Boosted Embeddings for Time Series Forecasting
This work addresses time series forecasting, a fundamental task in data-driven applications, with a novel hybrid method that shows improved performance.
The paper tackles time series forecasting by proposing DeepGB, a novel model that combines gradient boosting with deep neural networks as weak learners. The authors demonstrate that their approach outperforms existing state-of-the-art models on real-world sensor data and public datasets.
Time series forecasting is a fundamental task emerging from diverse data-driven applications. Many advanced autoregressive methods such as ARIMA were used to develop forecasting models. Recently, deep learning based methods such as DeepAr, NeuralProphet, Seq2Seq have been explored for time series forecasting problem. In this paper, we propose a novel time series forecast model, DeepGB. We formulate and implement a variant of Gradient boosting wherein the weak learners are DNNs whose weights are incrementally found in a greedy manner over iterations. In particular, we develop a new embedding architecture that improves the performance of many deep learning models on time series using Gradient boosting variant. We demonstrate that our model outperforms existing comparable state-of-the-art models using real-world sensor data and public dataset.