{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:22:13Z","timestamp":1791570133804,"version":"4.3.4"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Unlike traditional time series, the action sequences of human decision making usually involve many cognitive processes such as beliefs, desires, intentions, and theory of mind, i.e., what others are thinking. This makes predicting human decision-making challenging to be treated agnostically to the underlying psychological mechanisms. We propose here to use a recurrent neural network architecture based on long short-term memory networks (LSTM) to predict the time series of the actions taken by human subjects engaged in gaming activity, the first application of such methods in this research domain. In this study, we collate the human data from 8 published literature of the Iterated Prisoner\u2019s Dilemma comprising 168,386 individual decisions and post-process them into 8,257 behavioral trajectories of 9 actions each for both players. Similarly, we collate 617 trajectories of 95 actions from 10 different published studies of Iowa Gambling Task experiments with healthy human subjects. We train our prediction networks on the behavioral data and demonstrate a clear advantage over the state-of-the-art methods in predicting human decision-making trajectories in both the single-agent scenario of the Iowa Gambling Task and the multi-agent scenario of the Iterated Prisoner\u2019s Dilemma. Moreover, we observe that the weights of the LSTM networks modeling the top performers tend to have a wider distribution compared to poor performers, as well as a larger bias, which suggest possible interpretations for the distribution of strategies adopted by each group.<\/jats:p>","DOI":"10.1371\/journal.pone.0267907","type":"journal-article","created":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T13:25:36Z","timestamp":1654003536000},"page":"e0267907","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":15,"title":["Predicting human decision making in psychological tasks with recurrent neural networks"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7979-5509","authenticated-orcid":true,"given":"Baihan","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djallel","family":"Bouneffouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillermo","family":"Cecchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"issue":"1","key":"pone.0267907.ref001","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/BF02294587","article-title":"Comparing the predictive powers of alternative multiple regression models","volume":"56","author":"MR Hagerty","year":"1991","journal-title":"Psychometrika"},{"issue":"4","key":"pone.0267907.ref002","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1002\/cjce.5450850401","article-title":"The use of simplified or misspecified models: Linear case","volume":"85","author":"S Wu","year":"2007","journal-title":"The Canadian Journal of Chemical Engineering"},{"issue":"6","key":"pone.0267907.ref003","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1177\/1745691617693393","article-title":"Choosing prediction over explanation in psychology: Lessons from machine learning","volume":"12","author":"T Yarkoni","year":"2017","journal-title":"Perspectives on Psychological Science"},{"issue":"1","key":"pone.0267907.ref004","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/002200278002400101","article-title":"Effective choice in the prisoner\u2019s dilemma","volume":"24","author":"R Axelrod","year":"1980","journal-title":"Journal of conflict resolution"},{"issue":"5","key":"pone.0267907.ref005","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1017\/S1930297500001200","article-title":"Bayesian analysis of deterministic and stochastic prisoner\u2019s dilemma games","volume":"4","author":"H Kunreuther","year":"2009","journal-title":"Judgment and Decision Making"},{"issue":"2","key":"pone.0267907.ref006","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1016\/j.geb.2008.07.003","article-title":"Cooperative behavior and the frequency of social interaction","volume":"66","author":"J Duffy","year":"2009","journal-title":"Games and Economic Behavior"},{"issue":"5","key":"pone.0267907.ref007","article-title":"Predicting human cooperation","volume":"11","author":"JJ Nay","year":"2016","journal-title":"PloS one"},{"issue":"1-3","key":"pone.0267907.ref008","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/0010-0277(94)90018-3","article-title":"Insensitivity to future consequences following damage to human prefrontal cortex","volume":"50","author":"A Bechara","year":"1994","journal-title":"Cognition"},{"issue":"3","key":"pone.0267907.ref009","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1037\/1040-3590.14.3.253","article-title":"A contribution of cognitive decision models to clinical assessment: decomposing performance on the Bechara gambling task","volume":"14","author":"JR Busemeyer","year":"2002","journal-title":"Psychological assessment"},{"issue":"8","key":"pone.0267907.ref010","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1080\/03640210802352992","article-title":"Comparison of decision learning models using the generalization criterion method","volume":"32","author":"WY Ahn","year":"2008","journal-title":"Cognitive science"},{"issue":"1","key":"pone.0267907.ref011","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.jmp.2009.10.002","article-title":"Cognitive mechanisms underlying risky decision-making in chronic cannabis users","volume":"54","author":"DJ Fridberg","year":"2010","journal-title":"Journal of mathematical psychology"},{"key":"pone.0267907.ref012","doi-asserted-by":"crossref","first-page":"61","DOI":"10.3389\/fnins.2012.00061","article-title":"Iowa Gambling Task: There is more to consider than long-term outcome. Using a linear equation model to disentangle the impact of outcome and frequency of gains and losses","volume":"6","author":"A Horstmann","year":"2012","journal-title":"Frontiers in Neuroscience"},{"key":"pone.0267907.ref013","doi-asserted-by":"crossref","unstructured":"Lin B, Bouneffouf D, Cecchi G. Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits, and RL. arXiv preprint arXiv:200504544. 2020;.","DOI":"10.1007\/978-981-16-1288-6_2"},{"key":"pone.0267907.ref014","unstructured":"Lin B, Bouneffouf D, Reinen J, Rish I, Cecchi G. A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry. In: Proceedings of the Nineteenth International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS-20. International Foundation for Autonomous Agents and Multiagent Systems; 2020. p. 744\u2013752."},{"key":"pone.0267907.ref015","doi-asserted-by":"crossref","unstructured":"Lin B, Bouneffouf D, Cecchi G. Split Q learning: reinforcement learning with two-stream rewards. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press; 2019. p. 6448\u20136449.","DOI":"10.24963\/ijcai.2019\/913"},{"key":"pone.0267907.ref016","doi-asserted-by":"crossref","unstructured":"Lin B, Cecchi G, Bouneffouf D, Reinen J, Rish I. Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL. In: International Workshop on Human Brain and Artificial Intelligence. Springer; 2021. p. 14\u201333.","DOI":"10.1007\/978-981-16-1288-6_2"},{"key":"pone.0267907.ref017","unstructured":"Lin B, Bouneffouf D, Cecchi G. Online Learning in Iterated Prisoner\u2019s Dilemma to Mimic Human Behavior. arXiv preprint arXiv:200606580. 2020;."},{"key":"pone.0267907.ref018","doi-asserted-by":"crossref","unstructured":"Lin B, Bouneffouf D, Cecchi G. Predicting Human Decision Making with LSTM. In: 2022 International Joint Conference on Neural Networks (IJCNN). IEEE; 2022.","DOI":"10.1109\/IJCNN55064.2022.9892963"},{"key":"pone.0267907.ref019","unstructured":"Lipton ZC, Berkowitz J, Elkan C. A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:150600019. 2015;."},{"issue":"10","key":"pone.0267907.ref020","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: what it does and how to do it","volume":"78","author":"PJ Werbos","year":"1990","journal-title":"Proceedings of the IEEE"},{"issue":"8","key":"pone.0267907.ref021","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural computation"},{"issue":"4489","key":"pone.0267907.ref022","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1126\/science.7466396","article-title":"The evolution of cooperation","volume":"211","author":"R Axelrod","year":"1981","journal-title":"science"},{"issue":"418","key":"pone.0267907.ref023","doi-asserted-by":"crossref","first-page":"570","DOI":"10.2307\/2234532","article-title":"Rational cooperation in the finitely repeated prisoner\u2019s dilemma: Experimental evidence","volume":"103","author":"J Andreoni","year":"1993","journal-title":"The economic journal"},{"issue":"5","key":"pone.0267907.ref024","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1257\/000282805775014434","article-title":"Cooperation under the shadow of the future: experimental evidence from infinitely repeated games","volume":"95","author":"PD B\u00f3","year":"2005","journal-title":"American economic review"},{"issue":"4","key":"pone.0267907.ref025","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1257\/aer.96.4.1029","article-title":"The speed of learning in noisy games: Partial reinforcement and the sustainability of cooperation","volume":"96","author":"Y Bereby-Meyer","year":"2006","journal-title":"American Economic Review"},{"issue":"1","key":"pone.0267907.ref026","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1257\/aer.101.1.411","article-title":"The evolution of cooperation in infinitely repeated games: Experimental evidence","volume":"101","author":"P Dal B\u00f3","year":"2011","journal-title":"American Economic Review"},{"issue":"1","key":"pone.0267907.ref027","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1257\/aer.102.1.337","article-title":"A continuous dilemma","volume":"102","author":"D Friedman","year":"2012","journal-title":"American Economic Review"},{"issue":"2","key":"pone.0267907.ref028","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1257\/aer.102.2.720","article-title":"Slow to anger and fast to forgive: Cooperation in an uncertain world","volume":"102","author":"D Fudenberg","year":"2012","journal-title":"American Economic Review"},{"issue":"1","key":"pone.0267907.ref029","first-page":"340","article-title":"Data from 617 healthy participants performing the Iowa gambling task: A \u201cmany labs\u201d collaboration","volume":"3","author":"H Steingroever","year":"2015","journal-title":"Journal of Open Psychology Data"},{"key":"pone.0267907.ref030","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;."},{"key":"pone.0267907.ref031","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-27752-1","volume-title":"New introduction to multiple time series analysis","author":"H L\u00fctkepohl","year":"2005"},{"issue":"6","key":"pone.0267907.ref032","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical model identification","volume":"19","author":"H Akaike","year":"1974","journal-title":"IEEE transactions on automatic control"},{"issue":"253","key":"pone.0267907.ref033","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","article-title":"The Kolmogorov-Smirnov test for goodness of fit","volume":"46","author":"FJ Massey","year":"1951","journal-title":"Journal of the American statistical Association"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T16:17:33Z","timestamp":1675700253000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267907"}},"subtitle":[],"editor":[{"given":"Luo-Luo","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":33,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0267907","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.11.15.468588","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,31]]}}}