The impact of advertising along the conversion funnel

Abstract

We assemble a unique data set that combines information on supermarket feature advertising with path-tracking data on consumers’ movement within the store as well as purchase information. Using these novel data, we trace out how advertising affects consumer behavior along the path-to-purchase. We find advertising has no significant effect on the number of consumers visiting the category being advertised. The null effect is precisely estimated. At the upper bound of the confidence interval, a one-standard-deviation shift in advertising increases category traffic by only 1.3%. We do find a significant effect at the lower end of the conversion funnel. A one-standard-deviation change in advertising (evaluated at the point estimate) increases category-level sales by 10%. We further decompose the impact on sales and find the increase is driven by the same number of consumers buying a larger number of products of the same brand. We find no evidence of spillover effects of advertising between categories that are stocked in proximity of each other, nor between different products in the same category. Two mechanisms are consistent with these patterns: consumers retrieve memory of the ad only when interacting with the category or only consumers wanting to purchase the brand choose to consume the ad.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Notes

  1. 1.

    “The Food Industry Speaks 2015,” Food Marketing Institute.

  2. 2.

    If a consumer moves farther than to an adjacent traffic point between signals, the movement over traffic points between the signals is interpolated. Because the signal is emitted at a high frequency, little interpolation is necessary for most trips.

  3. 3.

    The data provide the linkage between traffic points and product locations. Most product locations are associated with two or three traffic points.

  4. 4.

    We find that for 88% of all brand/week combinations in our data, feature advertising status is identical across all products within the specific brand/week (i.e., products within the same brand are all featured or not featured).

  5. 5.

    The average pairwise correlation of displays (across all categories and weeks) between stores of the same chain in the same market is equal to 0.50.

  6. 6.

    The categories in IRI not included in our analysis are razors, razor blades, cigarettes, deodorant, diapers, household cleaner, photo, shampoo, sugar substitutes, and tooth brushes.

  7. 7.

    We also implement the wild bootstrap method that Cameron et al. (2008) propose for settings with a small number of clusters. For our baseline regressions (for the impact on traffic as well as sales), we find the level of precision is slightly higher when applying the bootstrap procedure.

  8. 8.

    The price information is obtained from the purchase data. A promotion is defined as a reduction of at least 15% relative to the base price. The average price level is computed as the average (unweighted) price of all products in the category, and captures promotional price fluctuation over time in a more continuous fashion (relative to the number-of-promotions variable).

  9. 9.

    The inclusion of marketing controls does not play a role in driving the null effect (see Table 6 in the Appendix).

  10. 10.

    We emphasize that the null effect is precisely estimated and not due to a lack of statistical power, which is often documented in studies of online advertising (see Lewis and Rao 2015; Lewis and Reiley 2014).

  11. 11.

    We compute the standard deviation of features within categories by regressing the feature variable onto category fixed effects and then calculating the standard deviation of the residuals from this regression.

  12. 12.

    One could also use the share of purchases divided by the number of consumers visiting the category as the dependent variable. Due to the null effect on traffic, conditioning on category visits will not materially affect the results. For simplicity, we therefore focus on the unconditional number of purchases.

  13. 13.

    Because the across-store regression is estimated at the weekly level, we divide the estimated demand shocks by 7.

  14. 14.

    We emphasize that the display variable in the academic IRI data set is recorded for each store individually. Although industry practice is to sometimes impute display information from other stores, we did confirm with IRI directly that the display information is not imputed for the data used here.

  15. 15.

    The standard deviation of the pickup/purchase ratio (based on all locations) is 0.306, and hence a one-standard-deviation shift in the number of features (eight additional products) leads to an increase of 4% of a standard deviation (0.0017*8/0.306).

  16. 16.

    All of our discussion in this section focuses on classical, that is, additively separable, measurement error.

  17. 17.

    As discussed above, one could imagine that displays divert traffic away from main category locations, and hence the impact on traffic might be negative. However, our analysis in the previous section provides evidence against such an effect.

  18. 18.

    We note that we have sales data for all products and categories in the store, but the advertising data (from IRI) is limited to only 21 categories. See Section 2.3 for more details.

  19. 19.

