Machine Learning: プロジェクト設計 — SalesPredict エンドツーエンド計画ガイド

# Project design as code
project_config = {
    "name": "SalesPredict",
    "goal": "Monthly revenue prediction MAPE < 10%",
    "data_sources": ["orders", "users", "products", "ad_logs"],
    "model_pipeline": "LinearRegression → XGBoost → MLP",
    "deployment": "FastAPI + Docker + MLflow",
    "team": {"Alice": "Data Engineering", "Bob": "ML Engineering", "Charlie": "DevOps"},
}

# Requirements as structured config
requirements = {
    "business_goal": "Predict next month's revenue per product category",
    "success_metrics": {
        "primary": "MAPE < 10% for monthly revenue prediction",
        "secondary": ["MAE < 50k USD per category", "Prediction latency < 100ms"],
    },
    "user_stories": [
        "As Bob (Operations), I want monthly revenue predictions so I can optimize inventory",
        "As Alice (US Manager), I want USD-denominated predictions for the US market",
        "As Charlie (EU Manager), I want EUR-denominated predictions for the EU market",
        "As CFO, I want prediction confidence intervals for budget planning",
    ],
    "constraints": {
        "data_latency": "Daily batch update by 6:00 AM",
        "prediction_sla": "API response < 100ms p95",
        "model_retraining": "Weekly automated retraining",
        "compliance": "GDPR for EU user data",
    },
    "scope": {
        "in_scope": ["3 market regions", "5 product categories", "Monthly & weekly predictions"],
        "out_of_scope": ["Real-time per-order prediction", "Image-based product classification"],
    },
}

# Executed successfully

data_sources = {
    "orders": {
        "source": "PostgreSQL (production DB)",
        "fields": ["order_id", "user_id", "product_id", "amount_usd", "order_date", "category"],
        "volume": "~500k rows/month",
        "latency": "T+1 (next day available)",
    },
    "users": {
        "source": "CRM System",
        "fields": ["user_id", "region", "segment", "register_date", "lifetime_value"],
        "volume": "~50k active users",
        "latency": "T+1",
    },
    "ad_spend": {
        "source": "Google Ads + Facebook Ads API",
        "fields": ["date", "channel", "campaign", "spend_usd", "impressions", "clicks"],
        "volume": "~10k rows/month",
        "latency": "T+2",
    },
    "product_catalog": {
        "source": "PIM System",
        "fields": ["product_id", "category", "price_usd", "margin_pct", "launch_date"],
        "volume": "~5k products",
        "latency": "Weekly update",
    },
}

# Executed successfully

model_architecture = {
    "stage_1_baseline": {
        "model": "LinearRegression + Pipeline",
        "expected_r2": "0.72-0.78",
        "expected_mape": "12-15%",
        "purpose": "Establish baseline, validate data pipeline",
        "timeline": "Week 1-2",
    },
    "stage_2_advanced": {
        "model": "XGBoost + Feature Engineering",
        "expected_r2": "0.85-0.89",
        "expected_mape": "8-10%",
        "purpose": "Production model, meet MAPE < 10% target",
        "timeline": "Week 3-5",
    },
    "stage_3_deep_learning": {
        "model": "MLP / LSTM (time series)",
        "expected_r2": "0.87-0.92",
        "expected_mape": "7-9%",
        "purpose": "Incremental improvement, capture temporal patterns",
        "timeline": "Week 6-8",
    },
}

# Executed successfully

evaluation_strategy = {
    "cv_method": "TimeSeriesSplit(n_splits=5)",
    "primary_metric": "MAPE",
    "secondary_metrics": ["MAE", "RMSE", "R2"],
    "business_alignment": {
        "MAPE_10pct": "Prediction error within 10% of actual revenue",
        "MAE_50k": "Average absolute error less than 50k USD per category",
        "cost_of_error": "1% MAPE ≈ 100k USD annual inventory waste",
    },
    "ab_testing": {
        "duration": "3 weeks",
        "metric": "Revenue prediction MAPE vs actuals",
        "sample_size": "All categories, all markets",
    },
}

risk_register = {
    "data_quality": {
        "risk": "Raw data has >5% missing values in key features",
        "probability": "High",
        "impact": "Critical - model trained on biased data",
        "mitigation": "Automated data quality checks in ETL pipeline",
        "owner": "Alice",
    },
    "model_overfitting": {
        "risk": "XGBoost overfits on small category samples",
        "probability": "Medium",
        "impact": "High - poor generalization to new markets",
        "mitigation": "TimeSeriesSplit CV, regularization, early stopping",
        "owner": "Bob",
    },
    "api_latency": {
        "risk": "Prediction API exceeds 100ms SLA under load",
        "probability": "Medium",
        "impact": "Medium - user experience degradation",
        "mitigation": "Redis cache for hot queries, Nginx rate limiting",
        "owner": "Charlie",
    },
}

# Executed successfully

project_schedule = {
    "Week 1-2: Data & Baseline": {
        "Alice": "ETL pipeline, data lake setup, data quality checks",
        "Bob": "EDA, feature engineering, LinearRegression baseline",
        "Charlie": "Dev environment, MLflow setup, CI/CD pipeline",
    },
    "Week 3-5: Advanced Model": {
        "Alice": "Feature store, online serving layer, data monitoring",
        "Bob": "XGBoost training, hyperparameter tuning, model evaluation",
        "Charlie": "FastAPI scaffold, Docker setup, load testing",
    },
    "Week 6-8: Deep Learning & Deploy": {
        "Alice": "Real-time features, data drift detection",
        "Bob": "MLP/LSTM experiments, A/B test design",
        "Charlie": "Production deployment, monitoring dashboard, alerting",
    },
    "Week 9-10: Launch & Monitor": {
        "Alice": "Data pipeline monitoring, feature validation",
        "Bob": "Model monitoring, retraining pipeline",
        "Charlie": "A/B test execution, gradual rollout, on-call setup",
    },
}

# Executed successfully