/api/forecast_units

Header

X-Customer-Api-Id: <uuid>
X-Secret: <secret>
Content-Type: application/json

Request Body Schema

{
  "product_code": "string",      // SKU or internal code
  "forecast_period": int,        // ≥1, number of months to predict
  "data": [                      // historical daily units sold; ≥45 rows recommended
    {
      "date": "YYYY-MM-DD",      // ISO date; gaps auto-filled as 0
      "sales_quantity": int      // non-negative units sold
    }
    // … additional records …
  ]
}

Example Request Body

// Example Request
{
  "product_code": "38788",
  "forecast_period": 6,
  "data": [
    { "date": "2025-02-20", "sales_quantity": 11 },
    { "date": "2025-02-21", "sales_quantity": 12 },
    { "date": "2025-02-22", "sales_quantity": 6  },
    { "date": "2025-02-23", "sales_quantity": 5  },
    { "date": "2025-02-24", "sales_quantity": 14 },
    { "date": "2025-02-25", "sales_quantity": 13 },
    { "date": "2025-02-26", "sales_quantity": 12 },
    { "date": "2025-02-27", "sales_quantity": 13 },
    { "date": "2025-02-28", "sales_quantity": 12 },
    { "date": "2025-03-01", "sales_quantity": 7  },
    // … at least 45 total entries …
    { "date": "2025-04-20", "sales_quantity": 8  }
  ]
}

Example Response Body

// Example Response
{
  "forecast_period": 6,
  "forecasts": [
    {
      "product_code": "38788",
      "best_algorithm": "Random Forest",
      "evaluation_metrics": {
        "RMSE": 1.00945,
        "MAE": 0.98201,
        "R2": 0.93241,
        "average_daily_sales": 12.93465,
        "Interpretation": "Random Forest selected (RMSE=1.01, MAE=0.98, R²=0.93)."
      },
      "forecast": {
        "calendar": [
          {"yyyy-mm": "2025-05", "value": 435.7681},
          {"yyyy-mm": "2025-06", "value": 420.2209},
          {"yyyy-mm": "2025-07", "value": 443.8330},
          {"yyyy-mm": "2025-08", "value": 426.7841},
          {"yyyy-mm": "2025-09", "value": 429.2683},
          {"yyyy-mm": "2025-10", "value": 442.8731}
        ],
        "business": [
          {"yyyy-mm": "2025-05", "value": 362.2446},
          {"yyyy-mm": "2025-06", "value": 347.6626},
          {"yyyy-mm": "2025-07", "value": 378.9078},
          {"yyyy-mm": "2025-08", "value": 345.6275},
          {"yyyy-mm": "2025-09", "value": 364.3430},
          {"yyyy-mm": "2025-10", "value": 377.9478}
        ]
      }
    }
  ],
  "execution_time_seconds": 1.5340
}

Description

Generate a one-shot, 6-month demand forecast at the SKU level (day-granular, calendar vs. business-day splits). The endpoint auto-benchmarks ARIMA, ETS, Prophet, TBATS, Random Forest, Gradient Boost, and Croston for intermittent demand, selects the best model by RMSE, and returns month-level unit forecasts with diagnostic metrics and run time.

Business Usage

• Replenishment Planning: Feed calendar forecasts into PO generation to balance stock-out vs. over-stock. • Workforce Scheduling: Use business-day forecasts for labour and picking slot planning. • Intermittent & Lumpy Items: Auto-select Croston when demand is sparse without custom code.

← Back to all routes