GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecasting

no code implementations • 7 Jul 2023 • Sitan Yang, Malcolm Wolff, Shankar Ramasubramanian, Vincent Quenneville-Belair, Ronak Metha, Michael W. Mahoney

Encoder-decoder deep neural networks have been increasingly studied for multi-horizon time series forecasting, especially in real-world applications.

Data Augmentation Time Series +1

MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation

no code implementations • 21 Jul 2022 • Sitan Yang, Carson Eisenach, Dhruv Madeka

For example, MQTransformer - an improvement of MQCNN - has shown the state-of-the-art performance in probabilistic demand forecasting.

Probabilistic Time Series Forecasting Retrieval +1