Pastprop-RNN: improved predictions of the future by correcting the past
This addresses data quality issues in forecasting for domains like demand prediction, but it is incremental as it builds on existing LSTM methods.
The paper tackles the problem of forecasting accuracy being affected by poor past data by introducing pastcasting, which predicts corrected past data to better explain the future, and shows that Pastprop-LSTM improves forecasting accuracy, particularly when standard LSTM errors are high.
Forecasting accuracy is reliant on the quality of available past data. Data disruptions can adversely affect the quality of the generated model (e.g. unexpected events such as out-of-stock products when forecasting demand). We address this problem by pastcasting: predicting how data should have been in the past to explain the future better. We propose Pastprop-LSTM, a data-centric backpropagation algorithm that assigns part of the responsibility for errors to the training data and changes it accordingly. We test three variants of Pastprop-LSTM on forecasting competition datasets, M4 and M5, plus the Numenta Anomaly Benchmark. Empirical evaluation indicates that the proposed method can improve forecasting accuracy, especially when the prediction errors of standard LSTM are high. It also demonstrates the potential of the algorithm on datasets containing anomalies.