The paper presents a new framework for storing and retrieving financial time-series data. Rather than using traditional databases, the authors propose using deep encoders to store this data in a lower-dimensional latent space. This method not only captures time series trends but also other information such as price volatility. The proposed system also offers user-friendly query interfaces for natural language text or sketches of time-series. The authors demonstrate the advantages of their method in terms of computational efficiency and accuracy on both real historical and synthetic data.
Publication date: 2 Oct 2023
Project Page: https://doi.org/XXXXXXX.XXXXXXX
Paper: https://arxiv.org/pdf/2309.16741
