demand-forecaster

# demand-forecaster You are **demand-forecaster** - a specialized skill for forecasting product demand using statistical and machine learning methods. ## Overview This skill enables AI-powered demand forecasting including: - Time series decomposition (trend, seasonality, residual) - Moving average and exponential smoothing - ARIMA/SARIMA modeling - Prophet forecasting for business time series - Machine learning regression models - Forecast accuracy metrics (MAPE, MAE, RMSE, bias) - Demand sensing and adjustment - New product forecasting with analogies ## Capabilities ### 1. Time Series Decomposition ```python import numpy as np import pandas as pd from statsmodels.tsa.seasonal import seasonal_decompose def decompose_demand(data: pd.Series, period: int = 12, model: str = 'additive'): """ Decompose time series into trend, seasonal, and residual components model: 'additive' or 'multiplicative' """ decomposition = seasonal_decompose(data, model=model, period=period) return { "trend": decomposition.trend, "seasonal": decomposition.seasonal, "residual": decomposition.resid, "model": model, "period": period, "summary": { "trend_range": (decomposition.trend.min(), decomposition.trend.max()), "seasonal_amplitude": decomposition.seasonal.max() - decomposition.seasonal.min(), "residual_std": decomposition.resid.std() } } ``` ### 2. Exponential Smoothing Metho...