{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T15:09:43Z","timestamp":1748272183374,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031264214"},{"type":"electronic","value":"9783031264221"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26422-1_12","type":"book-chapter","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T01:08:37Z","timestamp":1679879317000},"page":"185-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Risk-Aware Reinforcement Learning for\u00a0Multi-Period Portfolio Selection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8829-0863","authenticated-orcid":false,"given":"David","family":"Winkel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8083-7323","authenticated-orcid":false,"given":"Niklas","family":"Strau\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6566-6343","authenticated-orcid":false,"given":"Matthias","family":"Schubert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4861-1412","authenticated-orcid":false,"given":"Thomas","family":"Seidl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,18]]},"reference":[{"key":"12_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-030-86514-6_15","volume-title":"Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track","author":"C Abrate","year":"2021","unstructured":"Abrate, C., et al.: Continuous-action reinforcement learning for portfolio allocation of a life insurance company. In: Dong, Y., Kourtellis, N., Hammer, B., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12978, pp. 237\u2013252. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86514-6_15"},{"issue":"6","key":"12_CR2","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","volume":"19","author":"H Akaike","year":"1974","unstructured":"Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. Control 19(6), 716\u2013723 (1974)","journal-title":"IEEE Trans. Autom. Control"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.eswa.2017.06.023","volume":"87","author":"S Almahdi","year":"2017","unstructured":"Almahdi, S., Yang, S.Y.: An adaptive portfolio trading system: a risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown. Expert Syst. Appl. 87, 267\u2013279 (2017)","journal-title":"Expert Syst. Appl."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Andr\u00e9, E., Coqueret, G.: Dirichlet policies for reinforced factor portfolios. arXiv preprint arXiv:2011.05381 (2020)","DOI":"10.2139\/ssrn.3726714"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Ariyo, A.A., Adewumi, A.O., Ayo, C.K.: Stock price prediction using the Arima model. In: 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, pp. 106\u2013112. IEEE (2014)","DOI":"10.1109\/UKSim.2014.67"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Bisi, L., Sabbioni, L., Vittori, E., Papini, M., Restelli, M.: Risk-averse trust region optimization for reward-volatility reduction. In: Twenty-Ninth International Joint Conference on Artificial Intelligence Special Track, pp. 4583\u20134589. International Joint Conferences on Artificial Intelligence Organization (2020)","DOI":"10.24963\/ijcai.2020\/632"},{"issue":"5","key":"12_CR7","doi-asserted-by":"publisher","first-page":"28","DOI":"10.2469\/faj.v48.n5.28","volume":"48","author":"F Black","year":"1992","unstructured":"Black, F., Litterman, R.: Global portfolio optimization. Finan. Analy. J. 48(5), 28\u201343 (1992)","journal-title":"Finan. Analy. J."},{"issue":"1","key":"12_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2400000023","volume":"3","author":"S Boyd","year":"2017","unstructured":"Boyd, S., et al.: Multi-period trading via convex optimization. Found. Trends Optim. 3(1), 1\u201376 (2017)","journal-title":"Found. Trends Optim."},{"key":"12_CR9","unstructured":"Brigham, E.F., Ehrhardt, M.C.: Financial Management: Theory & Practice. Cengage Learning (2019)"},{"issue":"1","key":"12_CR10","first-page":"6070","volume":"18","author":"Y Chow","year":"2017","unstructured":"Chow, Y., Ghavamzadeh, M., Janson, L., Pavone, M.: Risk-constrained reinforcement learning with percentile risk criteria. J. Mach. Learn. Res. 18(1), 6070\u20136120 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Costa, G., Kwon, R.: A regime-switching factor model for mean-variance optimization. J. Risk (2020)","DOI":"10.21314\/JOR.2020.432"},{"key":"12_CR12","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"issue":"4","key":"12_CR13","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1111\/jofi.12048","volume":"69","author":"DD Guercio","year":"2014","unstructured":"Guercio, D.D., Reuter, J.: Mutual fund performance and the incentive to generate alpha. J. Financ. 69(4), 1673\u20131704 (2014)","journal-title":"J. Financ."