitation$$ $$ adopters\,via\,innovation=p\times remaining\,potential = p[M-N(t)]$$ $$ adopters\,via\,imitation=q\times proportion\,of\,adopters \times remaining\,potential$$ $$ \qquad = q\frac{N(t)}{M}[M-N(t)]$$ $$ Equation \,1: \mathbf{n(t)= p[M-N(t)]+q\frac{N(t)}{M}[M-N(t)]}$$Where:
n(t) = number of adopters at time t measured in years.
N(t) = n(0) + n(1) + n(2) ... n(t).
M = total number of potential adopters.
p = coefficient of innovation.
q = coefficient of immitation.
Exhibit 11.18 provides a comparison of the adoption trajectories for different values of p and q. If q > p, as is normally the case for most innovations, then imitation behaviour dominates, and the plot of sales over time will resemble a bell shape. On the other hand, if q <= p, as is the case for blockbuster products, then sales peak at introduction and decline in every subsequent time period.
Model Calibration
The model representation (Equation 1) is essentially of the form:
$$ X_i=a+bY_i+cY_i^2 $$ $$ where \, a=pM, \,b=q-p \,\, and\,\, c=-q/M $$If the innovation has been marketed, estimates of p, q and M from historical sales data may be obtained using a variety of statistical methods applicable for the above functional form. Of these the nonlinear least square method is known to yield better predictions, whereas the ordinary least squares linear regression is the easiest to work with.
If no sales data is available for the innovation, the parameters may be sourced from the diffusion patterns of product categories that exhibited similar characteristics when they were adopted. Estimates of coefficients p and q, for a wide range of product categories are readily available among a host of research publications. Based on a compilation provided in the text Principles of Marketing Engineering (Lilien et al., 2013) the average value across a wide range of products is 0.035 for the coefficient of innovation, and 0.390 for the coefficient of imitation. The book provides industry specific data for agricultural, consumer electronics, appliances, information technology, medical fields and a range of other products and services.
The assumptions inherent within the model and the inputs that it relies on, give rise to a number of limitations and model extensions including the following:
In summary, the Bass diffusion model is a conceptually appealing model that has been extensively researched. Academics have added numerous extensions enhancing the application and accuracy of the model in predicting the diffusion of innovations for categories where repeat purchases occur after many years. A key limitation however is that accurate estimation of the potential of an innovation usually requires a few years of sales data, by which time key investments would already have been made.
Use the Search Bar to find content on MarketingMind.
In an analytics-driven business environment, this analytics-centred consumer marketing workshop is tailored to the needs of consumer analysts, marketing researchers, brand managers, category managers and seasoned marketing and retailing professionals.
Unlock the Power of Digital Marketing: Join us for an immersive online experience designed to empower you with the skills and knowledge needed to excel in the dynamic world of digital marketing. In just three days, you will transform into a proficient digital marketer, equipped to craft and implement successful online strategies.
Contact | Privacy Statement | Disclaimer: Opinions and views expressed on www.ashokcharan.com are the author’s personal views, and do not represent the official views of the National University of Singapore (NUS) or the NUS Business School | © Copyright 2013-2024 www.ashokcharan.com. All Rights Reserved.