DELPHYNE: A Pre-Trained Model for General and Financial Time Series

TL;DR

Delphyne is a pre-trained model designed specifically for financial time series data, addressing previous limitations by incorporating financial data during training and handling the unique challenges of financial time series.

Contribution

It introduces Delphyne, a pre-trained model tailored for financial time series, improving performance through specialized training and addressing domain-specific challenges.

Findings

Delphyne achieves competitive performance with few fine-tuning steps.

Delphyne outperforms existing models on various financial tasks.

Incorporating financial data during pre-training enhances model effectiveness.

Abstract

Time-series data is a vital modality within data science communities. This is particularly valuable in financial applications, where it helps in detecting patterns, understanding market behavior, and making informed decisions based on historical data. Recent advances in language modeling have led to the rise of time-series pre-trained models that are trained on vast collections of datasets and applied to diverse tasks across financial domains. However, across financial applications, existing time-series pre-trained models have not shown boosts in performance over simple finance benchmarks in both zero-shot and fine-tuning settings. This phenomenon occurs because of a i) lack of financial data within the pre-training stage, and ii) the negative transfer effect due to inherently different time-series patterns across domains. Furthermore, time-series data is continuous, noisy, and can be collected at varying frequencies and with varying lags across different variables, making this data more challenging to model than languages. To address the above problems, we introduce a Pre-trained MoDEL for FINance TimE-series (Delphyne). Delphyne achieves competitive performance to existing foundation and full-shot models with few fine-tuning steps on publicly available datasets, and also shows superior performances on various financial tasks.