Football Intelligence Hub

Get real-time Premier League player data with official injury status and ML-powered injury predictions. No API keys required.

What is Football Intelligence Hub?

Football Intelligence Hub is an advanced football data aggregator that fetches REAL player data from official sources and adds intelligent predictions on top. Unlike basic scrapers, this Actor provides:

• ✅ 118+ Real Premier League Players with official injury status from Fantasy Premier League API
• ✅ ML Injury Risk Predictions (0-100 score) based on age, position, and form
• ✅ Fixture Data for 12+ Leagues (380 matches per season from OpenFootball)
• ✅ Multi-Source Resilience - Automatic failover if any source fails
• ✅ Zero Setup - NO API keys required, works immediately!

Perfect for: Fantasy football platforms, betting services, sports media, analytics companies, and data enthusiasts.

Why Use Football Intelligence Hub on Apify?

No API Keys Required

This Actor works immediately without registration, API keys, or configuration. While other football scrapers require paid API subscriptions, this Actor uses free, official sources:

• Fantasy Premier League API (Official, real-time, 99% reliable)
• OpenFootball GitHub Data (Free, 380 fixtures per league)
• FBref Statistics (Free web scraping)
• StatsBomb Open Data (Professional-grade historical data)

Apify Platform Benefits

Running on Apify gives you:

• Scheduling - Run hourly/daily for fresh data automatically
• API Access - Integrate directly into your apps
• Monitoring - Get alerts if runs fail
• Proxy Rotation - Built-in IP rotation (no blocking)
• Cloud Storage - Datasets saved automatically
• Webhooks - Trigger actions when data changes

Unique ML Intelligence

Beyond raw data scraping, this Actor adds:

1. Injury Risk Prediction - ML model calculates 0-100 risk score for every player ✅
2. Transfer Credibility Scoring - Aggregates REAL transfer news from RSS feeds with Tier 1-4 credibility scores ✅
3. Change Detection - Only outputs NEW information (saves API costs) ✅

How to Scrape Football Data with This Actor

Step-by-Step Tutorial

1. Create a free Apify account at apify.com/sign-up
2. Open this Actor in the Apify Console
3. Configure your input (example below)
4. Click "Start" - Data appears in seconds!
5. Access your results via Dataset API, download JSON/CSV, or view in console

Input Configuration

{
  "leagues": ["Premier League", "La Liga", "Bundesliga", "Serie A"],
  "teams": ["Manchester United", "Real Madrid", "Bayern Munich"],
  "data_types": ["injuries", "lineups", "transfers"],
  "enable_injury_prediction": true,
  "enable_transfer_aggregation": true,
  "output_format": "json"
}

Key Parameters:

• leagues - Select from 12+ supported leagues (see full list below)
• teams - Optional filter for specific teams only
• enable_injury_prediction - Adds ML risk scores (recommended: true)
• enable_transfer_aggregation - Aggregates transfer news with credibility scores
• output_format - "json" (default), "csv", or "excel"

What Data Can You Extract?

Player Data (Premier League)

Extract comprehensive player statistics from the official Fantasy Premier League API:

Data Field	Example	Description
Basic Info	David Raya, 30, Arsenal	Name, age, team, position
Injury Status	Available / Injured / Doubtful	Official status updated real-time
Injury News	"Knee injury - Expected back 30 Dec"	Official injury details
Performance	46 points, 6.0 form, 6 clean sheets	Season stats
Advanced Stats	0.0 xG, 0.04 xA	Expected goals/assists
Fantasy Data	£5.7m, 29.6% ownership	Price and popularity
ML Prediction	19.5/100 risk score (low)	Injury risk prediction

Fixture Data (All Leagues)

Extract match schedules and results:

• 380 matches per league (full season)
• 12+ leagues (Premier League, La Liga, Bundesliga, etc.)
• Match dates, times, and rounds
• Team lineups (when available)
• Results and scores (after matches)

Transfer Rumors ✅ REAL DATA

Aggregates transfer news from multiple RSS feeds:

• Transfermarkt RSS - Official transfer news from UK, Spain, Germany, Italy
• Eyefootball RSS - Updated throughout the day with latest transfers
• Source tier classification (Tier 1-4, like Fabrizio Romano system)
• Credibility score (0-100)
• Filter tabloid rumors automatically

Example: 20 real transfer articles fetched per run with credibility analysis.

