<ul><li>Cherry-picking datasets in time series forecasting can significantly distort the perceived performance of forecasting methods.</li><li>Selective dataset selection can lead to an exaggeration of the effectiveness of forecasting methods.</li><li>By selectively choosing just four datasets, 46% of methods could be considered best in class.</li><li>Increasing the number of datasets tested from 3 to 6 reduces the risk of incorrectly identifying an algorithm as the best one by approximately 40%.</li></ul>

Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine

Discover more