This paper introduces DeepVol, a pre-trained deep learning volatility model that is more general than traditional econometric models. DeepVol leverage the power of transfer learning to effectively capture and model the volatility dynamics of all financial assets, including previously unseen ones, using a single universal model. This contrasts to the usual practice in the econometrics literature, which trains a separate model for each asset. The introduction of DeepVol opens up new avenues for volatility modeling in the finance industry, potentially transforming the way volatility is predicted.

翻译：本文提出DeepVol，一种预训练的深度学习波动率模型，其通用性优于传统计量经济学模型。DeepVol利用迁移学习能力，通过单一通用模型有效捕获并建模所有金融资产（包括先前未见过的资产）的波动率动态特征。这与计量经济学文献中针对每个资产分别训练独立模型的常规做法形成鲜明对比。DeepVol的引入为金融行业的波动率建模开辟了新路径，有望改变波动率预测的方式。