{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:30:56Z","timestamp":1753893056737,"version":"3.41.2"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Retail banks use <jats:italic>Asset Liability Management<\/jats:italic> (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.<\/jats:p>","DOI":"10.3389\/frai.2023.1120297","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T05:24:02Z","timestamp":1679462642000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep treasury management for banks"],"prefix":"10.3389","volume":"6","author":[{"given":"Holger","family":"Englisch","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Krabichler","sequence":"additional","affiliation":[]},{"given":"Konrad J.","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Schwarz","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,3,22]]},"reference":[{"key":"B1","unstructured":"Basel III: A Global Regulatory Framework for More Resilient Banks and Banking Systems (revised version)2011"},{"journal-title":"Interest Rate Models-Theory and Practice","year":"2007","author":"Brigo","key":"B2"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1080\/14697688.2019.1571683","article-title":"Deep hedgingQuant","volume":"19","author":"Buehler","year":"2019","journal-title":"Finance"},{"key":"B4","doi-asserted-by":"crossref","unstructured":"BuehlerH.\n            HorvathB.\n            LyonsT.\n            Perez ArribasI.\n            WoodB.\n          Generating financial markets with signatures2020","DOI":"10.2139\/ssrn.3657366"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.07844","article-title":"Deep hedging: learning to remove the drift under trading frictions with minimal equivalent near-martingale measures","author":"Buehler","year":"","journal-title":"arXiv:2111.07844"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4151026","article-title":"Deep bellman hedging","author":"Buehler","year":"","journal-title":"arXiv:2207.00932"},{"key":"B7","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3390\/risks8010016","article-title":"Assessing asset-liability risk with neural networks","volume":"8","author":"Cheridito","year":"2020","journal-title":"Risks"},{"key":"B8","doi-asserted-by":"crossref","unstructured":"CheyetteO.\n          Markov Representation of the Heath-Jarrow-Morton Model2001","DOI":"10.2139\/ssrn.6073"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3782412","article-title":"Black-box model risk in finance","author":"Cohen","year":"2021","journal-title":"arXiv:2102.04757"},{"key":"B10","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s00780-016-0291-5","article-title":"A general HJM framework for multiple yield curve modelling","volume":"20","author":"Cuchiero","year":"2016","journal-title":"Finance Stochast"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.01570","article-title":"Goal-conditioned generators of deep policies","author":"Faccio","year":"2022","journal-title":"arXiv:2207.01570"},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-68015-4","author":"Filipovi\u0107","year":"2009","journal-title":"Term-Structure Models-A Graduate Course"},{"key":"B13","doi-asserted-by":"crossref","unstructured":"FontouraA.\n            HaddadD.\n            BezerraE.\n          A \u201cDeep reinforcement learning approach to asset-liability management,\u201d in 2019","DOI":"10.1109\/BRACIS.2019.00046"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.10295","article-title":"Noisy networks for exploration","author":"Fortunato","year":"2019","journal-title":"arXiv:1706.10295"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21617-1","author":"Glasserman","year":"2003","journal-title":"Monte Carlo Methods in Financial Engineering"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.10122","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv:1803.10122"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.07422","article-title":"Deep learning approximation for stochastic control problems","author":"Han","year":"2016","journal-title":"arXiv:1611.07422"},{"key":"B18","unstructured":"\u201cDeep residual learning for image recognition,\u201d770778\n            HeK.\n            ZhangX.\n            RenS.\n            SunJ.\n          32166560IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016"},{"key":"B19","doi-asserted-by":"publisher","first-page":"77","DOI":"10.2307\/2951677","article-title":"Bond pricing and the term structure of interest rates: a new methodology for contingent claims valuation","volume":"60","author":"Heath","year":"1992","journal-title":"Econometr. J. Econ. Soc"},{"key":"B20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1142\/S0218488598000094","article-title":"The vanishing gradient problem during learning recurrent neural nets and problem solutions","volume":"6","author":"Hochreiter","year":"1998","journal-title":"Int. J. Uncertainty Fuzziness Knowl. Based Syst"},{"key":"B21","doi-asserted-by":"publisher","first-page":"138","DOI":"10.3390\/risks9070138","article-title":"Deep hedging under rough volatility","volume":"9","author":"Horvath","year":"2021","journal-title":"Risks"},{"key":"B22","doi-asserted-by":"publisher","first-page":"448","DOI":"10.48550\/arXiv.1502.03167","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","volume":"37","author":"Ioffe","year":"2015","journal-title":"Proc. Mach. Learn. Res"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.05034","article-title":"Deep