    We manually code whether categories are substitutes, complements, or unrelated to each other. For instance, in the vicinity of beer, one substitute category (wine) is stocked as well as several complementary categories (chips, popcorn, etc.). We also note the majority of nearby products belongs to unrelated categories (88%) and only a small subset of products are either substitutes or complements of the focal category.

  20. 20.

    We note, however, that our estimates from this regression are noisy, and only the coefficient on the feature dummy variable is precisely estimated. The confidence interval for the brand-level effect of advertising (α 1 + α 2) ranges from -0.45 to 1.17 and therefore includes a null effect of advertising at the brand level as well as a modest positive spillover effect.

  21. 21.

    The path-data time stamp that records the arrival at the checkout can be noisy because the consumer will be stationary when standing in line at the cashier. Therefore, checkout baskets within a certain time window after the consumer became stationary in the checkout area qualify as possible matches.

  22. 22.

    The data provider did not disclose the precise algorithm to us.

  23. 23.

    We have path data for only 26 days, but we have data on feature advertising and other marketing variables for a longer time period. As a result, our lagged regressions have the same number of observations as the main regressions.

  24. 24.

    We can only define visit timing for consumers who actually pass the category at all during their trip. The day/category average therefore represents the average visit time for the subset of consumers who visit the specific category.

  25. 25.

    We also ran the same set of regressions based on distance walked before reaching a specific category (rather than time elapsed), and found similarly small and insignificant results.

  26. 26.

    The confidence interval for columns (5) and (6), respectively, are equal to [-0.050,0.021] minutes and [-0.089,0.149] percentage points.

References

  1. Anderson, E., Malin, B.A., Nakamura, E., Simester, D., & Steinsson, J. (2016). Informational rigidities and the stickiness of temporary sales. Journal of Monetary Economics, forthcoming.

  2. Anderson, E.T., & Simester, D. (2013). Advertising in a competitive market: the role of product standards, customer learning, and switching costs. Journal of Marketing Research, 50, 489–504.

    Article  Google Scholar 

  3. Bagwell, K. (2007). The economic analysis of advertising. In M. Armstrong, & R. Porter (Eds.), Handbook of industrial organization. Elsevier Science, (Vol. 3 pp. 1701–1844).

  4. Blattberg, R.C., & Neslin, S.A. (1990). Sales promotion: concepts, methods and strategies, 2nd edn. Prentice Hall.

  5. Bodapati, A.V., & Srinivasan, V. (2006). The impact of feature advertising on customer store choice. Working Paper.

  6. Bronnenberg, B.J., Kim, J.B., & Mela, C.F. (2016). Zooming in on choice: how do consumers search for cameras online? Marketing Science, 35, 693–712.

    Article  Google Scholar 

  7. Bronnenberg, B.J., Kruger, M.W., & Mela, C.F. (2008). The IRI marketing data set. Marketing Science, 27, 745–748.

    Article  Google Scholar 

  8. Cameron, A.C., Gelbach, J.B., & Miller, D.L. (2008). Bootstrap-based improvements for inference with clustered errors. The Review of Economics and Statistics, 3, 414–427.

    Article  Google Scholar 

  9. Chan, T., Ma, Y., Narasimhan, C., & Singh, V. (2006). An empirical analysis of store competition. Working Paper.

  10. Chen, Y., & Yao, S. (2016). Sequential search with refinement: model and application with click-stream data. Management Science, forthcoming.

  11. De Los Santos, B.I., Hortacsu, A., & Wildenbeest, M. (2012). Testing models of consumer search using data on web browsing and purchasing behavior. American Economic Review, 102, 2955–2980.

    Article  Google Scholar 

  12. Erdem, T., Imai, S., & Keane, M.P. (2003). Brand and quantity choice dynamics under price uncertainty. Quantitative Marketing and Economics, 1, 5–64.

    Article  Google Scholar 

  13. Hendel, I., & Nevo, A. (2006). Measuring the implications of sales and consumer inventory behavior. Econometrica, 74, 1637–1673.

    Article  Google Scholar 

  14. Honka, E., Hortacsu, A., & Vitorino, M.A. (2016). Advertising, consumer awareness and choice: Evidence from the U.S. Banking Industry. RAND Journal of Economics, forthcoming.

