Time series forecasting is an important problem with various applications in different domains. Improving forecast performance has been the center of investigation in the last decades. Several pieces of research show that old statistical methods, such as ARIMA, are still state-of-the-art in many domains and applications. However, one of the main limitations of these methods is their low performance on longer horizons in multi-step forecasting scenarios. We attack this problem from an entirely new perspective. We propose a new universal post-correction approach that can be applied to fix the problematic forecasts of any forecasting model, including ARIMA. The idea is intuitive: We query the last window of observations plus the given forecast, searching for similar shapes in history, and using the future shape of the nearest neighbor, we post-correct the forecast. In order to make sure that post-correction is adequate, we train a supervised decision model on the successfulness of post-corrections on the training set. Our experiments on several datasets show that the proposed post-correction method effectively improves forecasts for 30 steps ahead and beyond.