MASE (Mean Absolute Scaled Error)

Information

• MASE (Mean Absolute Scaled Error) is a metric for measuring forecast accuracy.
• MASE compares the accuracy of a given forecast with that of a naive forecast (e.g., a seasonal naïve or a random walk model).
• MASE is scale-independent, making it useful for comparing the accuracy of forecasts across different time series with different scales.
• The formula for MASE is:
  • MASE = mean(|e_t|) / (mean(|y_t-y_{t-1}|) for t = 2,...,n)
  • where e_t is the forecast error at time t, y_t is the actual value at time t, and n is the length of the time series.
• A MASE value of less than 1 indicates that the given forecast is better than the naive forecast.
• MASE has been used in various fields, including finance, energy, and transportation, to evaluate the performance of forecasting models.