Auditing the Grid-Based Placement of Private Label Products on E-commerce Search Result Pages

TL;DR

The paper addresses fairness concerns surrounding private-label (PL) promotion in e-commerce search by auditing grid-based SERPs on Amazon.in and Flipkart. Using 101 queries collected over 10 days plus a 68-participant MTurk survey, it quantifies PL ad share (Amazon ~11.7% overall, up to 15.16% on the first SERP; Flipkart ~4.5%), and delineates platform-specific PL placement strategies in a grid layout. The study reveals that Amazon concentrates PL ads in prominent positions and yields substantial nudging effects (3x more clicks when PLs follow the observed strategy), while Flipkart shows a weaker, more heterogeneous pattern. These findings have regulatory relevance under frameworks like the DMA and antitrust scrutiny, and the authors propose a replicable audit approach to measure PL exposure and its impact on customers and sellers across platforms.

Abstract

E-commerce platforms support the needs and livelihoods of their two most important stakeholders -- customers and producers/sellers. Multiple algorithmic systems, like ``search'' systems mediate the interactions between these stakeholders by connecting customers to producers with relevant items. Search results include (i) private label (PL) products that are manufactured/sold by the platform itself, as well as (ii) third-party products on advertised / sponsored and organic positions. In this paper, we systematically quantify the extent of PL product promotion on e-commerce search results for the two largest e-commerce platforms operating in India -- Amazon.in and Flipkart. By analyzing snapshots of search results across the two platforms, we discover high PL promotion on the initial result pages (~ 15% PLs are advertised on the first SERP of Amazon). Both platforms use different strategies to promote their PL products, such as placing more PLs on the advertised positions -- while Amazon places them on the first, middle, and last rows of the search results, Flipkart places them on the first two positions and the (entire) last column of the search results. We discover that these product placement strategies of both platforms conform with existing user attention strategies proposed in the literature. Finally, to supplement the findings from the collected data, we conduct a survey among 68 participants on Amazon Mechanical Turk. The click pattern from our survey shows that users strongly prefer to click on products placed at positions that correspond to the PL products on the search results of Amazon, but not so strongly on Flipkart. The click-through rate follows previously proposed theoretically grounded user attention distribution patterns in a two-dimensional layout.

Figures (4)

• Figure 1: First SERP for the Amazon e-commerce platform. The different markers are -- ① Search bar for typing in the search query, ② A typical private label (PL) product being shown in the sponsored position, ③ A typical third-party (3P) product being shown in the sponsored position, ④ A typical third-party (3P) product being shown in the organic position.
• Figure 2: Counts of the Private Label (PL) products and advertisement positions (highlighted by blue rectangles) on the first SERP of the Amazon and Flipkart platforms. PL products are present on the entire page, irrespective of the platform. On Amazon, the maximum occurrences of PL products are on the advertisement positions. On Flipkart, a higher count of PL products is shown in the top half (first 4 rows) of the SERP.
• Figure 3: Orders for all queries on the websites with original SERPs for Amazon ($W_A^O$) and Flipkart ($W_F^O$). For Amazon, the orders are clustered toward the top whereas they are distributed throughout the SERP for Flipkart, but with a higher ratio on the last column. This indicates that placing PLs at such positions can lead to more attention and orders for the same. These observation also falls in line with our observation of PL product placement in Figure \ref{['fig:pl_pos_ad_pos']}.
• Figure 4: Comparison of orders between queries where the PL products are placed randomly and where the PL products are placed as per the original distribution observed in the collected data. The uptick in number of clicks and orders for Amazon PLs further underpins the effectiveness of their PL promotion strategy. For Flipkart, the drop is marginal.