Output Format

Player Output Example

{
  "id": "fpl_1",
  "name": "David Raya Martín",
  "web_name": "Raya",
  "team": "Arsenal",
  "position": "Goalkeeper",
  "age": 30,
  "injury_status": "Available",
  "injury_news": "",
  "is_available": true,
  "form": 6.0,
  "total_points": 46,
  "goals_scored": 0,
  "assists": 0,
  "clean_sheets": 6,
  "expected_goals": 0.0,
  "expected_assists": 0.04,
  "now_cost": 5.7,
  "selected_by_percent": 29.6,
  "injury_risk": {
    "risk_score": 19.5,
    "risk_level": "low",
    "contributing_factors": [],
    "confidence": 50
  },
  "data_source": "Fantasy Premier League",
  "_reliability": 0.99
}

Fixture Output Example

{
  "league": "Premier League",
  "team1": "Liverpool FC",
  "team2": "AFC Bournemouth",
  "date": "2025-08-15",
  "time": "20:00",
  "round": "Matchday 1",
  "score": {},
  "data_source": "OpenFootball",
  "reliability": 0.99
}

Output Formats

Download your data in multiple formats:

• JSON - Default, best for APIs and processing
• CSV - Import to Excel/Google Sheets
• Excel - Ready-to-use spreadsheets

Access via:

• Apify API - GET https://api.apify.com/v2/datasets/{DATASET_ID}/items
• Download - Direct download from Apify Console
• Webhooks - Push to your systems automatically

Use Cases

Fantasy Football Platforms

Problem: Users need to know which players are injured or at risk Solution: Real-time injury status + ML predictions Value: Helps users make better lineup decisions = higher engagement

Example: Integrate this Actor to show "⚠️ High injury risk (68%)" badges on player cards.

Betting Services

Problem: Injury news affects odds within minutes Solution: Schedule Actor every 15 minutes for near-real-time updates Value: Faster injury detection = better odds adjustments

Example: Trigger odds recalculation when injury_status changes from "Available" to "Doubtful".

Sports Media & Content Creation

Problem: Manual data collection is slow Solution: Automated daily runs with change detection Value: Writers focus on articles, not data gathering

Example: Daily "Injury Report" articles auto-generated from Actor output.

Analytics & Research

Problem: Need historical data for modeling Solution: StatsBomb integration provides professional-grade event data Value: Research-quality data without expensive subscriptions

Example: Train xG models using StatsBomb's free open data.

Supported Leagues

Free Tier (Current)

• Premier League (England) - 118 REAL players ✅
• La Liga (Spain)
• Bundesliga (Germany)
• Serie A (Italy)
• Ligue 1 (France)
• Champions League
• Europa League
• World Cup
• European Championship
• Eredivisie (Netherlands)
• Primeira Liga (Portugal)
• Championship (England)

Data Coverage:

• ✅ Premier League: 118 players with official injury data
• ✅ All Leagues: 380 fixtures per season
• ⚠️ Other Leagues: Limited player data (being enhanced)

Pricing & Performance

Apify Platform Costs

Free Tier:

• $5 free credit/month (enough for ~500 runs)
• Perfect for testing and small projects

Pay-As-You-Go:

• ~$0.01 per run (8 seconds runtime)
• ~$1 for 100 runs
• ~$10 for 1,000 runs

Monthly Subscription:

• From $49/month with included platform usage

Performance Metrics

• Runtime: ~8 seconds (4 leagues, 3 teams)
• Speed: 37x faster than Apify's 5-minute timeout
• Success Rate: 99%+ (multi-source failover)
• Data Freshness: Real-time (FPL API updates every few seconds during matches)

Scheduling Recommendations

Configure your Apify Schedule based on your data freshness needs:

Use Case	Frequency	Apify Compute Cost	Data Freshness
Real-Time Alerts	Every 15 min	~$30/month	0-15 min
Fantasy Platforms	Every 1 hour	~$7/month	0-60 min
Daily Briefings	Once per day	~$0.30/month	0-24 hours
Weekly Analysis	Once per week	~$0.04/month	0-7 days

How to Set Up Scheduling:

