BrainPredict Controlling: Use Cases

# Step 1: Configure rolling forecast
from brainpredict import ControllingClient

client = ControllingClient(api_key="bp_controlling_live_xxx")

# Create rolling forecast configuration
rolling_forecast = client.forecasts.create_rolling(
    forecast_horizon=12,
    update_frequency="monthly",
    kpis=["revenue", "costs", "ebitda", "cash_flow"],
    auto_update=True,
    data_sources=["erp", "crm", "market_data"],
    ai_model="rolling_forecast_engine"
)

print(f"Rolling Forecast ID: {rolling_forecast.id}")
print(f"Next Update: {rolling_forecast.next_update}")

# Step 2: Get current forecast
current = client.forecasts.get_current(rolling_forecast.id)

print(f"Revenue Forecast (12M): €{current.revenue:,.0f}")
print(f"EBITDA Forecast (12M): €{current.ebitda:,.0f}")
print(f"Forecast Accuracy: {current.accuracy}%")

# Step 3: Set up alerts for significant changes
client.forecasts.configure_alerts(
    rolling_forecast.id,
    alerts=[
        {
            "kpi": "revenue",
            "threshold": 5.0,  # Alert if forecast changes >5%
            "notification": "email"
        },
        {
            "kpi": "ebitda",
            "threshold": 10.0,
            "notification": "email"
        }
    ]
)

# Step 1: Configure real-time variance monitoring
from brainpredict import ControllingClient

client = ControllingClient(api_key="bp_controlling_live_xxx")

# Set up variance monitoring
variance_monitor = client.analytics.configure_variance_monitoring(
    dimensions=["store", "product_category", "region"],
    variance_threshold=5.0,  # Alert if variance >5%
    frequency="daily",
    include_root_cause=True,
    ai_model="variance_analyzer"
)

# Step 2: Analyze variances for current period
analysis = client.analytics.analyze_variance(
    period="2025-11",
    dimensions=["store", "product_category"],
    variance_threshold=5.0,
    include_root_cause=True
)

print(f"Total Variance: €{analysis.total_variance:,.0f}")
print(f"Variance %: {analysis.variance_percentage}%")
print(f"Significant Variances: {len(analysis.significant_variances)}")

# Step 3: Get root causes for top variances
for variance in analysis.significant_variances[:5]:
    print(f"\n{variance.entity}:")
    print(f"  Variance: €{variance.variance:,.0f} ({variance.variance_pct}%)")
    print(f"  Root Causes:")
    for cause in variance.root_causes:
        print(f"    - {cause}")
    print(f"  AI Recommendations:")
    for rec in variance.recommendations:
        print(f"    - {rec}")