{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T08:06:43Z","timestamp":1789200403191,"version":"build-2803163510"},"reference-count":71,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2225354"],"award-info":[{"award-number":["2225354"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.asoc.2026.116052","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T16:02:57Z","timestamp":1784908977000},"page":"116052","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Directly learning stock trading strategies through profit guided loss functions"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1404-1076","authenticated-orcid":false,"given":"Devroop","family":"Kar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5650","authenticated-orcid":false,"given":"Sheeraja","family":"Rajakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7546-4473","authenticated-orcid":false,"given":"Zimeng","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4082-0439","authenticated-orcid":false,"given":"Travis","family":"Desell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-1310","authenticated-orcid":false,"given":"Alex","family":"Ororbia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-3086","authenticated-orcid":false,"given":"Daniel","family":"Krutz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.116052_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116659","article-title":"Machine learning techniques and data for stock market forecasting: a literature review","volume":"197","author":"Kumbure","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"10.1016\/j.asoc.2026.116052_bib0010","doi-asserted-by":"crossref","first-page":"94","DOI":"10.3390\/ijfs11030094","article-title":"Forecasting stock market prices using machine learning and deep learning models: a systematic review, performance analysis and discussion of implications","volume":"11","author":"Sonkavde","year":"2023","journal-title":"Int. J. Financ. Stud."},{"key":"10.1016\/j.asoc.2026.116052_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.115019","article-title":"A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction","volume":"178","author":"Jing","year":"2021","journal-title":"Expert Syst. Appl."},{"issue":"5","key":"10.1016\/j.asoc.2026.116052_bib0020","doi-asserted-by":"crossref","first-page":"3847","DOI":"10.1007\/s10462-022-10273-7","article-title":"A brief review of portfolio optimization techniques","volume":"56","author":"Gunjan","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.asoc.2026.116052_bib0025","series-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","first-page":"3966","article-title":"Contrastive learning and reward smoothing for deep portfolio management","author":"Lien","year":"2023"},{"key":"10.1016\/j.asoc.2026.116052_bib0030","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1112","article-title":"Reinforcement-learning based portfolio management with augmented asset movement prediction states","volume":"vol. 34","author":"Ye","year":"2020"},{"key":"10.1016\/j.asoc.2026.116052_bib0035","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.jfds.2020.06.002","article-title":"Deep deterministic portfolio optimization","volume":"6","author":"Chaouki","year":"2020","journal-title":"J. Finance Data Sci."},{"key":"10.1016\/j.asoc.2026.116052_bib0040","author":"Jiang"},{"issue":"8","key":"10.1016\/j.asoc.2026.116052_bib0045","doi-asserted-by":"crossref","first-page":"7","DOI":"10.17010\/ijf\/2019\/v13i8\/146301","article-title":"Predicting the stock market index using stochastic time series ARIMA modelling: the sample of BSE and NSE","volume":"13","author":"Reddy","year":"2019","journal-title":"Indian J. Finance"},{"issue":"3","key":"10.1016\/j.asoc.2026.116052_bib0050","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","author":"Bollerslev","year":"1986","journal-title":"J. Econom."},{"issue":"2","key":"10.1016\/j.asoc.2026.116052_bib0055","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.jfineco.2021.08.017","article-title":"Machine learning in the Chinese stock market","volume":"145","author":"Leippold","year":"2022","journal-title":"J. Financ. Econ."},{"key":"10.1016\/j.asoc.2026.116052_bib0060","series-title":"1990 IJCNN International Joint Conference on Neural Networks","first-page":"215","article-title":"Stock price pattern recognition-a recurrent neural network approach","author":"Kamijo","year":"1990"},{"key":"10.1016\/j.asoc.2026.116052_bib0065","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s10614-008-9144-4","article-title":"Testing forecast accuracy of foreign exchange rates: predictions from feed forward and various recurrent neural network architectures","volume":"32","author":"Kiani","year":"2008","journal-title":"Comput. Econ."},{"key":"10.1016\/j.asoc.2026.116052_bib0070","first-page":"1","article-title":"Stock closing price and trend prediction with LSTM-RNN","author":"Smith","year":"2024","journal-title":"J. Artif. Intell. Big Data"},{"key":"10.1016\/j.asoc.2026.116052_bib0075","series-title":"2018 International Symposium on Computer, Consumer and Control (IS3C)","first-page":"10","article-title":"Share price trend prediction using CRNN with LSTM structure","author":"Gao","year":"2018"},{"key":"10.1016\/j.asoc.2026.116052_bib0080","series-title":"Proceedings of 32nd International Conference on, Vol. 63","first-page":"101","article-title":"Stock price prediction using LSTM on Indian share market","author":"Ghosh","year":"2019"},{"key":"10.1016\/j.asoc.2026.116052_bib0085","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1007\/s12652-020-02057-0","article-title":"Prediction model for stock price trend based on recurrent neural network","volume":"12","author":"Zhao","year":"2021","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"10.1016\/j.asoc.2026.116052_bib0090","series-title":"2018 13th International Conference on Computer Science & Education (ICCSE)","first-page":"1","article-title":"High-frequency stock trend forecast using LSTM model","author":"Yao","year":"2018"},{"key":"10.1016\/j.asoc.2026.116052_bib0095","series-title":"Emerging Trends in Expert Applications and Security: Proceedings of ICETEAS 2018","first-page":"493","article-title":"Stock market price prediction using LSTM RNN","author":"Pawar","year":"2019"},{"issue":"15","key":"10.1016\/j.asoc.2026.116052_bib0100","doi-asserted-by":"crossref","first-page":"8813","DOI":"10.3390\/app13158813","article-title":"Research on improved GRU-based stock price prediction method","volume":"13","author":"Chen","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.asoc.2026.116052_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117986","article-title":"StockNet\u2014GRU based stock index prediction","volume":"207","author":"Gupta","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0110","series-title":"International Conference on the Applications of Evolutionary Computation (Part of EvoStar)","article-title":"Evolving RNNs for stock forecasting: a low parameter efficient alternative to transformers","author":"Lyu","year":"2025"},{"key":"10.1016\/j.asoc.2026.116052_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106943","article-title":"Mean\u2013variance portfolio optimization using machine learning-based stock price prediction","volume":"100","author":"Chen","year":"2021","journal-title":"Appl. Soft Comput."},{"issue":"12","key":"10.1016\/j.asoc.2026.116052_bib0120","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1080\/08839514.2021.1942520","article-title":"Predicting stock price movement using a DBN-RNN","volume":"35","author":"Zhang","year":"2021","journal-title":"Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.116052_bib0125","series-title":"2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC)","first-page":"546","article-title":"A new combined CNN-RNN model for sector stock price analysis","volume":"vol. 2","author":"Zhang","year":"2018"},{"key":"10.1016\/j.asoc.2026.116052_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112116","article-title":"Separating the predictable part of returns with CNN-GRU-attention from inputs to predict stock returns","volume":"165","author":"Yang","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.116052_bib0135","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11968","article-title":"Unlocking the power of LSTM for long term time series forecasting","volume":"vol. 39","author":"Kong","year":"2025"},{"key":"10.1016\/j.asoc.2026.116052_bib0140","author":"Beck"},{"key":"10.1016\/j.asoc.2026.116052_bib0145","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117239","article-title":"Transformer-based attention network for stock movement prediction","volume":"202","author":"Zhang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0155","first-page":"1","article-title":"Stock market index prediction using transformer neural network models and frequency decomposition","author":"Ya\u00f1ez","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0160","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0165","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Crossformer: transformer utilizing cross-dimension dependency for multivariate time series forecasting","author":"Zhang","year":"2022"},{"key":"10.1016\/j.asoc.2026.116052_bib0170","author":"Shu"},{"key":"10.1016\/j.asoc.2026.116052_bib0175","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"vol. 37","author":"Zeng","year":"2023"},{"key":"10.1016\/j.asoc.2026.116052_bib0180","author":"Wu"},{"key":"10.1016\/j.asoc.2026.116052_bib0185","series-title":"2022 International Conference on High Performance Big Data and Intelligent Systems (HDIS)","first-page":"21","article-title":"An attention-based long short-term memory framework for detection of Bitcoin scams","author":"Zhao","year":"2022"},{"key":"10.1016\/j.asoc.2026.116052_bib0190","series-title":"2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)","first-page":"558","article-title":"StockNet: automatic stock prediction using LSTM and transformer structures","author":"Guo","year":"2024"},{"key":"10.1016\/j.asoc.2026.116052_bib0195","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1109\/TCSS.2025.3623272","article-title":"Exposing disguises and tracing illicit flows: dual-view graph representation learning for money laundering detection","volume":"13","author":"Li","year":"2026","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0200","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1658","article-title":"Melding the data-decisions pipeline: decision-focused learning for combinatorial optimization","volume":"vol. 33","author":"Wilder","year":"2019"},{"key":"10.1016\/j.asoc.2026.116052_bib0205","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.52202\/068431-0097","article-title":"Decision-focused learning without decision-making: learning locally optimized decision losses","volume":"35","author":"Shah","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0210","series-title":"Proceedings of the 6th ACM International Conference on AI in Finance","first-page":"114","article-title":"Return prediction for mean-variance portfolio selection: how decision-focused learning shapes forecasting models","author":"Lee","year":"2025"},{"key":"10.1016\/j.asoc.2026.116052_bib0215","author":"Jeon"},{"issue":"4","key":"10.1016\/j.asoc.2026.116052_bib0220","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1142\/S0129065797000422","article-title":"Using a financial training criterion rather than a prediction criterion","volume":"8","author":"Bengio","year":"1997","journal-title":"Int. J. Neural Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0225","doi-asserted-by":"crossref","first-page":"137010","DOI":"10.52202\/079017-4354","article-title":"Fincon: a synthesized LLM multi-agent