  15. Hui, S.K., Bradlow, E.T., & Fader, P.S. (2009a). The traveling salesman goes shopping: the systematic deviations of grocery paths from TSP optimality. Marketing Science, 28, 566–572.

  16. Hui, S.K., Fader, P.S., & Bradlow, E.T. (2009b). Path data in marketing: an integrative framework and prospectus for model building. Marketing Science, 28, 320–335.

  17. Hui, S.K., Huang, Y., Suher, J., & Inman, J. (2013a). Deconstructing the first moment of truth: understanding unplanned consideration and purchase conversion using In-Store video tracking. Journal of Marketing Research, 50, 445–462.

  18. Hui, S.K., Inman, J., Huang, Y., & Suher, J. (2013b). Estimating the effect of travel distance on unplanned spending: applications to mobile promotion strategies. Journal of Marketing, 77, 1–16.

  19. Jedidi, K., Mela, C.F., & Gupta, S. (1999). Managing advertising and promotion for long-run profitability. Marketing Science, 18, 1–22.

    Article  Google Scholar 

  20. Johnson, G.A., Lewis, R., & Nubbemeyer, E. (2016). The online display ad effectiveness funnel & carry-over: a meta-study of ghost ad experiments. Working Paper.

  21. Keller, K.L. (1987). Memory factors in advertising: the effect of advertising retrieval cues on brand evaluations. Journal of Consumer Research, 14, 316–333.

    Article  Google Scholar 

  22. Kim, J.B., Albuquerque, P., & Bronnenberg, B.J. (2010). Online demand under limited consumer search. Marketing Science, 29, 1001–1023.

    Article  Google Scholar 

  23. Lee, A.Y. (2002). Effects of implicit memory on memory-based versus stimulus-based brand choice. Journal of Marketing Research, 39, 440–454.

    Article  Google Scholar 

  24. Lee, A.Y., & Labroo, A.A. (2004). The effect of conceptual and perceptual fluency on brand evaluation. Journal of Marketing Research, 41, 151–165.

    Article  Google Scholar 

  25. Lewis, R.A., & Nguyen, D. (2014). A Samsung Ad for the iPad? Display advertising’s competitive spillovers to search. Working Paper.

  26. Lewis, R.A., & Rao, J.M. (2015). The unfavorable economics of measuring the returns to advertising*. The Quarterly Journal of Economics, 130, 1941.

    Article  Google Scholar 

  27. Lewis, R.A., & Reiley, D.H. (2014). Online ads and offline sales: measuring the effect of retail advertising via a controlled experiment on Yahoo! Quantitative Marketing and Economics, 12, 235–266.

    Article  Google Scholar 

  28. Mela, C.F., Gupta, S., & Lehmann, D.R. (1997). The long-term impact of promotion and advertising on consumer brand choice. Journal of Marketing Research, 34, 248–261.

    Article  Google Scholar 

  29. Osborne, M. (2011). Consumer learning, switching costs and heterogeneity: a structural examination. Quantitative Marketing and Economics, 9, 25–70.

    Article  Google Scholar 

  30. Quelch, J.A., & Court, A.M. (1983). PROCTER & GAMBLE CO. (B). HBS Case, 584048.

  31. Rossi, P.E. (2014). Invited paper – even the rich can make themselves poor: a critical examination of IV methods in marketing applications. Marketing Science, 33, 655–672.

    Article  Google Scholar 

  32. Sahni, N.S. (2016). Advertising spillovers: evidence from online field experiments and implications for returns on advertising. Journal of Marketing Research, 53, 459–478.

    Article  Google Scholar 

  33. Sahni, N.S., Zou, D., & Chintagunta, P.K. (2016). Do targeted discount offers serve as advertising? Evidence from 70 field experiments. Management Science, forthcoming.

  34. Seiler, S., & Pinna, F. (2016). Estimating search benefits from path-tracking data: measurement and determinants. Marketing Science, forthcoming.

  35. Shapiro, B.T. (2016). Positive spillovers and free riding in advertising of prescription pharmaceuticals: The case of antidepressants. Journal of Political Economy, forthcoming.

