DMIDAS: Deep Mixed Data Sampling Regression for Long Multi-Horizon Time Series Forecasting
This work provides a more efficient and accurate method for long-horizon forecasting in domains like healthcare and electricity pricing, though it is incremental as it builds on an existing architecture.
The paper tackled the challenge of predicting extremely long horizons in time series forecasting by addressing volatility and computational complexity, resulting in a 5% improvement in prediction accuracy and a 70% reduction in parameters compared to state-of-the-art models.
Neural forecasting has shown significant improvements in the accuracy of large-scale systems, yet predicting extremely long horizons remains a challenging task. Two common problems are the volatility of the predictions and their computational complexity; we addressed them by incorporating smoothness regularization and mixed data sampling techniques to a well-performing multi-layer perceptron based architecture (NBEATS). We validate our proposed method, DMIDAS, on high-frequency healthcare and electricity price data with long forecasting horizons (~1000 timestamps) where we improve the prediction accuracy by 5% over state-of-the-art models, reducing the number of parameters of NBEATS by nearly 70%.