{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:08:23Z","timestamp":1755907703685,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698664","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"478-486","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven Derivative Hedging with Quadratic Variation Penalty"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1121-818X","authenticated-orcid":false,"given":"Alessio","family":"Brini","sequence":"first","affiliation":[{"name":"Pratt School of Engineering, Duke University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2797-1547","authenticated-orcid":false,"given":"Giacomo","family":"Domeniconi","sequence":"additional","affiliation":[{"name":"AI Innovation Team, U.S. Bank, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5511-698X","authenticated-orcid":false,"given":"Ali","family":"Fathi","sequence":"additional","affiliation":[{"name":"AI Innovation Team, U.S. Bank, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4855601"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on learning representations.","author":"Andrychowicz Marcin","year":"2021","unstructured":"Marcin Andrychowicz, Anton Raichuk, Piotr Sta\u0144czyk, Manu Orsini, Sertan Girgin, Rapha\u00ebl Marinier, Leonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, 2021. What matters for on-policy deep actor-critic methods? a large-scale study. In International conference on learning representations."},{"key":"e_1_3_2_1_3_1","volume-title":"Market Impacts and the Life Cycle of Investors Orders. ERN: Other Microeconomics: General Equilibrium & Disequilibrium Models of Financial Markets (Topic)","author":"Bacry Emmanuel","year":"2014","unstructured":"Emmanuel Bacry, Adrianna Iuga, Matthieu Lasnier, and Charles-Albert Lehalle. 2014. Market Impacts and the Life Cycle of Investors Orders. ERN: Other Microeconomics: General Equilibrium & Disequilibrium Models of Financial Markets (Topic) (2014). https:\/\/api.semanticscholar.org\/CorpusID:1652468"},{"key":"e_1_3_2_1_4_1","unstructured":"Philippe Bergault and Olivier Gu\u2019eant. 2023. Liquidity Dynamics in RFQ Markets and Impact on Pricing. https:\/\/api.semanticscholar.org\/CorpusID:261660584"},{"key":"e_1_3_2_1_5_1","volume-title":"Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems 24","author":"Bergstra James","year":"2011","unstructured":"James Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems 24 (2011)."},{"key":"e_1_3_2_1_6_1","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, 2 (2012).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_7_1","volume-title":"Hedging derivative securities and incomplete markets: An \u03f5 -arbitrage approach. Operations research 49, 3","author":"Bertsimas Dimitris","year":"2001","unstructured":"Dimitris Bertsimas, Leonid Kogan, and Andrew\u00a0W Lo. 2001. Hedging derivative securities and incomplete markets: An \u03f5 -arbitrage approach. Operations research 49, 3 (2001), 372\u2013397."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"e_1_3_2_1_9_1","series-title":"SIAM review 60, 2","volume-title":"Optimization methods for large-scale machine learning","author":"Bottou L\u00e9on","year":"2018","unstructured":"L\u00e9on Bottou, Frank\u00a0E Curtis, and Jorge Nocedal. 2018. Optimization methods for large-scale machine learning. SIAM review 60, 2 (2018), 223\u2013311."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/003465303762687758"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep reinforcement trading with predictable returns. Physica A: Statistical Mechanics and its Applications 622","author":"Brini Alessio","year":"2023","unstructured":"Alessio Brini and Daniele Tantari. 2023. Deep reinforcement trading with predictable returns. Physica A: Statistical Mechanics and its Applications 622 (2023), 128901."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2019.1571683"},{"key":"e_1_3_2_1_13_1","volume-title":"Abides: Towards high-fidelity market simulation for ai research. arXiv preprint arXiv:1904.12066","author":"Byrd David","year":"2019","unstructured":"David Byrd, Maria Hybinette, and Tucker\u00a0Hybinette Balch. 