  36. Sorensen, H. (2003). The science of shopping. Marketing Research, 15, 31–35.

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Stephan Seiler.

Additional information

We thank Eric Anderson, Tomomichi Amano, Eric Bradlow, Pradeep Chintagunta, Yufeng Huang, Mitch Lovett, Carl Mela, Sridhar Narayanan, Aviv Nevo, Thomas Otter, Brad Shapiro, and participants of the INFORMS Marketing Science Conference 2016 and Yale Customer Insights Conference 2017 for their feedback. We thank Herb Sorensen for his invaluable help with the path-tracking data. We particularly thank Pedro Gardete for helping us compute wild bootstrap standard errors. All errors are our own.

Appendix

Appendix

A.1 Linking sales and path data

One important features of our data set is the linkage of sales to trip records. As part of the RFID tracking process, the data report when the consumer arrives at the checkout. Independently, the sales data also have a time stamp for each shopper’s transaction at the checkout. Comparing the time stamp of a particular path with the sales data allows us to define a set of “candidate” checkout product baskets that occurred at a similar point in time.Footnote 21 Matching which trip goes with which specific transaction involves considering the physical location of all the UPCs in each candidate basket. Based on how many of those locations lie on the path we are trying to match, a score is created for the baskets and the highest-scoring one is matched to the path.Footnote 22 The matches do not necessarily yield a perfect score, because consumers might occasionally leave the cart and pick up an item. Therefore, we might not see the path of the consumer going past a specific item, even if the item was in her matched purchase basket.

A.2 (Lack of a) spatial correlation in feature advertising

In this section, we explore spatial correlation patterns in feature advertising activity in different categories. Correlation in feature advertising could have an impact on our results with regards to the lack of an effect of advertising on category traffic. Specifically, if feature advertising in categories that are stocked near each other is negatively correlated over time, such a correlation could mask an effect of advertising on traffic for any individual category.

To study spatial correlation, we first compute correlations between pairs of categories that are stocked in the same aisle. Among the 21 categories in our sample, 11 such pairs exist, and no systematic patterns emerges regarding the pairwise correlations. Out of 11 correlations, 5 are positive and 6 are negative.

Next, to assess the relationship between categories more systematically, we calculate the distance between each pair of categories in our sample. We then estimate a regression at the category-pair level where we regress the correlation coefficient (of features) for the category pair on the distance between the categories. Doing so, we find a small and insignificant coefficient for the distance variable. A one-standard-deviation change in distance (51 feet) leads to an (insignificant) increase in the correlation coefficient of 0.027. This number corresponds to a 0.05-standard-deviation increase in the correlation coefficient. We also implement regression specifications that include a “same-aisle” dummy and higher-order terms for the distance variable. Across all such specifications, we find consistently small and insignificant effects of distance (and other measures of vicinity) on the correlation in features between category pairs.

A.3 Intertemporal effects of advertising

Our main analysis of advertising impact on product sales in Section 3.2 investigates the effect of advertising on category-level sales in the same time period. It is conceivable that any increase in contemporaneous purchases is offset by lower levels of purchases in subsequent periods. Such intertemporal demand effects are well documented for price promotions (see Erdem et al. 2003; Hendel and Nevo 2006 and Osborne 2011) and could also occur in response to advertising.

To look at intertemporal advertising effects, we amend our regression framework in a simple way. Namely, we add lagged feature advertising, as well as similar terms for the other marketing variables, to our main regression, which regresses category-level sales on marketing variables (feature advertising, display, promotion dummy, and average price), and category and day fixed effects. Such a regression will show a “post-advertising dip” in sales if intertemporal effects are important, and hence a negative effect of lagged advertising would provide evidence for intertemporal substitution.

In Table 8, we present results for the two sales measures on which advertising has a significant impact: the number of consumer/UPC pairs and total quantity (the dependent variables used in columns (3) and (4) of Table 3). The baseline regressions without lagged variables are replicated in the first two columns, followed by the corresponding regressions with lagged terms.Footnote 23 For both outcome variables, we find the effect of lagged advertising to be insignificant and small in magnitude. The magnitude of the contemporaneous advertising effects do not change significantly relative to the specifications without lagged terms. However, adding the lagged variables makes the effect of contemporaneous advertising insignificant in the specification based on total quantity (column (4)). Results stay significant when using consumer/UPC pairs as the dependent variable. We also note that when we run the traffic regressions with lagged terms (not reported), both contemporaneous and lagged advertising effects are insignificant.