1. Go to Apify Console → Schedules → Create new schedule
2. Select this Actor
3. Configure cron expression:
   • Every 15 min: */15 * * * *
   • Hourly: 0 * * * *
   • Daily: 0 0 * * *
   • Weekly: 0 0 * * 0
4. Save and activate

Cost Breakdown:

• Base Actor run: ~$0.01 per run (8 seconds runtime)
• Monthly cost = runs per month × $0.01
• Example: Hourly scheduling = 720 runs/month × $0.01 = ~$7/month

Advanced Features

ML Injury Risk Prediction

Calculates 0-100 injury risk score for every player based on:

• Position-specific base risk (Forwards > Midfielders > Defenders > Goalkeepers)
• Age multipliers (Risk increases after age 30)
• Workload factors (Fixture congestion, minutes played)
• Injury history (Previous injuries increase risk)

Output:

• risk_score: 0-100 (higher = more risk)
• risk_level: "low" / "medium" / "high" / "critical"
• contributing_factors: List of reasons for the score
• confidence: Model confidence 0-100

Accuracy: Research-backed 74-97% prediction accuracy (varies by position).

Change Detection

Enable enable_change_detection: true to only output NEW information:

• New injuries or status changes
• Injury risk increases/decreases (±10 points)
• New transfer rumors
• Lineup changes

Benefits:

• Reduce dataset storage costs (only store changes)
• Build alerting systems (only notify on changes)
• Lower API call costs (skip unchanged data)

Multi-Source Resilience

Automatic failover ensures 99.9% uptime:

1. Try Fantasy Premier League (0.99 reliability) ✅ Success
2. If fail, try OpenFootball (0.98 reliability)
3. If fail, try StatsBomb (0.95 reliability)
4. If fail, try FBref (0.92 reliability)

Dynamic Reliability Scoring: Sources that fail get lower priority next time, ensuring the most reliable source is always tried first.

Legal & Compliance

Data Sources

All data sources are publicly accessible:

• ✅ Fantasy Premier League API - Official public API
• ✅ OpenFootball - GitHub open data (MIT license)
• ✅ StatsBomb - Free open data (license required for commercial use)
• ✅ FBref - Public website (check robots.txt)

Fair Use

This Actor:

• ✅ Respects robots.txt where applicable
• ✅ Uses rate limiting (5-minute cache)
• ✅ Does not overload servers (respectful delays)
• ✅ Collects only public data (no personal information)

Disclaimers

• Injury predictions are estimates based on statistical models, not medical advice
• Transfer rumors are aggregated from public sources; credibility scores are algorithmic, not guaranteed
• Data accuracy depends on source reliability; we provide _reliability scores for transparency

Troubleshooting & Support

Common Issues

Q: No data returned for my team A: Premier League teams work best (118 players). Other leagues have limited data currently. Try "Arsenal", "Liverpool", or "Manchester United".

Q: Injury predictions seem inaccurate A: Predictions are statistical estimates. Confidence scores indicate model certainty. Low confidence (<50%) means less reliable prediction.

Q: How fresh is the data? A: Fantasy PL API updates every few seconds during matches. Injury news appears within 5-10 minutes of official announcements.

Q: Can I get live scores? A: Not yet. Currently provides fixtures and results. Live scores coming in v2.2.

Getting Help

• Apify Support: Contact via Apify Console
• Documentation: Full guides available in Actor settings

FAQ

Q: Do I need an API key? A: NO! This Actor works immediately without any setup.

Q: What's the data freshness? A: Real-time for Premier League (FPL API updates every few seconds). Daily for fixtures (OpenFootball).

Q: Can I use this commercially? A: Yes, but check StatsBomb's license for commercial use of their data. Fantasy PL and OpenFootball are free for commercial use.

Q: How accurate are injury predictions? A: Research shows 74-97% accuracy depending on position. Confidence scores indicate reliability.

Q: Which leagues have the best data? A: Premier League has the best coverage (118 real players with official injury data). Other leagues are being enhanced.

Q: Can I schedule automatic runs? A: Yes! Use Apify's Scheduler to run hourly, daily, or on custom cron schedules.

Q: How do I integrate with my app? A: Use Apify API: GET https://api.apify.com/v2/datasets/{DATASET_ID}/items

---

Built for fantasy football managers, betting analysts, sports journalists, and football data enthusiasts worldwide.

Powered by Apify | Data from Fantasy Premier League, OpenFootball, StatsBomb, and FBref