{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T03:32:50Z","timestamp":1780803170886,"version":"3.54.1"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.patrec.2026.03.007","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:21:28Z","timestamp":1773361288000},"page":"170-176","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Alternative loss function in evaluation of algorithmic investing strategies based on transformer models"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0567-6240","authenticated-orcid":false,"given":"Jakub","family":"Micha\u0144k\u00f3w","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3384-3795","authenticated-orcid":false,"given":"Pawe\u0142","family":"Sakowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5227-2014","authenticated-orcid":false,"given":"Robert","family":"\u015alepaczuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.03.007_bib0001","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin, Attention is all you need, 2023. arXiv: 1706.03762."},{"key":"10.1016\/j.patrec.2026.03.007_bib0002","unstructured":"A. Zeng, M. Chen, L. Zhang, Q. Xu, Are transformers effective for time series forecasting?, 2022. arXiv: 2205.13504."},{"key":"10.1016\/j.patrec.2026.03.007_bib0003","doi-asserted-by":"crossref","unstructured":"Q. Wen, T. Zhou, C. Zhang, W. Chen, Z. Ma, J. Yan, L. Sun, Transformers in time series: a survey, 2023. arXiv: 2202.07125.","DOI":"10.24963\/ijcai.2023\/759"},{"issue":"1","key":"10.1016\/j.patrec.2026.03.007_bib0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0227222","article-title":"Forecasting stock prices with long-short term memory neural network based on attention mechanism","volume":"15","author":"Qiu","year":"2020","journal-title":"PLoS ONE"},{"issue":"1","key":"10.1016\/j.patrec.2026.03.007_bib0005","doi-asserted-by":"crossref","DOI":"10.1088\/1742-6596\/1631\/1\/012141","article-title":"Comparison of time series forecasting based on statistical ARIMA model and LSTM with attention mechanism","volume":"1631","author":"Zhou","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"10.1016\/j.patrec.2026.03.007_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118128","article-title":"Stock market index prediction using deep transformer model","volume":"208","author":"Wang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.03.007_bib0007","unstructured":"Z. Zeng, R. Kaur, S. Siddagangappa, S. Rahimi, T. Balch, M. Veloso, Financial time series forecasting using CNN and transformer, 2023. arXiv: 2304.04912."},{"issue":"C","key":"10.1016\/j.patrec.2026.03.007_bib0008","article-title":"Attention is all you need: an interpretable transformer-based asset allocation approach","volume":"90","author":"Ma","year":"2023","journal-title":"Int. Rev. Financ. Anal."},{"key":"10.1016\/j.patrec.2026.03.007_bib0009","unstructured":"M. Lopez de Prado, What to look for in a backtest, SSRN Working Paper, Available at SSRN: https:\/\/ssrn.com\/abstract=2308682, 2013."},{"issue":"4","key":"10.1016\/j.patrec.2026.03.007_bib0010","first-page":"39","article-title":"The probability of backtest overfitting","volume":"20","author":"Bailey","year":"2016","journal-title":"J. Comput. Finance"},{"key":"10.1016\/j.patrec.2026.03.007_bib0011","first-page":"403","article-title":"Artificial neural networks architectures for stock price prediction: comparisons and applications","volume":"10","author":"Di Persio","year":"2016","journal-title":"Int. J. Circuits Syst. Signal Process."},{"key":"10.1016\/j.patrec.2026.03.007_bib0012","unstructured":"J. Yang, Y. Li, X. Chen, J. Cao, K. Jiang, Deep learning for stock selection based on high frequency price-volume data, (2019). arXiv: 1911.02502 [cs, q-fin]."},{"issue":"3","key":"10.1016\/j.patrec.2026.03.007_bib0013","doi-asserted-by":"crossref","first-page":"69","DOI":"10.3905\/joi.2016.25.3.069","article-title":"All that glitters is not gold: comparing backtest and out-of-sample performance on a large cohort of trading algorithms","volume":"25","author":"Wiecki","year":"2016","journal-title":"J. Investing"},{"key":"10.1016\/j.patrec.2026.03.007_bib0014","series-title":"International Conference on Business Information Systems","first-page":"424","article-title":"Portfolio of global futures algorithmic trading strategies for best out-of-sample performance","author":"Raudys","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.007_bib0015","series-title":"Algorithmic Trading: Winning Strategies and Their Rationale","volume":"625","author":"Chan","year":"2013"},{"key":"10.1016\/j.patrec.2026.03.007_bib0016","series-title":"Quantitative Trading: How to Build Your Own Algorithmic Trading Business","author":"Chan","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.007_bib0017","series-title":"Machine Learning for Algorithmic Trading","author":"Jansen","year":"2020"},{"issue":"8","key":"10.1016\/j.patrec.2026.03.007_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5539\/ijef.v10n8p36","article-title":"Multi factor stock selection model based on LSTM","volume":"10","author":"Zhang","year":"2018","journal-title":"Int. J. Econ. Finance"},{"issue":"2","key":"10.1016\/j.patrec.2026.03.007_bib0019","first-page":"52","article-title":"Backtest overfitting in financial markets","volume":"39","author":"Bailey","year":"2016","journal-title":"Automated Trader"},{"key":"10.1016\/j.patrec.2026.03.007_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113761","article-title":"A Q-learning agent for automated trading in equity stock markets","volume":"163","author":"Chakole","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.03.007_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.frl.2019.101396","article-title":"Technical trading rules in the cryptocurrency market","volume":"32","author":"Grobys","year":"2020","journal-title":"Finance Res. Lett."},{"issue":"8","key":"10.1016\/j.patrec.2026.03.007_bib0022","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.patrec.2026.03.007_bib0023","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1724","article-title":"Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","author":"Cho","year":"2014"},{"issue":"3","key":"10.1016\/j.patrec.2026.03.007_bib0024","doi-asserted-by":"crossref","DOI":"10.3390\/s22030917","article-title":"LSTM in algorithmic investment strategies on BTC and S&P500 index","volume":"22","author":"Micha\u0144k\u00f3w","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.patrec.2026.03.007_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocs.2024.102375","article-title":"Mean absolute directional loss as a new loss function for machine learning problems in algorithmic investment strategies","volume":"81","author":"Micha\u0144k\u00f3w","year":"2024","journal-title":"J. Comput. Sci."},{"key":"10.1016\/j.patrec.2026.03.007_bib0026","doi-asserted-by":"crossref","unstructured":"A. Perekhodko, R. \u015alepaczuk, Stochastic volatility modelling with LSTM networks: a hybrid approach for S&P 500 index volatility forecasting, 2025, 10.48550\/arXiv.2512.12250.","DOI":"10.2139\/ssrn.5910742"},{"issue":"4","key":"10.1016\/j.patrec.2026.03.007_bib0027","doi-asserted-by":"crossref","first-page":"36","DOI":"10.2478\/fiqf-2018-0026","article-title":"Investment strategies that beat the market. what can we squeeze from the market?","volume":"14","author":"\u015alepaczuk","year":"2018","journal-title":"Financ. Internet Q."},{"key":"10.1016\/j.patrec.2026.03.007_bib0028","series-title":"Predicting prices of S&P 500 index using classical methods and recurrent neural networks","author":"Kijewski","year":"2024"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526000942?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526000942?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:58:49Z","timestamp":1774976329000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526000942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":28,"alternative-id":["S0167865526000942"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.007","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Alternative loss function in evaluation of algorithmic investing strategies based on transformer models","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.007","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}