Affiliation:
1. Department of Finance, School of Economics, Shanghai University, Shanghai 200444, China
Abstract
This paper proposes two data-driven models (including LSTM pricing model, WGAN pricing model) and an improved model of LSM based on GAN to analyze the pricing of convertible bonds. In addition, the LSM model with higher precision in traditional pricing model is selected for comparative study with other pricing models. It is found that the traditional LSM pricing model has a large error in the first-day pricing, and the pricing function needs to be further improved. Among the four pricing models, LSTM pricing model and WGAN pricing model have the best pricing effect. The WGAN pricing model is better than the LSTM pricing model (0.21%), and the LSM improved model (1.17%) is better than the traditional LSM model (2.26%). Applying the generative deep learning model GAN to the pricing of convertible bonds can circumvent the harsh preconditions of assumptions, and significantly improve the pricing effect of the traditional model. The scope of application of each model is different. Therefore, this paper proves the feasibility of the GAN model applied to the pricing of convertible bonds, and enriches the pricing function of derivatives in the financial field.
Funder
National Social Science Fund Project
Reference42 articles.
1. Arjovsky, Martin, and Bottou, Léon (2017). Towards Principled Methods for Training Generative Adversarial Networks. arXiv.
2. Batten, Jonathan A., Khaw, Karren Lee-Hwei, and Young, Martin R. (2018). Pricing Convertible Bonds using Stochastic Interest Rate. Journal of Banking & Finance, S0378426618301006.
3. Convertible bonds: Valuation and optimal strategies for call and conversion;Brennan;The Journal of Finance,1977
4. Pricing of Convertible Bonds Based on Tsallis Entropy Distribution under Stochastic Interest Rate Model;Chang;Operational Research and Management,2020
5. Option pricing: A simplified approach;Cox;Journal of Financial Economics,1979
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献