TY  - JOUR
AB  - Purpose– Quantitative measures are not commonly available to identify and measure product cannibalization resulting from the introduction of new products, and existing forecasting methods such as ARIMA do not explicitly account for the phenomenon. This paper aims to present a methodology to build cannibalization effects into forecasting models as measured through product attributes. It follows on from a paper by the same authors in Vol. 23 No. 4Design/methodology/approach– The contribution of product attributes to cannibalization is tested by a series of hypotheses, then integrated into the proposed cannibalization model. Results are compared with predictions from an ARIMA‐based model and actual historical sales data.Findings– The proposed model improves on the fidelity of ARIMA‐based models, by between 16 and 42 percent.Originality/value– Effective prediction of cannibalization losses will allow marketing planners to make better‐informed decisions with respect to new product introduction.
VL  - 23
IS  - 5
SN  - 0263-4503
DO  - 10.1108/02634500510612645
UR  - https://doi.org/10.1108/02634500510612645
AU  - Ragharan Srinivasan Sundara
AU  - Ramakrishnan Sreeram
AU  - Grasman Scott E.
PY  - 2005
Y1  - 2005/01/01
TI  - Incorporating cannibalization models into demand forecasting
T2  - Marketing Intelligence & Planning
PB  - Emerald Group Publishing Limited
SP  - 470
EP  - 485
Y2  - 2024/04/19
ER  -