Online Program

Friday, February 19
CS06 Model Selection and Experimental Design Fri, Feb 19, 11:00 AM - 12:30 PM
Topaz

New Product Diffusion Models: Theory and Practice (303132)

*Mariangela Guidolin, University of Padua 

Keywords: Innovation diffusion models, Quantitative marketing, Nonlinear regression, Time series

Main aim of the presentation is to provide an introduction to the most known innovation diffusion models, used to describe and forecast the evolution in time of sales of new products. In most cases, sales of new products are characterized by a finite life cycle, which follows a nonlinear path (birth, growth, maturity, and decline): In this context, traditional time series tools such as ARIMA models do not prove a satisfactory choice. Quantitative marketing has played a central role in the development of new product diffusion models. The statistical techniques involved in model estimation combine time series analysis with nonlinear regression techniques. The key objectives of the presentation are: to describe the main mathematical features of the models, illustrating the meaning of the parameters from the marketing point of view; to present and discuss the statistical aspects involved in model estimation and selection; to show and discuss forecasting and explanatory ability of the proposed models with real-data applications in several industrial and commercial sectors.