2019. Abides: Towards high-fidelity market simulation for ai research. arXiv preprint arXiv:1904.12066 (2019)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1129370"},{"key":"e_1_3_2_1_15_1","volume-title":"Deep hedging of derivatives using reinforcement learning. arXiv preprint arXiv:2103.16409","author":"Cao Jay","year":"2021","unstructured":"Jay Cao, Jacky Chen, John Hull, and Zissis Poulos. 2021. Deep hedging of derivatives using reinforcement learning. arXiv preprint arXiv:2103.16409 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1806343"},{"key":"e_1_3_2_1_17_1","volume-title":"Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems 2, 4","author":"Cybenko George","year":"1989","unstructured":"George Cybenko. 1989. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems 2, 4 (1989), 303\u2013314."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2020.1.045"},{"key":"e_1_3_2_1_19_1","volume-title":"Implementation matters in deep policy gradients: A case study on ppo and trpo. arXiv preprint arXiv:2005.12729","author":"Engstrom Logan","year":"2020","unstructured":"Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, and Aleksander Madry. 2020. Implementation matters in deep policy gradients: A case study on ppo and trpo. arXiv preprint arXiv:2005.12729 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"A comparison of reinforcement learning and deep trajectory based stochastic control agents for stepwise mean-variance hedging. arXiv preprint arXiv:2302.07996","author":"Fathi Ali","year":"2023","unstructured":"Ali Fathi and Bernhard Hientzsch. 2023. A comparison of reinforcement learning and deep trajectory based stochastic control agents for stepwise mean-variance hedging. arXiv preprint arXiv:2302.07996 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Towards Robust and Stable Deep Learning Algorithms for Forward Backward Stochastic Differential Equations. ArXiv abs\/1910.11623","author":"G\u00fcler Batuhan","year":"2019","unstructured":"Batuhan G\u00fcler, Alexis Laignelet, and Panos Parpas. 2019. Towards Robust and Stable Deep Learning Algorithms for Forward Backward Stochastic Differential Equations. ArXiv abs\/1910.11623 (2019). https:\/\/api.semanticscholar.org\/CorpusID:204901508"},{"key":"e_1_3_2_1_22_1","volume-title":"QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds. In Jurnal derivate. https:\/\/api.semanticscholar.org\/CorpusID:23773127","author":"Halperin Igor","year":"2017","unstructured":"Igor Halperin. 2017. QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds. In Jurnal derivate. https:\/\/api.semanticscholar.org\/CorpusID:23773127"},{"key":"e_1_3_2_1_23_1","volume-title":"Deep learning approximation for stochastic control problems. arXiv preprint arXiv:1611.07422","author":"Jiequn Han","year":"2016","unstructured":"Jiequn Han 2016. Deep learning approximation for stochastic control problems. arXiv preprint arXiv:1611.07422 (2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. pmlr, 448\u2013456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. pmlr, 448\u2013456."},{"key":"e_1_3_2_1_25_1","volume-title":"Bartlett\u2019s Delta revisited: Variance-optimal hedging in the lognormal SABR and in the rough Bergomi model. arXiv preprint arXiv:2207.13573","author":"Keller-Ressel Martin","year":"2022","unstructured":"Martin Keller-Ressel. 2022. Bartlett\u2019s Delta revisited: Variance-optimal hedging in the lognormal SABR and in the rough Bergomi model. arXiv preprint arXiv:2207.13573 (2022)."},{"key":"e_1_3_2_1_26_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_27_1","volume-title":"Kolm and Gordon Ritter","author":"N.","year":"2019","unstructured":"Petter\u00a0N. Kolm and Gordon Ritter. 2019. Dynamic Replication and Hedging: A Reinforcement Learning Approach. In The Journal of Financial Data Science. https:\/\/api.semanticscholar.org\/CorpusID:201147959"},{"key":"e_1_3_2_1_28_1","volume-title":"Modern perspectives on reinforcement learning in finance. Modern Perspectives on Reinforcement Learning in Finance (September 6","author":"Kolm N","year":"2019","unstructured":"Petter\u00a0N Kolm and Gordon Ritter. 