Machine Learning Based Approach for Measuring Promotion Effectiveness in Multiple Parallel Promotions’ Scenarios
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32847
Machine Learning Based Approach for Measuring Promotion Effectiveness in Multiple Parallel Promotions’ Scenarios

Authors: Revoti Prasad Bora, Nikita Katyal


Promotion is a key element in the retail business. Thus, analysis of promotions to quantify their effectiveness in terms of Revenue and/or Margin is an essential activity in the retail industry. However, measuring the sales/revenue uplift is based on estimations, as the actual sales/revenue without the promotion is not present. Further, the presence of Halo and Cannibalization in a multiple parallel promotions’ scenario complicates the problem. Calculating Baseline by considering inter-brand/competitor items or using Halo and Cannibalization's impact on Revenue calculations by considering Baseline as an interpretation of items’ unit sales in neighboring nonpromotional weeks individually may not capture the overall Revenue uplift in the case of multiple parallel promotions. Hence, this paper proposes a Machine Learning based method for calculating the Revenue uplift by considering the Halo and Cannibalization impact on the Baseline and the Revenue. In the first section of the proposed methodology, Baseline of an item is calculated by incorporating the impact of the promotions on its related items. In the later section, the Revenue of an item is calculated by considering both Halo and Cannibalization impacts. Hence, this methodology enables correct calculation of the overall Revenue uplift due a given promotion.

Keywords: Halo, cannibalization, promotion, baseline, temporary price reduction, retail, elasticity, cross price elasticity, machine learning, random forest, linear regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1235


[1] Thirunavukkarasu, Shobitha Madhavan.: “System and method for promotion optimization using machine learning”, US Patent Application no: US 2020/0334700 A1 (2020) GoogleScholar
[2] Mudassir, Sukumar, Garlapati, Pahwa.: “Systems and methods for calculating and presenting information related to the effectiveness of a promotion”, US Patent Application no: US20190340633A1(2018) GoogleScholar
[3] Ailawadi, Harlam, Cesar, Trounce: “Quantifying and Improving Promotion Effectiveness at CVS”, Marketing Science (July 2007) GoogleScholar
[4] Blattberg, Kim, Jianming Ye.: “Defining Baseline sales in a Competitive Environment”, Seoul Journel of Business Volume 2 Number 1 (1996) GoogleScholar
[5] Olli Herrala.: “Evaluating cannibalization between items in retail promotions”, Aalto University Bachelor’s thesis (2018) GoogleScholar
[6] Heerde, Leeflang, Wittink.: “How promotions Work: SCAN*PRO-Based Evolutionary Model Building”, Schmalenbach Business Review Vol. 54 (July 2002) GoogleScholar
[7] Abraham, Lodish.: “An Implemented System for Improving Promotion Productivity using store scanner data”, Marketing Science, Vol. 12, No. 3(Summer 1993) GoogleScholar
[8] Kurt Jetta, Rengifo.: “A model to Improve the Estimation of Baseline Retail sales”, Journa of CENTRUM Cathedra, (2011) GoogleScholar
[9] Andrews, Currim, Leeflang, Lim.: “Estimating the SCAN*PRO model of store sales: HB,FM or just OLS?, International Journal of Research in Marketing, (2005) GoogleScholar
[10] Baohong Sun.: “Promotion effect on endogenous consumption”, Marketing Science, (2005) GoogleScholar
[11] S.Mace, S. Neslin, “The Determinants of Pre- and Postpromotion Dips in sales of frequently purchased goods”, Marketing Research, (Aug 2004) GoogleScholar
[12] Sunil Gupta, “Impact of sales promotions on when, what, and how much to buy”, Marketing Research, (Nov 1988) GoogleScholar
[13] David R. Bell, Chiang, V. Padmanabhan, “The Decomposition of Promotional Response: An Empirical Generalization”, Marketing Science, (Nov 1999) GoogleScholar
[14] Zliobaithe, Bakker, Pechenizkiy.: “Beating the Baseline prediction in food Sales: How intelligent an intelligent predictor is?”, Expert Systems with Applications (January 2012) GoogleScholar