Key Features
- Personalised Bet Recommendations: Offers tailored suggestions based on individual player preferences, adapting dynamically to reflect each player’s unique betting behaviour and history. Powered by AI, the engine refines its understanding over time, ensuring increasingly precise and relevant recommendations.
- Prioritised Engagement: Presents players with the most relevant market options, ordered by importance. This prioritisation leverages historical player data, current trends, and event-specific insights, ensuring recommendations are timely and resonate with player interests.
Practical Use Cases
- Dynamic Content for Personalised Dashboards
Integrate personalised bet recommendations directly into player dashboards, offering relevant and enticing betting opportunities that enhance engagement and keep players interacting on the platform. - Targeted Email Campaigns with Personalised Recommendations
Increase email campaign effectiveness by embedding personalised bet recommendations. Players are more likely to open, engage with, and act on emails featuring bets aligned with their preferences, driving higher playera ctivity. - Retention and Reactivation Strategies via Personalised Banners
Use personalised banners to re-engage players with decreased activity.
Banners featuring bets tailored to individual preferences communicate directly with players based on their historical behaviour, increasing the likelihood of reactivation. - VIP and Loyalty Personalisation for Exclusive Experiences
Enhance VIP and loyalty programmes by providing tailored bet recommendations in exclusive sections. Personalised content in designated areas strengthens VIP player loyalty and contributes to a premium, individualised experience.
Business Benefits and Operational Impact
- Player-Centric Engagement: A focus on personalisation ensures each platform interaction is tailored to individual preferences, enhancing player-centric engagement.
- Higher Player Satisfaction: By aligning recommendations with player interests, the platform increases satisfaction as players are presented with bets that resonate with their preferences.
- Improved Retention: Personalised experiences foster stronger connections, improving retention rates and encouraging long-term player loyalty.
- Enhanced Bet Relevance: Players are more likely to engage with bets that match their interests, boosting betting activity and providing a more enjoyable experience.
- Increased Conversion Rates: Targeted communications, dynamic content, and effective cross-selling increase conversion rates by prompting players to act on tailored recommendations.
- Streamlined Marketing Strategies: Personalised bet recommendations enable more targeted and efficient marketing, aligning outreach with player behaviour and driving both satisfaction and loyalty.
How Single Bet Recommendations Work
The personalised recommendation engine leverages advanced player behaviour analysis and algorithmic processing to deliver tailored betting suggestions. By combining detailed insights into individual preferences with predictive modelling, the system ensures every recommendation aligns with player interests and market trends, enhancing engagement and satisfaction.
Player Behaviour Analysis- In-Depth Exploration: The engine analyses player behaviour, considering historical bets, preferred sports, competitions, and specific event types.
- Individualized Insights: This analysis goes beyond surface-level trends, delving into individual player preferences and betting patterns.
- Predictive Modelling: These algorithms predict and prioritize potential bets based on a comprehensive understanding of player preferences, encompassing recent trends, market dynamics, and individualized parameters.
API Request and Response Structure
Request Structure
- Endpoint:
- Base URL: Client-specific endpoint URL (provided separately)
- HTTP Method:
GET
- Headers:
Content-Type: application/json
Request Parameters
Parameter | Type | Description |
id_clients | string[] or string | Target client ID(s) for recommendations |
top_n | integer | Number of recommendations to return per client |
Request Example
{
"id_clients": [1011377, 1023029],
"top_n": 3
}
- Default response returns 250 market-level recommendations if
top_n
is not specified - Supports both single client ID (string) and multiple client IDs (array)
Response Structure
Base Response Schema
Field | Type | Description |
items | array | Collection of client recommendations |
Item Object
Field | Type | Description |
id_client | string | Unique client identifier |
bet_recommendations | array | List of recommended bets |
bet_recommendations Object
Field | Type | Description |
eventTime | string | Event timestamp (format: YYYY-MM-DD HH:MM:SS) |
SportName | string | Sport category |
TournamentName | string | Tournament identifier |
MarketName | string | Market type |
rating | float | Recommendation score (exponentially scaled) |
rec_id | string | Unique recommendation identifier |
Error Response - Missing Clients
Field | Type | Description |
missing_clients.missing_client_ids | string[] | Array of client IDs not found |
missing_clients.message | string | Error description |
- Rating values use exponential scaling (e.g., 0.3397 > 2.978e-1)
- Minimum requirement of 10 bets for client recommendations
Responses Examples
Successful Response
{
"items": [{
"id_client": "1023029",
"bet_recommendations": [{
"eventTime": "2023-11-01 20:15:00",
"SportName": "Football",
"TournamentName": "England EFL Cup",
"MarketName": "DoubleChance",
"rating": 1.0298758529188778,
"rec_id": "12023110140397012"
}]
}]
}
Response with Missing Clients
{ "items": [...],
"missing_clients": {
"missing_client_ids": ["2345321", "2345673"],
"message": "We could not find any recommendations for the missing clients. This may be due to these clients being new, with fewer than 10 bets, or because these client IDs do not exist in our database."
}
}
Invalid Request Error (Empty client array)
{
"error": "The 'id_clients' field is missing or not a valid array."
}