{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:59:23Z","timestamp":1791482363358,"version":"4.3.4"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"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>\n                    How can we identify stable patterns to accurately predict stock price movements amidst severe market noise? Predicting stock price movements is a crucial problem in financial data mining, and has attracted significant attention from researchers and financial institutions. Although there have been several works on learning patterns from quantitative data to predict stock prices, they encounter critical challenges from data uncertainty and model limitations. Data uncertainty arises in financial data because asset prices are determined by the market. Different participants hold distinct valuations for the same asset, which causes prices to fluctuate. This inherent randomness makes it difficult to identify consistent patterns in the data. Additionally, because of this inherent randomness, existing stock movement prediction models that repeatedly stack more recurrent layers end up propagating the randomness forward. It thus becomes more difficult to capture the complex patterns of stock prices. In this work, we propose\n                    <jats:sc>Craft<\/jats:sc>\n                    (\n                    <jats:sc>Centroid-based Randomness Smoothing Approach for Stock Forecasting with Transformer Architecture<\/jats:sc>\n                    ), an accurate stock movement prediction model designed to extract clear patterns in stock data and perform refined forecasting through a Transformer-based architecture. By applying an effective randomness smoothing process, Craft uncovers meaningful and consistent patterns that facilitate accurate predictions. We evaluate Craft on fourteen test settings spanning six real-world datasets and three market regimes. Craft achieves the highest prediction accuracy in twelve of these settings and ranks the second in the other two.\n                    <jats:sc>Craft<\/jats:sc>\n                    also improves the annualized Sharpe ratio by up to 1.0 while reducing the relative maximum drawdown by up to 7.0% points over the best competitor.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0345252","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:46:18Z","timestamp":1791481578000},"page":"e0345252","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accurate stock movement prediction via centroid-based randomness smoothing"],"prefix":"10.1371","volume":"21","author":[{"given":"Yejun","family":"Soun","sequence":"first","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2401-1002","authenticated-orcid":true,"given":"Hosung","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-6950","authenticated-orcid":true,"given":"U","family":"Kang","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"issue":"1","key":"pone.0345252.ref001","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/0304-405X(93)90023-5","article-title":"Common risk factors in the returns on stocks and bonds","volume":"33","author":"EF Fama","year":"1993","journal-title":"J Finan Econo"},{"key":"pone.0345252.ref002","first-page":"100060","article-title":"Feature selection and deep neural networks for stock price direction forecasting using technical analysis indicators","volume":"5","author":"Y Peng","year":"2021","journal-title":"Machine Learn Appl"},{"key":"pone.0345252.ref003","doi-asserted-by":"crossref","unstructured":"Vargas MR, dos Anjos CEM, Bichara GLG, Evsukoff AG. Deep leaming for stock market prediction using technical indicators and financial news articles. In: 2018 International Joint Conference on Neural Networks (IJCNN), 2018. 1\u20138. https:\/\/doi.org\/10.1109\/ijcnn.2018.8489208","DOI":"10.1109\/IJCNN.2018.8489208"},{"key":"pone.0345252.ref004","doi-asserted-by":"crossref","unstructured":"Deng S, Mitsubuchi T, Shioda K, Shimada T, Sakurai A. Combining technical analysis with sentiment analysis for stock price prediction. In: 2011 IEEE Ninth international conference on dependable, autonomic and secure computing. 2011. 