• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

银行的深度资金管理。

Deep treasury management for banks.

作者信息

Englisch Holger, Krabichler Thomas, Müller Konrad J, Schwarz Marc

机构信息

Department of Treasury, Thurgauer Kantonalbank, Weinfelden, Switzerland.

Centre for Banking and Finance, Eastern Switzerland University of Applied Sciences, St. Gallen, Switzerland.

出版信息

Front Artif Intell. 2023 Mar 22;6:1120297. doi: 10.3389/frai.2023.1120297. eCollection 2023.

DOI:10.3389/frai.2023.1120297
PMID:37035532
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10073554/
Abstract

Retail banks use (ALM) to hedge interest rate risk associated with differences in maturity and predictability of their loan and deposit portfolios. The opposing goals of profiting from maturity transformation and hedging interest rate risk while adhering to numerous regulatory constraints make ALM a challenging problem. We formulate ALM as a high-dimensional stochastic control problem in which monthly investment and financing decisions drive the evolution of the bank's balance sheet. To find strategies that maximize long-term utility in the presence of constraints and stochastic interest rates, we train neural networks that parametrize the decision process. Our experiments provide practical insights and demonstrate that the approach of Deep ALM deduces dynamic strategies that outperform static benchmarks.

摘要

零售银行运用资产负债管理（ALM）来对冲与贷款和存款组合的期限差异及可预测性相关的利率风险。在坚持众多监管约束的同时，从期限转换中获利和对冲利率风险这两个相互对立的目标，使得资产负债管理成为一个具有挑战性的问题。我们将资产负债管理表述为一个高维随机控制问题，其中每月的投资和融资决策推动银行资产负债表的演变。为了在存在约束和随机利率的情况下找到使长期效用最大化的策略，我们训练对决策过程进行参数化的神经网络。我们的实验提供了实际见解，并证明深度资产负债管理方法推导出的动态策略优于静态基准。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/e466c8619810/frai-06-1120297-g0019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/1a4d6f12e61b/frai-06-1120297-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/b00d21543656/frai-06-1120297-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/801c918a6d6c/frai-06-1120297-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/3b050863995c/frai-06-1120297-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/86b21f155bb5/frai-06-1120297-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/77827608143d/frai-06-1120297-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/f68617b72786/frai-06-1120297-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/1804396a86e6/frai-06-1120297-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/3afe536d3c3a/frai-06-1120297-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/ad1fbc368038/frai-06-1120297-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/d24dd9a13945/frai-06-1120297-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/51e227eb6c8b/frai-06-1120297-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/a1067fbf75d0/frai-06-1120297-g0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/ffde53a444bf/frai-06-1120297-g0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/e446408b0613/frai-06-1120297-g0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/d0da24f52f14/frai-06-1120297-g0016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/464b6d1e87b8/frai-06-1120297-g0017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/b23acc109fec/frai-06-1120297-g0018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/e466c8619810/frai-06-1120297-g0019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/1a4d6f12e61b/frai-06-1120297-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/b00d21543656/frai-06-1120297-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/801c918a6d6c/frai-06-1120297-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/3b050863995c/frai-06-1120297-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/86b21f155bb5/frai-06-1120297-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/77827608143d/frai-06-1120297-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/f68617b72786/frai-06-1120297-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/1804396a86e6/frai-06-1120297-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/3afe536d3c3a/frai-06-1120297-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/ad1fbc368038/frai-06-1120297-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/d24dd9a13945/frai-06-1120297-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/51e227eb6c8b/frai-06-1120297-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/a1067fbf75d0/frai-06-1120297-g0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/ffde53a444bf/frai-06-1120297-g0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/e446408b0613/frai-06-1120297-g0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/d0da24f52f14/frai-06-1120297-g0016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/464b6d1e87b8/frai-06-1120297-g0017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/b23acc109fec/frai-06-1120297-g0018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/52fb/10073554/e466c8619810/frai-06-1120297-g0019.jpg

相似文献

1
Deep treasury management for banks.银行的深度资金管理。
Front Artif Intell. 2023 Mar 22;6:1120297. doi: 10.3389/frai.2023.1120297. eCollection 2023.
2
A case study for unlocking the potential of deep learning in asset-liability-management.一个关于挖掘深度学习在资产负债管理中潜力的案例研究。
Front Artif Intell. 2023 May 22;6:1177702. doi: 10.3389/frai.2023.1177702. eCollection 2023.
3
On the Hedging of Interest Rate Margins on Bank Demand Deposits.
Comput Econ. 2022 Aug 7:1-33. doi: 10.1007/s10614-022-10287-x.
4
From deterministic to stochastic: an interpretable stochastic model-free reinforcement learning framework for portfolio optimization.从确定性到随机性：一种用于投资组合优化的可解释的无模型随机强化学习框架。
Appl Intell (Dordr). 2023;53(12):15188-15203. doi: 10.1007/s10489-022-04217-5. Epub 2022 Nov 11.
5
Determinants of bank's efficiency in an emerging economy: A data envelopment analysis approach.新兴经济体中银行效率的决定因素：数据包络分析方法。
PLoS One. 2023 Mar 14;18(3):e0281663. doi: 10.1371/journal.pone.0281663. eCollection 2023.
6
Multi-agent reinforcement learning approach for hedging portfolio problem.用于套期保值投资组合问题的多智能体强化学习方法。
Soft comput. 2021;25(12):7877-7885. doi: 10.1007/s00500-021-05801-6. Epub 2021 Apr 19.
7
Learning to trade via direct reinforcement.通过直接强化学习进行交易。
IEEE Trans Neural Netw. 2001;12(4):875-89. doi: 10.1109/72.935097.
8
Intelligent Evaluation and Early Warning of Liquidity Risk of Commercial Banks Based on RNN.基于 RNN 的商业银行流动性风险智能评估与预警
Comput Intell Neurosci. 2022 May 18;2022:7325798. doi: 10.1155/2022/7325798. eCollection 2022.
9
Deep Neural Networks for Behavioral Credit Rating.用于行为信用评级的深度神经网络。
Entropy (Basel). 2020 Dec 27;23(1):27. doi: 10.3390/e23010027.
10
Treasury inconvenience yields during the COVID-19 crisis.新冠疫情危机期间美国国债的非便利收益率
J financ econ. 2022 Jan;143(1):57-79. doi: 10.1016/j.jfineco.2021.05.044. Epub 2021 May 28.

引用本文的文献

1
Adoption of artificial intelligence and machine learning in banking systems: a qualitative survey of board of directors.银行系统中人工智能和机器学习的应用：对董事会的定性调查
Front Artif Intell. 2024 Nov 27;7:1440051. doi: 10.3389/frai.2024.1440051. eCollection 2024.
2
A case study for unlocking the potential of deep learning in asset-liability-management.一个关于挖掘深度学习在资产负债管理中潜力的案例研究。
Front Artif Intell. 2023 May 22;6:1177702. doi: 10.3389/frai.2023.1177702. eCollection 2023.

本文引用的文献

1
Backpropagation through time and the brain.时间反向传播与大脑。
Curr Opin Neurobiol. 2019 Apr;55:82-89. doi: 10.1016/j.conb.2019.01.011. Epub 2019 Mar 7.