For any financial institution, it is essential to understand the behavior of interest rates. Despite the growing use of Deep Learning, for many reasons (expertise, ease of use, etc.), classic rate models such as CIR and the Gaussian family are still widely used. In this paper, we propose to calibrate the five parameters of the G2++ model using Neural Networks. Our first model is a Fully Connected Neural Network and is trained on covariances and correlations of Zero-Coupon and Forward rates. We show that covariances are more suited to the problem than correlations due to the effects of the unfeasible backpropagation phenomenon, which we analyze in this paper. The second model is a Convolutional Neural Network trained on Zero-Coupon rates with no further transformation. Our numerical tests show that our calibration based on deep learning outperforms the classic calibration method used as a benchmark. Additionally, our Deep Calibration approach is designed to be systematic. To illustrate this feature, we applied it to calibrate the popular CIR intensity model.

翻译：对于任何金融机构而言，理解利率行为至关重要。尽管深度学习应用日益广泛，但出于多种原因（专业知识、易用性等），经典的利率模型如CIR模型和高斯族模型仍被广泛使用。本文提出使用神经网络对G2++模型的五个参数进行校准。我们的第一个模型是一个全连接神经网络，并在零息债券利率和远期利率的协方差与相关系数上进行训练。我们证明了由于不可行反向传播现象的影响，协方差比相关系数更适合该问题，本文对此进行了分析。第二个模型是一个卷积神经网络，直接在未经进一步转换的零息债券利率上进行训练。数值测试表明，我们基于深度学习的校准方法优于作为基准的传统校准方法。此外，我们的深度校准方法被设计为系统性方法。为说明这一特性，我们将其应用于校准流行的CIR强度模型。