system with conceptual verbal reinforcement for enhanced financial decision making","volume":"37","author":"Yu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0230","author":"Mohammadshafie"},{"key":"10.1016\/j.asoc.2026.116052_bib0235","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"10.1016\/j.asoc.2026.116052_bib0240","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0245","series-title":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","first-page":"1924","article-title":"Enabling an informed contextual multi-armed bandit framework for stock trading with neuroevolution","author":"Kar","year":"2024"},{"key":"10.1016\/j.asoc.2026.116052_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108490","article-title":"TradeBot: bandit learning for hyper-parameters optimization of high frequency trading strategy","volume":"124","author":"Zhang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.116052_bib0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119677","article-title":"Contextual combinatorial bandit on portfolio management","volume":"221","author":"Ni","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0260","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.ins.2020.05.066","article-title":"Adaptive stock trading strategies with deep reinforcement learning methods","volume":"538","author":"Wu","year":"2020","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2026.116052_bib0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116523","article-title":"Learning financial asset-specific trading rules via deep reinforcement learning","volume":"195","author":"Taghian","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0270","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110211","article-title":"Deep reinforcement learning based on transformer and U-Net framework for stock trading","volume":"262","author":"Yang","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.asoc.2026.116052_bib0275","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122581","article-title":"A novel deep reinforcement learning framework with BiLSTM-Attention networks for algorithmic trading","volume":"240","author":"Huang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0280","series-title":"2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA)","first-page":"82","article-title":"Reinforcement learning with deep deterministic policy gradient","author":"Tan","year":"2021"},{"key":"10.1016\/j.asoc.2026.116052_bib0285","series-title":"Proceedings of the 2022 8th International Conference on Computer Technology Applications","first-page":"22","article-title":"DDPG based on multi-scale strokes for financial time series trading strategy","author":"Chen","year":"2022"},{"key":"10.1016\/j.asoc.2026.116052_bib0290","series-title":"Proceedings of the First ACM International Conference on AI in Finance","first-page":"1","article-title":"Deep reinforcement learning for automated stock trading: an ensemble strategy","author":"Yang","year":"2020"},{"key":"10.1016\/j.asoc.2026.116052_bib0295","author":"Mnih"},{"key":"10.1016\/j.asoc.2026.116052_bib0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124350","article-title":"Improving algorithmic trading consistency via human alignment and imitation learning","author":"Huang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0305","author":"Liu"},{"key":"10.1016\/j.asoc.2026.116052_bib0310","series-title":"Proceedings of the Second ACM International Conference on AI in Finance","first-page":"1","article-title":"FinRL: deep reinforcement learning framework to automate trading in quantitative finance","author":"Liu","year":"2021"},{"key":"10.1016\/j.asoc.2026.116052_bib0315","doi-asserted-by":"crossref","first-page":"1835","DOI":"10.52202\/068431-0134","article-title":"FinRL-Meta: market environments and benchmarks for data-driven financial reinforcement learning","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.asoc.2026.116052_bib0320","doi-asserted-by":"crossref","first-page":"2795","DOI":"10.1007\/s10994-023-06511-w","article-title":"Dynamic datasets and market environments for financial reinforcement learning","volume":"113","author":"Liu","year":"2024","journal-title":"Mach. Learn."},{"key":"10.1016\/j.asoc.2026.116052_bib0325","author":"Xiong"},{"key":"10.1016\/j.asoc.2026.116052_bib0330","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.asoc.2026.116052_bib0335","series-title":"International Conference on Machine Learning","first-page":"1861","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.asoc.2026.116052_bib0340","author":"Schulman"},{"key":"10.1016\/j.asoc.2026.116052_bib0345","author":"Pricope"},{"key":"10.1016\/j.asoc.2026.116052_bib0350","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122801","article-title":"A novel deep reinforcement learning based automated stock trading system using cascaded LSTM networks","volume":"242","author":"Zou","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.116052_bib0355","series-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence","first-page":"4548","article-title":"An end-to-end optimal trade execution framework based on proximal policy optimization","author":"Lin","year":"2021"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626015000?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626015000?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T07:48:38Z","timestamp":1789199318000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626015000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":71,"alternative-id":["S1568494626015000"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116052","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Directly learning stock trading strategies through profit guided loss functions","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116052","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116052"}}