2020. Modern perspectives on reinforcement learning in finance. Modern Perspectives on Reinforcement Learning in Finance (September 6, 2019). The Journal of Machine Learning in Finance 1, 1 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Option pricing and replication with transactions costs. The journal of finance 40, 5","author":"Leland E","year":"1985","unstructured":"Hayne\u00a0E Leland. 1985. Option pricing and replication with transactions costs. The journal of finance 40, 5 (1985), 1283\u20131301."},{"key":"e_1_3_2_1_30_1","volume-title":"FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance. arXiv preprint arXiv:2011.09607","author":"Liu Xiao-Yang","year":"2020","unstructured":"Xiao-Yang Liu, Hongyang Yang, Qian Chen, Runjia Zhang, Liuqing Yang, Bowen Xiao, and Christina\u00a0Dan Wang. 2020. FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance. arXiv preprint arXiv:2011.09607 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2244531"},{"key":"e_1_3_2_1_33_1","unstructured":"Volodymyr Mnih Adri\u00e0\u00a0Puigdom\u00e8nech Badia Mehdi Mirza Alex Graves Timothy\u00a0P. Lillicrap Tim Harley David Silver and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. arxiv:1602.01783\u00a0[cs.LG]"},{"key":"e_1_3_2_1_34_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Huy\u00ean Pham. 2009. Continuous-time stochastic control and optimization with financial applications \/ Huyen Pham. https:\/\/api.semanticscholar.org\/CorpusID:60132565","DOI":"10.1007\/978-3-540-89500-8"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119815068"},{"key":"e_1_3_2_1_37_1","volume-title":"Deep stochastic optimization in finance. Digital Finance","author":"Reppen A\u00a0Max","year":"2022","unstructured":"A\u00a0Max Reppen, H\u00a0Mete Soner, and Valentin Tissot-Daguette. 2022. Deep stochastic optimization in finance. Digital Finance (2022), 1\u201321."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42521-022-00074-6"},{"key":"e_1_3_2_1_39_1","volume-title":"Machine Learning for Trading. Microeconomics: General Equilibrium & Disequilibrium Models of Financial Markets eJournal","author":"Ritter Gordon","year":"2017","unstructured":"Gordon Ritter. 2017. Machine Learning for Trading. Microeconomics: General Equilibrium & Disequilibrium Models of Financial Markets eJournal (2017). https:\/\/api.semanticscholar.org\/CorpusID:158806504"},{"key":"e_1_3_2_1_40_1","volume-title":"Neural networks for option pricing and hedging: a literature review. arXiv preprint arXiv:1911.05620","author":"Ruf Johannes","year":"2019","unstructured":"Johannes Ruf and Weiguan Wang. 2019. Neural networks for option pricing and hedging: a literature review. arXiv preprint arXiv:1911.05620 (2019)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"volume-title":"Stochastic calculus for finance II: Continuous-time models. Vol.\u00a011","author":"E Shreve","key":"e_1_3_2_1_42_1","unstructured":"Steven\u00a0E Shreve 2004. Stochastic calculus for finance II: Continuous-time models. Vol.\u00a011. Springer."},{"key":"e_1_3_2_1_43_1","volume-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation. Adv. Neural Inf. Process. Syst 12 (02","author":"Sutton Richard","year":"2000","unstructured":"Richard Sutton, David Mcallester, Satinder Singh, and Yishay Mansour. 2000. Policy Gradient Methods for Reinforcement Learning with Function Approximation. Adv. Neural Inf. Process. Syst 12 (02 2000)."},{"key":"e_1_3_2_1_44_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning: An Introduction. The MIT Press."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422532"},{"key":"e_1_3_2_1_46_1","volume-title":"Option Dynamic Hedging Using Reinforcement Learning. arXiv preprint arXiv:2306.10743","author":"Zheng Cong","year":"2023","unstructured":"Cong Zheng, Jiafa He, and Can Yang. 2023. Option Dynamic Hedging Using Reinforcement Learning. arXiv preprint arXiv:2306.10743 (2023)."}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","acronym":"ICAIF '24","location":"Brooklyn NY USA"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698664","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:14:16Z","timestamp":1755882856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":46,"alternative-id":["10.1145\/3677052.3698664","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698664","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}