Table 8 The impact of lagged advertising on purchases

We take the results from these regressions as evidence that intertemporal advertising effects do not occur in our setting.

A.4 The impact of feature advertising on visit timing

In this section, we describe in more detail the analysis of category-visit timing summarized briefly in Section 3.4. To analyze the timing of visits, we compute for each shopping trip the point in time at which the consumer is for the first time walking past a specific product category. We then compute the average time since the start of the trip during which a specific category was visited at the category/day level.Footnote 24 We first regress the time of the visit (measured in minutes since the start of the trip) and fraction of total shopping time elapsed on the number of featured products in a particular category. Both regressions include category and day fixed effects and marketing controls, and hence mirror the traffic regression (Eq. 1).

We start by implementing the analysis based on all product locations for each category. In other words, we define visit timing as the point in time at which a consumer first passes any location in the store associated with the particular category. The results using both minutes elapsed and the fraction of shopping time elapsed are reported in columns (1) and (2) of Table 9. Columns (3) and (4) replicate the same regressions, but base the visit timing only on the primary locations of each category. Across all four specifications, we find effects of feature advertising that are consistently small in magnitude and mostly insignificant. Take, for example, the results in column (1). According to the (insignificant) point estimates, a one-standard-deviation increase in the number of features (eight additional features) in a particular category delays the visit to the category by 0.016 minutes (i.e., about 1 second) or shifts the visit timing back by 0.05 percentage points relative to the total time spent in the store.Footnote 25

Table 9 The impact of advertising on visit timing and dwell-time

The marginally significant effect in column (4) is similarly small in magnitude and does not constitute an economically meaningful shift in the timing of the category visit.

Finally, advertising might only affect a small set of consumers who are planning to purchase within the category due to the feature ad. When analyzing the visit timing of all consumers in the store, the unaltered behavior of the majority of visitors to the store might mask a significant effect for this group of consumers. We hence isolate the group of consumers who are most likely to be affected, by computing the daily average time of a category visit based only on consumers who purchase in the specific category. The results from regressions based on this measure of visit timing are reported in columns (5) and (6) of Table 9. We again find a null effect of feature advertising on visit timing, and the confidence intervals do not contain economically large effect sizes.Footnote 26

We hence conclude feature advertising does not influence when consumers visit a specific category.

A.5 The impact of feature advertising on dwell-time

In this section, we provide further details on the impact of advertising on dwell-time in front of the category. Based on the path data, we calculate the total time a consumer spends on traffic points belonging to the specific category for each category in which she purchased during a given shopping trip. Similar to other parts of our analysis, we aggregate this variable to the category/day level and regress the average daily dwell-time onto the number of features (and control variables). Results from this regression are reported in column (7) of Table 9 and show a small and insignificant effect. We note that dwell-time is measured in seconds, and average daily dwell-time has a mean (standard deviation) of 53 (41) seconds. A one-standard-deviation shift in the number of features changes dwell-time by only 0.29 seconds (0.29 = 0.036 * 8).

We note that we would ideally like to measure the time a consumer spent contemplating which product to buy in the category. Total time spent in the vicinity of a given category is likely to be a noisy measure of search time (see Seiler & Pinna (2016) for a detailed discussion of the measurement error associated with path-tracking-based dwell-time measures). We therefore assess robustness of the null effect to using an alternative measure that only captures the amount of time spent near the specific product that was picked up (rather than the entire category). Results from this regression are reported in column (8) of Table 9 and also yield an insignificant result and an effect size that is small in magnitude.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Seiler, S., Yao, S. The impact of advertising along the conversion funnel. Quant Mark Econ 15, 241–278 (2017). https://doi.org/10.1007/s11129-017-9184-y

Download citation

Keywords

  • Advertising
  • Conversion funnel
  • Spillovers
  • Path-tracking data

JEL Classification

  • L81
  • M31
  • M37