OpenMetadata/ingestion/examples/sample_data/models/models.json

[
  {
    "name": "eta_predictions",
    "displayName": "ETA Predictions",
    "description": "Deep learning model for predicting estimated time of arrival using historical delivery data and real-time traffic patterns",
    "algorithm": "mlmodel",
    "dashboard": "sample_superset.eta_predictions_performance",
    "mlStore": {
      "storage": "mlflow-artifacts:/1/abc123def456/artifacts/model"
    },
    "sourceUrl": "http://localhost:8088/#/models/eta_predictions",
    "mlFeatures": [
      {
        "name": "distance",
        "dataType": "numerical"
      },
      {
        "name": "traffic_density",
        "dataType": "numerical"
      },
      {
        "name": "weather_condition",
        "dataType": "categorical"
      },
      {
        "name": "day_of_week",
        "dataType": "categorical"
      }
    ],
    "mlHyperParameters": [
      {
        "name": "learning_rate",
        "value": "0.001"
      },
      {
        "name": "batch_size",
        "value": "32"
      },
      {
        "name": "epochs",
        "value": "100"
      },
      {
        "name": "dropout_rate",
        "value": "0.3"
      }
    ]
  },
  {
    "name": "forecast_sales",
    "displayName": "Sales Forecast Predictions",
    "description": "Time series forecasting model for predicting future sales based on historical trends and seasonality patterns",
    "algorithm": "mlmodel",
    "dashboard": "sample_superset.forecast_sales_performance",
    "mlStore": {
      "storage": "mlflow-artifacts:/2/xyz789abc012/artifacts/model"
    },
    "sourceUrl": "http://localhost:8088/#/models/forecast_sales",
    "mlFeatures": [
      {
        "name": "historical_sales",
        "dataType": "numerical"
      },
      {
        "name": "month",
        "dataType": "categorical"
      },
      {
        "name": "promotion_flag",
        "dataType": "categorical"
      }
    ],
    "mlHyperParameters": [
      {
        "name": "seasonality_mode",
        "value": "multiplicative"
      },
      {
        "name": "changepoint_prior_scale",
        "value": "0.05"
      },
      {
        "name": "seasonality_prior_scale",
        "value": "10.0"
      }
    ]
  },
  {
    "name": "customer_segmentation",
    "displayName": "Customer Segmentation Model",
    "description": "Clustering model for customer segmentation based on purchase behavior and demographics",
    "algorithm": "mlmodel",
    "dashboard": "sample_superset.eta_predictions_performance",
    "mlStore": {
      "storage": "mlflow-artifacts:/3/seg456cluster/artifacts/model"
    },
    "sourceUrl": "http://localhost:8088/#/models/customer_segmentation",
    "mlFeatures": [
      {
        "name": "total_purchase_amount",
        "dataType": "numerical"
      },
      {
        "name": "purchase_frequency",
        "dataType": "numerical"
      },
      {
        "name": "avg_basket_size",
        "dataType": "numerical"
      },
      {
        "name": "customer_age_group",
        "dataType": "categorical"
      },
      {
        "name": "preferred_category",
        "dataType": "categorical"
      }
    ],
    "mlHyperParameters": [
      {
        "name": "n_clusters",
        "value": "5"
      },
      {
        "name": "max_iter",
        "value": "300"
      },
      {
        "name": "init",
        "value": "k-means++"
      },
      {
        "name": "random_state",
        "value": "42"
      }
    ]
  }
]