Digital lead generation platforms: Rightsizing the seller base
Bibliographic record
Abstract
This article introduces Digital Lead Generation Platforms (DLGPs), an increasingly popular way to allow users to explore products from multiple retailers. Despite their growing influence, little is known about how DLGPs can manage their effectiveness or profitability. Here, we discuss their distinctive and salient aspects relative to other types of digital retailing, and explore data-centric methods to better manage the size of their seller base. Specifically, using a rich proprietary dataset, we examine drivers of user click propensity (UCP), focusing on a key issue for platform managers: is consumer response better when there are “endless aisles,” or should the number of sellers active at a given time (the “base of sellers”) be somehow limited in a category-specific manner? Based on a flexible nonparametric model, our results suggest that base of sellers has an inverted-U relationship with UCP, with potentially severe consequences for seller underpopulation, one that is masked when endogeneity is not corrected for. Intriguingly, we do not find such an effect for the number of offers, which might be expected based on “overchoice”. Although this general shape for base of sellers is apparent in all 10 product categories studied, there is substantial variation in how often each is suitably populated, with Cars over 60 % of the time and Mobile Accessories only 5 %. These findings have important implications for both DLGP managers and sellers: platform operators can enhance their revenue potential by “rightsizing” their seller base, while sellers may be able to improve clickthrough rates by timing their involvement based on contemporaneous competition in their particular categories.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.030 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".