StubHub
dynamic price recommendation engine for sellers
In 2019, StubHub launched Pricing Assistant, an engine that recommends and automatically adjusts sellers' ticket prices according to the market and the approach of the event, on nearly twenty years of data.
Objective
Help sellers set a price that maximizes the probability of sale, and thus the transaction volume and the commissions taken by the marketplace.
The deployment
Pricing Assistant, rolled out in North America from April 2019 and officially announced in November 2019, is an optional toggle: once activated, the algorithm adjusts ticket prices up or down as the market evolves and the event date approaches. It draws on nearly twenty years of sales data, prices by seat and section, recent comparable transactions, and current market activity, and gives a recommended price along with a high and low range. The Sell It Now feature, launched in parallel, allows an immediate sale at a guaranteed price.
Results Proof C
Official StubHub press release and specialized ticketing press describing the tool by name, its operation, and its scope. No public financial result figure, hence a C level.
How it works
Documented architectureThe stack in detail
- outil Pricing Assistant seller toggle: recommended price with a high and low range, then automatic adjustment as the market and the event approach
- outil Moteur de recommandation de prix in-house model drawing on nearly twenty years of sales data, prices by seat and section, and recent comparable transactions
- outil Sell It Now immediate sale at a guaranteed price, launched in parallel with Pricing Assistant
How it runs, concretely
For ops teams-
1Activation by the seller customer
The seller activates Pricing Assistant on their listed tickets.
-
2Reading the market AI
The algorithm reads prices by section and seat, recent comparable transactions, and current activity.
-
3Price adjustment AI
It raises or lowers the price as the market evolves.
-
4Reduction as the event approaches AI
It lowers the price as the date approaches to maximize the probability of sale.
Market activity and recent comparable transactions by seat and section. Without liquidity of comparables, the price recommendation loses its reliability.
How your customers perceive this type of use
Sourced studiesLe pricing algorithmique est le terrain le plus inflammable : 68% des consommateurs disent se sentir leses quand les marques utilisent le pricing dynamique et 80% jugent plus dignes de confiance les marques aux prix constants (Gartner, 2024). L'equite percue varie selon le secteur : le pricing dynamique n'est juge juste que par 33% a 40% des repondants selon qu'il s'agit de concerts ou de cinemas (YouGov, 17 marches). Le prix personnalise par les donnees individuelles est le plus rejete : 47% des Americains s'y opposent fermement (Consumer Reports, 2024).
Acceptance conditions
- La constance des prix comme signal de confiance : 80% jugent plus fiables les marques aux prix stables (Gartner 2024)
- Le secteur conditionne l'equite percue : le pricing dynamique est mieux tolere pour les cinemas (40% le jugent juste) que pour les concerts (33%) (YouGov 2024)
Red lines
- Le pricing dynamique percu comme abus : 68% se sentent leses (Gartner 2024)
- Le prix individualise a partir des donnees personnelles : 47% d'opposition ferme (Consumer Reports 2024)
- Les frais caches et hausses imprevues, vecus par 79% des consommateurs sur un an et associes a la perte de confiance (Gartner 2024)
Sources: Gartner 2024 · YouGov 2024 · Consumer Reports 2024
How to replicate
Inference, not sourcedData prerequisites
- transaction history by seat and section
- real-time market activity
- comparables by event type
Org prerequisites
- marketplace with seller inventory
- tool to expose the recommendations
- guardrail rules on prices
Possible stack
- in-house price recommendation engine
- sale probability model
- market data feed
The plan, step by step
- Step 1Consolidate the history: transactions by event, seat, and section, with comparablesDeliverable: Cleaned and structured transaction dataset
- Step 2Model the probability of sale by price level from the comparablesDeliverable: Model evaluated in backtest on past sales
- Step 3Define the guardrails: price bounds, ranges, and rules as the date approachesDeliverable: Documented and testable pricing policy
- Step 4Expose the tool to sellers opt-in (toggle) on a pilot segmentDeliverable: Tool active with pilot sellers, sell-through measured
- Step 5Compare sale rate and listing revenue with and without the tool, adjust then open to allDeliverable: Quantified reading of sell-through and general rollout
First step: Build a per-price sale probability estimate from the history of comparable transactions.
The same pattern, proven in other industries
Airbnb
dynamic price suggestion to sellers (host pricing)
Delta Air Lines
AI dynamic pricing (yield management)
Shopee
AI automation of seller ad campaigns
Sources
- S1 StubHub launches Pricing Assistant and Sell It Now to make it even easier to sell tickets to live events Primary archive pending
- S2 StubHub Announces New Tools, Including Sell It Now Feature Secondary archive pending
- S3 StubHub Adds Dynamic Ticket Pricing Secondary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.