},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Hassan, M.R., Nath, B.: Stock market forecasting using hidden Markov model: a new approach. In: 5th International Conference on Intelligent Systems Design and Applications (ISDA 2005), pp. 192\u2013196. IEEE (2005)","DOI":"10.1109\/ISDA.2005.85"},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1016\/j.procs.2018.05.050","volume":"132","author":"M Hiransha","year":"2018","unstructured":"Hiransha, M., Gopalakrishnan, E.A., Menon, V.K., Soman, K.: NSE stock market prediction using deep-learning models. Procedia Comput. Sci. 132, 1351\u20131362 (2018)","journal-title":"Procedia Comput. Sci."},{"issue":"1","key":"12_CR16","first-page":"77","volume":"7","author":"H Markowitz","year":"1952","unstructured":"Markowitz, H.: Portfolio selection. J. Finan. 7(1), 77\u201391 (1952)","journal-title":"J. Finan."},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Munim, Z.H., Shakil, M.H., Alon, I.: Next-day bitcoin price forecast. J. Risk Finan. Manag. 12(2), 103 (2019)","DOI":"10.3390\/jrfm12020103"},{"key":"12_CR18","unstructured":"Navon, A., Shamsian, A., Fetaya, E., Chechik, G.: Learning the pareto front with hypernetworks. In: International Conference on Learning Representations (2021)"},{"issue":"2","key":"12_CR19","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/ijfs6020036","volume":"6","author":"N Nguyen","year":"2018","unstructured":"Nguyen, N.: Hidden Markov model for stock trading. Int. J. Finan. Stud. 6(2), 36 (2018)","journal-title":"Int. J. Finan. Stud."},{"issue":"3","key":"12_CR20","doi-asserted-by":"publisher","first-page":"2098","DOI":"10.1007\/s11227-017-2228-y","volume":"76","author":"X Pang","year":"2020","unstructured":"Pang, X., Zhou, Y., Wang, P., Lin, W., Chang, V.: An innovative neural network approach for stock market prediction. J. Supercomput. 76(3), 2098\u20132118 (2020)","journal-title":"J. Supercomput."},{"key":"12_CR21","unstructured":"Parisotto, E., et al.: Stabilizing transformers for reinforcement learning. In: International Conference on Machine Learning, pp. 7487\u20137498. PMLR (2020)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Pirotta, M., Parisi, S., Restelli, M.: Multi-objective reinforcement learning with continuous pareto frontier approximation. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9617"},{"key":"12_CR23","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"12_CR24","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1613\/jair.3987","volume":"48","author":"DM Roijers","year":"2013","unstructured":"Roijers, D.M., Vamplew, P., Whiteson, S., Dazeley, R.: A survey of multi-objective sequential decision-making. J. Artif. Intell. Res. 48, 67\u2013113 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"12_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1007\/3-540-44491-2_34","volume-title":"Intelligent Data Engineering and Automated Learning \u2014 IDEAL 2000. Data Mining, Financial Engineering, and Intelligent Agents","author":"M Sato","year":"2000","unstructured":"Sato, M., Kobayashi, S.: Variance-penalized reinforcement learning for risk-averse asset allocation. In: Leung, K.S., Chan, L.-W., Meng, H. (eds.) IDEAL 2000. LNCS, vol. 1983, pp. 244\u2013249. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44491-2_34"},{"key":"12_CR26","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Schwarz, G.: Estimating the dimension of a model. Ann. Statist. 6, 461\u2013464 (1978)","DOI":"10.1214\/aos\/1176344136"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Sharpe, W.F.: The sharpe ratio. Streetwise Best J. Portfolio Manag. 3, 169\u2013185 (1998)","DOI":"10.1515\/9781400829408-022"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Sobel, M.J.: The variance of discounted Markov decision processes. J. Appl. Probab. 19, pp. 794\u2013802 (1982)","DOI":"10.1017\/S0021900200023123"},{"issue":"4","key":"12_CR30","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1111\/mafi.12281","volume":"30","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhou, X.Y.: Continuous-time mean-variance portfolio selection: a reinforcement learning framework. Math. Financ. 30(4), 1273\u20131308 (2020)","journal-title":"Math. Financ."},{"key":"12_CR31","unstructured":"Wu, N., Green, B., Ben, X., O\u2019Banion, S.: Deep transformer models for time series forecasting: the influenza prevalence case. arXiv preprint arXiv:2001.08317 (2020)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liu, B., Whiteson, S.: Mean-variance policy iteration for risk-averse reinforcement learning. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i12.17302"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26422-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T19:10:49Z","timestamp":1683054649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26422-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264214","9783031264221"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26422-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"236","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}