Job Metrics

POST /api/v2/metrics/job

Description

The job endpoint retrieves detailed performance metrics and statistics for a specific Arcanna job. This endpoint provides comprehensive analytics including accuracy metrics, confusion matrix, model performance data, and time-based statistics for job evaluation and monitoring.

Quick Start Examples

Get metrics for a specific job

curl -X POST "https://your.arcanna.ai/api/v2/metrics/job?job_id=1234" \
  -H "X-Arcanna-Api-Key: your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{}'

Get metrics with custom time range

curl -X POST "https://your.arcanna.ai/api/v2/metrics/job?job_id=1234&start_datetime=2025-01-01T00:00:00Z&end_datetime=2025-01-02T00:00:00Z" \
  -H "X-Arcanna-Api-Key: your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{}'

Get metrics with filters

curl -X POST "https://your.arcanna.ai/api/v2/metrics/job?job_id=1234" \
  -H "X-Arcanna-Api-Key: your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "filters": [
      {
        "field": "arcanna.result_label",
        "operator": "is",
        "value": "Escalate"
      }
    ]
  }'

Request Parameters

Query Parameters

Parameter	Type	Required	Description
job_id	integer or string	Yes	The ID of the job to retrieve metrics for
start_datetime	string	No	Start date for metrics (ISO 8601 format)
end_datetime	string	No	End date for metrics (ISO 8601 format)

Request Body (Optional)

{
  "filters": [
    {
      "field": "string",
      "operator": "string", 
      "value": "string"
    }
  ]
}

Filter Parameters:

• field: The specific data field to apply the filter to
• operator: Comparison method ('is', 'is not', 'contains', 'exists', 'gt', 'lt', etc.)
• value: The criteria used by the operator to filter the field

Response

Success Response (200 OK)

{
  "confusion_matrix": [
    [4490, 0, 0],
    [0, 749, 0], 
    [0, 0, 37]
  ],
  "overall_accuracy": 1.0,
  "overall_f1_score": 1.0,
  "overall_recall": 1.0,
  "overall_precision": 1.0,
  "metrics_per_decision": {
    "Drop": {
      "precision": 1.0,
      "recall": 1.0,
      "f1_score": 1.0,
      "true_positives": 4490,
      "true_negatives": 786,
      "false_positives": 0,
      "false_negatives": 0
    },
    "Investigate": {
      "precision": 1.0,
      "recall": 1.0,
      "f1_score": 1.0,
      "true_positives": 749,
      "true_negatives": 4527,
      "false_positives": 0,
      "false_negatives": 0
    },
    "Escalate": {
      "precision": 1.0,
      "recall": 1.0,
      "f1_score": 1.0,
      "true_positives": 37,
      "true_negatives": 5239,
      "false_positives": 0,
      "false_negatives": 0
    }
  },
  "start_time": "2025-01-01T00:00:00Z",
  "end_time": "2025-01-02T00:00:00Z",
  "time_saved_minutes": 1250.5,
  "active_model_id": "generic-1-1234-model-1747385873.hdf5",
  "all_model_ids": ["generic-1-1234-model-1747385873.hdf5"],
  "total_events": 5276,
  "total_events_in_knowledge_base": 2516,
  "total_events_with_consensus": 5,
  "changed_consensus_after_training": {
    "total_events": 0,
    "top_events_ids": [],
    "top_buckets_ids": []
  }
}

Error Response (404 Not Found)

{
  "error": "Job not found"
}

Response Fields

Core Metrics

• confusion_matrix: 2D array representing the confusion matrix of model decisions
• overall_accuracy: Mean accuracy across all decisions (0-1)
• overall_f1_score: Mean F1 score across all decisions (0-1)
• overall_recall: Mean recall across all decisions (0-1)
• overall_precision: Mean precision across all decisions (0-1)

Decision-Level Metrics

• metrics_per_decision: Object containing metrics for each decision type:
  • precision: Precision score for this decision type
  • recall: Recall score for this decision type
  • f1_score: F1 score for this decision type
  • true_positives: Number of true positive predictions
  • true_negatives: Number of true negative predictions
  • false_positives: Number of false positive predictions
  • false_negatives: Number of false negative predictions

Additional Information

• start_time: Start time for the computed metrics period
• end_time: End time for the computed metrics period
• time_saved_minutes: Estimated time saved by Arcanna (in minutes)
• active_model_id: ID of the currently active model
• all_model_ids: List of all model IDs associated with this job
• total_events: Total number of events processed
• total_events_in_knowledge_base: Number of events in the knowledge base
• total_events_with_consensus: Number of events with consensus
• changed_consensus_after_training: Object containing information about events that changed consensus after training
  • total_events: Total number of events that changed consensus
  • top_events_ids: List of top 10 events IDs that changed consensus
  • top_buckets_ids: List of top 10 buckets IDs that changed consensus