Omni-channel retailing: Analysing the dynamic and interaction effects of both traditional and online advertising
Master Thesis Defense Presentation January 24, 2008 by Rixt Gerlofsma
Outline
• Introduction
• Quotes
• Problem statement
• Research question
• Theoretical foundation
• Conceptual model
• Methodology
• Tobit-2 model
• Findings
• Results
• Discussion and conclusion
• Recommendations and contribution
Quotes
"The role of advertising is controversial and complex”
(Zhou, Zhou and Ouyang, 2013)“There is a continuing rise of new communication channels, resulting in omni-channel retailing”
(Verhoef, Kannan and Inman, 2015)“A successful omni-channel strategy guarantees a retailer’s survival”
(Rigby,Advertising channels targeting consumers in the same stages of the buying process may lead to synergy effects or cannibalization effects
(Kumar and Gupta, 2016;Kumar, Choi and Green, 2017)
• 47% of online advertising is allocated to display advertising. Yet, there is still debate whether display advertising positively affects sales
(ZenithOptimedia, 2016)• Retailers still rely on trial-and-error or gut feelings when making budget allocations decisions for their marketing initiatives
(Jordan, Mahdian, Vassilvitskii and Vee, 2010)• Retailers seldom coordinate their various marketing campaigns
(Joo, Wilbur, Cowgill and Zhu, 2014)Research Question
“What are the dynamic and interaction effects of traditional and online advertising
and how do these channels influence offline sales?’’
Theoretical Foundation
Conceptual Model
Tobit-2 Model
• Weekly individual household data.
• Focus on channels who target consumers early in their buying making process.
• Tobit -2 model: Decision to make a purchase and the decision on how much to spent when making a purchase.
• Four types of models:
• Basic sales models
• Direct lag sales models
• Geometric lag sales models
• Interaction models
Results
• Basic sales model
• Sales: Print (-), Radio (+), TV (-), Display (+)
• Sales amount: No effects
• Direct lag model
• Sales: Short-term: TV (+), Long-term:
• Interaction model
• Sales: At time t: Print and TV (+)
• Geometric lag model
• Sales: Print (-), Radio (+), Diplay (+)
• Sales amount: No effects
• Display advertising: Basic sales model: (+)
Direct lag model: No effect Geometric lag model: (+)
•
• Sales amount: Negative long-term effect. This may imply that while advertising seems to increase number of sales, the amount spent per purchase decreases.
• Synergy effects: Whereas print and TV advertising both negatively affect sales on the short-term, combined together they positively affect sales on the short-term.
Recommendations and contribution
• Valuable insights for retailers planning their marketing activities:
• We recommend the retailer in question to (1) decrease spending on TV advertising and (2) increase spending on display advertising.
• Dynamic effects:
• There are marketing persistence effects which suggest that after a certain number of ad repetition an advertising channel can ‘hit in’.
• There are long-term effects which differ among advertising channels.
• Interaction effects:
• There are synergy effects both within and across channels.
Limitations and future research
• Focus on only offline sales:
• There is an incongruence between online advertising and the offline purchase channel. This may have influenced the indifferent performance of online display advertising.
• Limited number of media advertising channels:
• Search advertising and social media are indispensable in omni-channel retailing. This could have led to inaccurate conclusions.
• Weekly-household level data:
• One could imagine that when individual daily-level data is available, one can estimate advertising effects even more precisely.
• Sub-features:
• No information about the content of the advertisements, or the types of websites which is advertised on, or differences between new customers and existing customers.
References
Grewal, D., Roggeveen, A. L., and Nordfält, J. (2017). The future of retailing. Journal of Retailing, 93 (1), 1-6.
Joo, M., Wilbur, K., Cowgill, B., and Zhu, Y. (2014). Television advertising and online search. Management Science, 60 (1), 56-73.
Jordan, P., Mahdian, M., Vassilvitskii, S., & Vee, E. (2010). The multiple attribution problem in pay-per-conversion advertising. Lecture Notes in Computer Science, 6982, 31–43.
Kumar, V., Choi, J. B., and Greene, M. (2017). Synergistic effects of social media and traditional marketing on brand sales:
capturing the time-varying effects. Journal of the Academy of Marketing Science, 1–21.
Kumar, V., and Gupta, S. (2016). Conceptualizing the evolution and future of advertising. Journal of Advertising, 45 (3), 302-317.