replication of a runoff portfolio","author":"Krabichler","year":"2020","journal-title":"arXiv:2009.05034"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09611","article-title":"Learning a functional control for high-frequency finance","author":"Leal","year":"2021","journal-title":"arXiv:2006.09611"},{"key":"B25","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.conb.2019.01.011","article-title":"Backpropagation through time and the brain","volume":"55","author":"Lillicrap","year":"2019","journal-title":"Curr. Opin. Neurobiol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3905\/jfi.1991.692347","article-title":"Common factors affecting bond returns","volume":"1","author":"Litterman","year":"1991","journal-title":"J. Fixed Income"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.03265","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2021","journal-title":"arXiv:1908.03265"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1080\/14697688.2022.2056073","article-title":"Robust deep hedging","volume":"22","author":"L\u00fctkebohmert","year":"2022","journal-title":"Quantit. Finance"},{"key":"B29","doi-asserted-by":"crossref","unstructured":"MazziB.\n          Treasury Finance and Development Banking: A Guide to Credit, Debt, and Risk. John Wiley & Sons2013","DOI":"10.1002\/9781118738177"},{"journal-title":"Machine Learning: A Probabilistic Perspective","year":"2012","author":"Murphy","key":"B30"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1145\/3533271.3561731","article-title":"Deep hedging: continuous reinforcement learning for hedging of general portfolios across multiple risk aversions","author":"Murray","year":"2022","journal-title":"arXiv:2207.07467"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.48550\/arXiv.1211.5063","article-title":"On the difficulty of training recurrent neural networks","volume":"28","author":"Pascanu","year":"2013","journal-title":"Proc. Mach. Learn. Res"},{"key":"B33","unstructured":"PedersenH.\n            CampbellM. P.\n            ChristiansenS. L.\n            CoxS. H.\n            FinnD.\n            GriffinK.\n          Economic Scenario Generators: A Practical Guide. Society of Actuaries2016"},{"key":"B34","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1111\/mafi.12365","article-title":"Deep empirical risk minimization in finance: Looking into the future","volume":"33","author":"Reppen","year":"2023","journal-title":"Math. Finance"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.02875","article-title":"Reinforcement learning upside down: don't predict rewards-just map them to actions","author":"Schmidhuber","year":"2020","journal-title":"arXiv:1912.02875"},{"key":"B36","doi-asserted-by":"publisher","first-page":"3191","DOI":"10.48550\/arXiv.1612.08810","article-title":"The predictron: end-to-end learning and planning","volume":"70","author":"Silver","year":"2017","journal-title":"Proc. Mach. Learn. Res"},{"key":"B37","doi-asserted-by":"crossref","unstructured":"SpillmannM.\n            D\u00f6hnertK.\n            RissiR.\n          Asset Liability Management (ALM) in Banken. Springer Gabler2019","DOI":"10.1007\/978-3-658-25202-1"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.02877","article-title":"Training agents using upside-down reinforcement learning","author":"Srivastava","year":"2021","journal-title":"arXiv:1912.02877"},{"key":"B39","unstructured":"\u201cEstimating and interpreting forward interest rates: Sweden 1992-1994,\u201d\n            SvenssonL. E.\n          National Bureau of Economic Research, Working Paper Series, Vol. 48711994"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.00937","article-title":"Neural discrete representation learning","author":"van der Oord","year":"2018","journal-title":"arXiv:1711.00937"},{"key":"B41","unstructured":"\u201cLearning values across many orders of magnitude,\u201d\n            van HasseltH. P.\n            GuezA.\n            HesselM.\n            MnihV.\n            SilverD.\n          2016"},{"key":"B42","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/0304-405X(77)90016-2","article-title":"An equilibrium characterization of the term structure","volume":"5","author":"Va\u0161i\u010dek","year":"1977","journal-title":"J. Finance Econ"},{"journal-title":"The Theory of Games and Economic Behavior","year":"1947","author":"von Neumann","key":"B43"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: what it does and how to do it","volume":"78","author":"Werbos","year":"1990","journal-title":"Proc. IEEE"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1080\/14697688.2020.1730426","article-title":"Quant GANs: deep generation of financial time series","volume":"20","author":"Wiese","year":"2020","journal-title":"Quantit. Finance"},{"key":"B46","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3613600","article-title":"Deep learning for portfolio optimization","author":"Zhang","year":"2020","journal-title":"arXiv:2005.13665"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1120297\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T05:24:13Z","timestamp":1679462653000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1120297\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":47,"alternative-id":["10.3389\/frai.2023.1120297"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1120297","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2023,3,22]]},"article-number":"1120297"}}