N-BEATS : Time-Series Forecasting with Neural Basis Expansion

There's one thing that makes Time-Series Forecasting special. It was the only area of Data Science where Deep Learning and Transformers didn't decisively outperform the other models. Let's use the prestigious Makridakis M-competitions as a benchmark -- a series of large-scale challenges that showcase the latest advances in the time-series forecasting area. In the fourth iteration of the competition, known as M4, the winning solution was ES-RNN [2], a hybrid LSTM & Exponential Smoothing model developed by Uber. Interestingly, the 6 (out of 57) pure ML models performed so poorly, they barely surpassed the competition baseline.