---
title: Deep Learning for Corporate Bonds
url: https://www.ml-quant.com/papers/ssrn/4527372/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4527372
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4527372
featured: 2023-08-02
citations: 1
topic: Macro-Finance & Rates
---


# Deep Learning for Corporate Bonds

A U.S. corporate bonds market asset pricing model shows that maximizing the Sharpe ratio performs better for individual bonds, with significant excess returns shown in out-of-sample annual SDF portfolio Sharpe ratios.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4527372
- Identifier: SSRN 4527372
- Released: 2023-07-31
- First featured: Quant Letter No. 10 (2023-08-02): https://www.ml-quant.com/issues/2023-08-02/
- Citations (Semantic Scholar): 1
- Published in: not yet
- Topic: Macro-Finance & Rates

## Related

- [Agree to Disagree: Measuring Hidden Dissents in FOMC Meetings](https://www.ml-quant.com/papers/arxiv/2308.10131/): A deep learning model study reveals that disagreement among FOMC members is primarily driven by current or forecasted macroeconomic data, and intensifies with more aggressive monetary policy action.
- [Corporate Bond Factors: Replication Failures and a New Framework](https://www.ml-quant.com/papers/ssrn/4586652/): The study criticizes inconsistent methodologies in corporate bond factors literature, suggesting a robust factor construction and a clean database for corporate bond returns.
- [Deep Learning for Multi-Country GDP Prediction: A Study of Model Performance and Data Impact](https://www.ml-quant.com/papers/arxiv/2409.02551/): A study on predicting GDP growth in various countries using deep learning algorithms reveals that linear regression outperforms when only GDP growth values are considered, but deep learning excels when specific economic indicators are included, and light intensity data doesn't necessarily enhance prediction accuracy.
- [Supervised Similarity for High-Yield Corporate Bonds with Quantum Cognition Machine Learning](https://www.ml-quant.com/papers/arxiv/2502.01495/): The research applies quantum cognition machine learning to distance metric learning in corporate bond markets, outperforming traditional models in high-yield markets and performing similarly or better in investment grade markets.
- [CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market](https://www.ml-quant.com/papers/arxiv/2508.10208/): Geometric Deep Learning for CAT Bond Spread: The research introduces CATNet, a new model that uses geometric deep learning to predict the catastrophe bond primary market, showing that network connectivity significantly influences price.
- [International Corporate Bond Returns Prediction with ML](https://www.ml-quant.com/papers/ssrn/4506223/): Machine learning is used to forecast global corporate bond returns, showing varying influential factors in U.S. and non-U.S. markets and different levels of bond integration among countries.