Getting Started with BrainPredict Controlling

# Your API key will look like this:
bp_controlling_live_1234567890abcdef1234567890abcdef

# Keep it secure - never commit to version control!

# Python
pip install brainpredict-controlling

# Node.js
npm install @brainpredict/controlling

# Java
mvn install brainpredict-controlling

# PHP
composer require brainpredict/controlling

# Python
from brainpredict import ControllingClient

client = ControllingClient(api_key="bp_controlling_live_xxx")

# Forecast performance for next 12 months
forecast = client.performance.forecast(
    historical_months=24,
    forecast_months=12,
    kpis=["revenue", "ebitda", "cash_flow"]
)

print(f"Forecast Accuracy: {forecast.accuracy}%")
print(f"Revenue Forecast (12M): €{forecast.revenue_12m:,.0f}")
print(f"EBITDA Forecast (12M): €{forecast.ebitda_12m:,.0f}")
print(f"Confidence Level: {forecast.confidence}%")

# Output:
# Forecast Accuracy: 96.5%
# Revenue Forecast (12M): €125,400,000
# EBITDA Forecast (12M): €18,750,000
# Confidence Level: 94.2%

# Connect to SAP S/4HANA
client.integrations.connect(
    platform="sap_s4hana",
    host="your-sap-host.com",
    client="100",
    username="your_username",
    password="your_password"
)

# Sync actuals data automatically
actuals = client.actuals.sync_from_erp()
print(f"Synced {len(actuals)} actual records from SAP")

# Run AI-powered variance analysis
results = client.variance.analyze()
print(f"Detected {results.variances_found} significant variances")
print(f"Root causes identified: {results.root_causes_count}")
print(f"Analysis accuracy: {results.accuracy}%")

# Define KPIs to monitor
kpis = client.kpis.create_dashboard([
    {
        "name": "Revenue Growth",
        "target": 15.0,  # 15% YoY growth
        "threshold_warning": 12.0,
        "threshold_critical": 10.0
    },
    {
        "name": "EBITDA Margin",
        "target": 18.0,  # 18% margin
        "threshold_warning": 16.0,
        "threshold_critical": 14.0
    },
    {
        "name": "Cash Conversion Cycle",
        "target": 45,  # 45 days
        "threshold_warning": 55,
        "threshold_critical": 65
    }
])

# Enable predictive alerts
client.alerts.configure(
    prediction_horizon=90,  # 90 days ahead
    confidence_threshold=0.85,
    notification_channels=["email", "slack"]
)

print(f"Monitoring {len(kpis)} KPIs with predictive alerts enabled")

# Create scenario: 10% price increase
scenario = client.scenarios.create(
    name="Price Increase 10%",
    assumptions={
        "price_change": 0.10,
        "volume_elasticity": -0.15,
        "cost_inflation": 0.03
    },
    simulation_months=12
)

# Run AI simulation
results = client.scenarios.simulate(scenario.id)

print(f"Scenario: {scenario.name}")
print(f"Revenue Impact: {results.revenue_impact:+.1f}%")
print(f"Margin Impact: {results.margin_impact:+.1f}%")
print(f"Volume Impact: {results.volume_impact:+.1f}%")
print(f"Recommendation: {results.recommendation}")

# Output:
# Scenario: Price Increase 10%
# Revenue Impact: +8.5%
# Margin Impact: +12.3%
# Volume Impact: -1.5%
# Recommendation: Proceed - positive net impact on profitability

# Enable Intelligence Bus
client.intelligence_bus.enable()

# Subscribe to events from other platforms
client.intelligence_bus.subscribe([
    "commerce.revenue_spike_detected",
    "supply.cost_overrun_detected",
    "people.headcount_change",
    "sales.pipeline_change",
    "finance.budget_variance"
])

# Configure automatic actions
client.intelligence_bus.configure_actions({
    "commerce.revenue_spike_detected": "update_revenue_forecast",
    "supply.cost_overrun_detected": "trigger_cost_analysis",
    "people.headcount_change": "adjust_personnel_costs"
})

print("Intelligence Bus enabled - receiving events from 17 platforms")