Anofox Forecast

What is Anofox Forecast?

Anofox Forecast brings enterprise time-series forecasting directly to DuckDB. Generate forecasts with 31 state-of-the-art models using pure SQL - no Python, no complex pipelines, zero data movement.

Key Features

• 31 Forecasting Models - AutoML, Statistical, Advanced, and Intermittent demand models
• Pattern Detection - Seasonality detection, changepoint analysis, and diagnostics
• Feature Engineering - 87 tsfresh-compatible statistical features
• Evaluation Metrics - 12 accuracy metrics including MAE, RMSE, MAPE, MASE
• Production Ready - Handles millions of series with automatic parallelization

Quick Links

Documentation	Description
Installation	Setup and prerequisites
Function Finder	Find the right function for your task
Exploratory Data Analysis	Profile your time series data
Data Quality	Multi-dimensional quality assessment
Data Preparation	Clean and transform your data
Diagnostics	Pattern detection and analysis
Features	Feature engineering functions
Models	All 31 forecasting models
Metrics	12 evaluation metrics

Basic Usage

-- Load the extension
LOAD anofox_forecast;

-- Forecast your first series
SELECT
    forecast_step,
    date_col,
    point_forecast,
    lower_95,
    upper_95
FROM anofox_fcst_ts_forecast(
    'sales_data',           -- Your table
    'date',                 -- Date column
    'amount',               -- Value column
    'AutoETS',              -- Model
    28,                     -- Forecast horizon (days)
    MAP{'confidence_level': 0.95}
);

This returns 28 future forecasts with prediction intervals - all computed in-database.

Why Anofox Forecast?

• Native Performance - Zero Python overhead, direct C++ execution in DuckDB
• Automatic Parallelization - DuckDB distributes work across CPU cores
• In-Database - Process petabyte-scale data without moving it
• Pure SQL API - No new languages or DSLs to learn