FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
Researchers have developed FAME, a novel sparse mixture-of-experts framework designed for heterogeneous time series forecasting. This approach creates a "forecastability fingerprint" for each series to intelligently route it to a small subset of specialized forecasting experts. Applied to a large-scale vending machine sales dataset, FAME demonstrated a 12.4% reduction in Mean Squared Error compared to the best single expert, LightGBM, while using an average of just 1.92 experts per series. AI
IMPACT This framework could enhance the efficiency and accuracy of forecasting in complex, real-world systems by optimizing expert model selection.