Betby Personalisation at Peak Traffic
Danil Emelyanov, Head of AI at BETBY, takes us inside the workings of AI-powered sportsbooks and reveals how they must perform under the intense pressure of events like the FIFA World Cup. Over the course of this three-part mini-series, we’ll explore how AI systems enable operators to tailor the UX for each user, predict risk before it happens, and ultimately maximise acquisition and retention during critical moments.
In this first article, Emelyanov discusses how BETBY’s AI-powered UX uses real-time behavioural data and derived features to create a personalised, adaptive experience, offering a distinct advantage over traditional AI systems that fail to adjust at a deeper level during major events.
HOW PROPER AI-DRIVEN UX PERFORMS UNDER WORLD CUP PRESSURE Few sporting events put sportsbook platforms under as much pressure as the World Cup. Te World Cup brings surges in traffic, shifts in user attention, and emotional betting behaviour. Many users will interact with sportsbooks for the first time, and even regular bettors will experience heightened emotions and different patterns of engagement. For operators, real-time UX adaptation is essential to maximise acquisition and retention during this high-pressure event.
At BETBY, we rely on real-time behavioural data to provide a state- aware UX that adapts to the momentum and emotional shifts of users. Let’s explore how BETBY’s AI-driven UX stands out in the World Cup environment, and how it contrasts with traditional static systems that often fail to adjust to rapidly changing user behaviour.
UNDERSTANDING USER BEHAVIOUR THROUGH REAL-TIME DATA Rather than relying only on demographic data, such as age, gender, or country, BETBY tracks behavioural betting signals, actions like bet placements, session dynamics, and market types. Tis allows us to gain insights into a user’s engagement level and emotional state.
24
Core signals we track: u
u
Bet Placement Events (timestamp, odds, stake size): Tese show user intent and engagement
Bet Outcomes (win/loss, settlement time): Signals the user’s confidence
u
Session Dynamics (session length, bet cadence, navigation): Provides insight into user engagement
u
Temporal Patterns (time since last bet, time between bets): Indicates user momentum
u
Portfolio Structure (single bets vs. accumulators): Highlights user betting preferences
u
Risk Appetite Proxies (stake volatility, odds distribution): Shows the user's current risk level
When a user places a high-stakes live bet during an exciting World Cup moment, BETBY’s AI identifies the surge in excitement and adapts the interface to prioritise high-intensity live markets like “next goal scorer” or “goals in the next 10 minutes.”
Opposed to that, a traditional system often offers generic pre-match markets aligned with global trends and demographic preferences, like “match winner” or “total goals, ” failing to match the user’s emotional engagement in the moment.
DERIVED FEATURES ENHANCE UX WITH DEEPER INSIGHTS However, in addition to core signals, BETBY’s derived features allow the system to fine-tune UX adaptation based on deeper insights into user behaviour. Tese features include:
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102
