Evaluation and Comparison of Different Approaches for Promotional Forecasting: A Case Study of a Soft Drink Company

Lu, Yang (2011) Evaluation and Comparison of Different Approaches for Promotional Forecasting: A Case Study of a Soft Drink Company. [Dissertation (University of Nottingham only)] (Unpublished)

[img] PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (911kB)

Abstract

This paper describes two approaches for promotional forecasting based on a mathematical tool called linear regression. It intends to evaluate and compare the accuracy level of different forecasting approaches by introducing a case study between the Coca Cola Enterprises (CCE) and the Morrisons. Both of the two approaches are derived from previous researches and literature review on conventional forecasting, especially on promotional forecasting, and forecasts based on aggregation. They are designed as multivariable linear regression models, which involves several promotional mixes as variables including percentage discount, display, and holidays. The performances of both approaches are satisfactory in terms of the adjusted R2 (over 80%) and the MAPE (lower than 20%). Besides, for most kinds of soft drinks, the second approach represents a relative better ability on promotional forecasting. The limitation would be the errors between estimates and actual sales volume are magnified due to the process of disaggregation. Thus, in the final part of this research, a newly proposed model is tested on coke 2l product line, which is expected to give an initial idea for further research.

Item Type: Dissertation (University of Nottingham only)
Depositing User: EP, Services
Date Deposited: 26 Apr 2012 10:42
Last Modified: 27 Sep 2016 14:20
URI: http://eprints.nottingham.ac.uk/id/eprint/25013

Actions (Archive Staff Only)

Edit View Edit View