FanDuel
personalization of the betting offer driven by AI pricing, with a genAI discovery assistant
FanDuel personalizes its betting offer with Your Way, a parlay builder priced by its AI pricing models, complemented by the AceAI genAI assistant: according to Flutter's Q4 2024 results, roughly 1 in 20 customers used Your Way at the 2025 Super Bowl and 90 percent of them placed bets impossible without this personalization, on a day of 3 million active customers and 470 million dollars wagered.
Key points
- Personalization of the betting offer through Your Way, with the AceAI genAI discovery assistant.
- In-house Flutter pricing and risk, multi-LLM AceAI, numberFire statistics.
- At the 2025 Super Bowl, 1 in 20 customers used Your Way, 90% placed otherwise impossible bets.
- Evidence level A, confirmed active status.
Objective
Broaden and personalize the betting offer to capture wagers impossible with a standard catalog, drawing on proprietary pricing models and an AI-assisted discovery layer.
The deployment
Your Way is FanDuel's customizable parlay product, rolled out in every state for the NFL over the quarter and put to the test at the 2025 Super Bowl. It gives the customer more room to build their parlays, drawing on Flutter's proprietary pricing and risk management capabilities to offer near-unlimited combinations while holding the margin. According to Flutter's Q4 2024 results, roughly 1 in 20 customers used Your Way during the Super Bowl, and 90 percent of them placed bets they could not have made without these personalization options. On Super Bowl day, FanDuel counted 3 million active customers, 17.7 million bets, and 470 million dollars wagered. In addition, FanDuel launched AceAI, a conversational assistant that combines several large language models with the sportsbook infrastructure and numberFire data: the customer can analyze player and team statistics, discover betting ideas, and build their parlays in a single conversation, with adding to the bet slip left to the customer.
Results Proof A
Figures from Flutter's Q4 2024 financial results (published March 4, 2025) and attributed to CEO Peter Jackson, hence level A. Trade press corroborates the adoption of Your Way at the Super Bowl and FanDuel's activity.
How it works
Documented architectureThe stack in detail
- llm AceAI (multi-LLM) Conversational discovery assistant that combines several large language models with the sportsbook infrastructure; the exact models are not named publicly
- outil Moteur de pricing et de risque Flutter Proprietary pricing and risk management models that price the Your Way parlays in real time and cap the exposure
- outil numberFire FanDuel's sports analytics platform that feeds AceAI player and team statistics
- plateforme FanDuel Sportsbook Sportsbook application that exposes the Your Way parlay builder and the AceAI conversation
How it runs, concretely
For ops teams-
1Building the parlay customer
The customer assembles a personalized parlay beyond the standard catalog, alone or through AceAI.
-
2Pricing and risk control AI (pricing / risk)
The proprietary models price the parlay and cap the exposure while holding the margin.
-
3Assisted discovery AI (LLM)
AceAI analyzes statistics and trends through numberFire and offers betting ideas in the conversation.
-
4Adding to the bet slip customer
The customer confirms and adds the selection themselves; the AI never places the bet on their behalf.
The pricing and risk management on near-unlimited combinations. Without a solid risk model, an open parlay offer exposes the operator to negative-margin combinations.
How your customers perceive this type of use
Sourced studiesLe paradoxe est documente des deux cotes : 71% des consommateurs attendent des interactions personnalisees et 76% sont frustres quand elles manquent (McKinsey, 2021), mais 75% declarent ne pas acheter aupres d'organisations auxquelles ils ne confient pas leurs donnees (Cisco, 2024). La « creepy line » est localisee : messages recus quelques secondes apres une recherche et suivi de localisation sont les pratiques qui mettent le plus mal a l'aise (Periscope by McKinsey, 2019).
Acceptance conditions
- La confiance dans le traitement des donnees precede l'achat : 75% ne achetent pas sans elle (Cisco 2024)
- Un cadre legal protecteur rassure : 59% des consommateurs disent que des lois fortes sur la vie privee les rendent plus a l'aise pour partager des informations dans des applications IA (Cisco 2024)
- La personnalisation elle-meme est attendue quand elle est consentie : environ la moitie des consommateurs (US 55%, UK 52%) disent s'inscrire souvent ou parfois a des services personnalises (Periscope by McKinsey 2019)
Red lines
- Le message declenche quelques secondes apres une recherche ou un achat : deuxieme ou troisieme cause de malaise selon les pays (Periscope by McKinsey 2019)
- Le suivi de localisation percu comme de la surveillance : 40% de malaise en Allemagne et au Royaume-Uni (Periscope by McKinsey 2019)
- Le mesusage des donnees personnelles par l'IA, devenu la premiere inquietude des consommateurs, a 53% et en hausse (Qualtrics 2025)
Sources: McKinsey & Company 2021 · Periscope by McKinsey 2019 · Cisco 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- granular catalog of markets and props
- parlay correlation and pricing model
- sports statistics data for discovery
Org prerequisites
- trading and data science team for risk pricing
- responsible gambling compliance and local licensing
- AI Act guardrails on the conversational assistant
Possible stack
- parlay pricing engine
- LLM assistant connected to the product data
- app with a parlay builder
The plan, step by step
- Step 1Frame the data: granular catalog of markets and props, history of odds and outcomes to model the correlations between selections.Deliverable: Market reference and usable correlation dataset
- Step 2Build and backtest the parlay pricing and risk model on one sport, with exposure limits per combination.Deliverable: Pricing engine validated in backtest, with risk-capping rules
- Step 3Expose a personalized parlay builder in the app on that sport, priced in real time by the engine.Deliverable: Builder in production on one sport, priced on the fly
- Step 4Test in real conditions on a high-traffic event and measure adoption, share of bets made possible, and margin holding.Deliverable: Quantified adoption / margin review on the test event
- Step 5Add the conversational discovery layer connected to the statistics, with adding to the bet slip left to the customer and responsible gambling guardrails.Deliverable: Discovery assistant in beta, compliant with local rules
First step: Build a parlay pricing and correlation model, then expose a personalized builder on one sport before adding a conversational layer.
The same pattern, proven in other industries
King
ML recommendation of personalized offers and bundles
Roblox
ML discovery engine plus ML economy (personalized pricing and storefronts)
Supercell
ML personalization of in-game offers (which card or offer to serve)
Sources
- S1 Flutter Entertainment Reports Fourth Quarter 2024 Financial Results Primary archive pending
- S2 Flutter touts growth, particularly in US despite tough NFL season Established press archive pending
- S3 Meet AceAI: FanDuel's AI-Powered Sports Betting Assistant Interested party archive pending
- S4 How FanDuel's AI Chatbot, AceAI, Is Reshaping Sports Betting 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.