A New Metric for Lumpy and Intermittent Demand Forecasts: Stock-keeping-oriented Prediction Error Costs
This work addresses the need for better forecast evaluation in logistics and production optimization, particularly for industries with irregular demand patterns, though it appears incremental as it focuses on a specific metric improvement.
The authors tackled the problem of evaluating demand forecasts for lumpy and intermittent patterns, where common metrics like MAPE or RMSE are inadequate, by proposing a novel metric that incorporates statistical and business aspects, and they evaluated it on simulated and real automotive aftermarket data.
Forecasts of product demand are essential for short- and long-term optimization of logistics and production. Thus, the most accurate prediction possible is desirable. In order to optimally train predictive models, the deviation of the forecast compared to the actual demand needs to be assessed by a proper metric. However, if a metric does not represent the actual prediction error, predictive models are insufficiently optimized and, consequently, will yield inaccurate predictions. The most common metrics such as MAPE or RMSE, however, are not suitable for the evaluation of forecasting errors, especially for lumpy and intermittent demand patterns, as they do not sufficiently account for, e.g., temporal shifts (prediction before or after actual demand) or cost-related aspects. Therefore, we propose a novel metric that, in addition to statistical considerations, also addresses business aspects. Additionally, we evaluate the metric based on simulated and real demand time series from the automotive aftermarket.