800\u20137. https:\/\/doi.org\/10.1109\/dasc.2011.138","DOI":"10.1109\/DASC.2011.138"},{"key":"pone.0345252.ref005","doi-asserted-by":"crossref","unstructured":"Khairi TWA, Zaki RM, Mahmood WA. Stock price prediction using technical, fundamental and news based approach. In: 2019 2nd Scientific Conference of Computer Sciences (SCCS), 2019. 177\u201381. https:\/\/doi.org\/10.1109\/sccs.2019.8852599","DOI":"10.1109\/SCCS.2019.8852599"},{"key":"pone.0345252.ref006","doi-asserted-by":"crossref","unstructured":"Beyaz E, Tekiner F, Zeng X, Keane J. Comparing technical and fundamental indicators in stock price forecasting. In: 2018 IEEE 20th International conference on high performance computing and communications; IEEE 16th International conference on smart city; IEEE 4th International conference on data science and systems (HPCC\/SmartCity\/DSS), 2018. 1607\u201313. https:\/\/doi.org\/10.1109\/hpcc\/smartcity\/dss.2018.00262","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00262"},{"key":"pone.0345252.ref007","doi-asserted-by":"crossref","unstructured":"Turan AC, Kokach V, Koca\u00e7\u0131nar B, \u015eengel \u00d6, Akbulut FP. Hybrid deep learning framework for stock price prediction incorporating technical and macroeconomic indicators. In: 2024 9th International Conference on Computer Science and Engineering (UBMK), 2024. 1189\u201394. https:\/\/doi.org\/10.1109\/ubmk63289.2024.10773522","DOI":"10.1109\/UBMK63289.2024.10773522"},{"key":"pone.0345252.ref008","doi-asserted-by":"crossref","unstructured":"Cao Z, Xu J, Dong C, Yu P, Bai T. MATCC: a novel approach for robust stock price prediction incorporating market trends and cross-time correlations. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024. 187\u201396. https:\/\/doi.org\/10.1145\/3627673.3679715","DOI":"10.1145\/3627673.3679715"},{"issue":"1","key":"pone.0345252.ref009","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1609\/aaai.v38i1.27767","article-title":"MASTER: market-guided stock transformer for stock price forecasting","volume":"38","author":"T Li","year":"2024","journal-title":"AAAI"},{"key":"pone.0345252.ref010","doi-asserted-by":"crossref","unstructured":"Lin H, Zhou D, Liu W, Bian J. Learning multiple stock trading patterns with temporal routing adaptor and optimal transport. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021. 1017\u201326. https:\/\/doi.org\/10.1145\/3447548.3467358","DOI":"10.1145\/3447548.3467358"},{"key":"pone.0345252.ref011","doi-asserted-by":"crossref","unstructured":"Yoo J, Soun Y, Park Y, Kang U. Accurate multivariate stock movement prediction via data-axis transformer with multi-level contexts. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 2021. 2037\u201345. https:\/\/doi.org\/10.1145\/3447548.3467297","DOI":"10.1145\/3447548.3467297"},{"key":"pone.0345252.ref012","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0925-2312(01)00702-0","article-title":"Time series forecasting using a hybrid ARIMA and neural network model","volume":"50","author":"GP Zhang","year":"2003","journal-title":"Neurocomp"},{"key":"pone.0345252.ref013","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.procs.2015.04.167","article-title":"Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition","volume":"48","author":"I Khandelwal","year":"2015","journal-title":"Procedia Comp Sci"},{"key":"pone.0345252.ref014","volume-title":"Time series analysis: Forecasting and control","author":"GEP Box","year":"2015"},{"issue":"2","key":"pone.0345252.ref015","first-page":"543","article-title":"Factor-related and specific returns of common stocks: serial correlation and market inefficiency","volume":"37","author":"B Rosenberg","year":"1982","journal-title":"J Finance"},{"issue":"2","key":"pone.0345252.ref016","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.jfineco.2015.12.002","article-title":"Momentum crashes","volume":"122","author":"K Daniel","year":"2016","journal-title":"J Finan Econ"},{"key":"pone.0345252.ref017","doi-asserted-by":"crossref","unstructured":"Zhou T, Niu P, Wang X, Sun L, Jin R. One fits all: power general time series analysis by pretrained LM. In: Advances in neural information processing systems 36. 2023. 43322\u201355. https:\/\/doi.org\/10.52202\/075280-1877","DOI":"10.52202\/075280-1877"},{"key":"pone.0345252.ref018","unstructured":"Jin M, Wang S, Ma L, Chu Z, Zhang JY, Shi X. Time-llm: Time series forecasting by reprogramming large language models. 2023."},{"key":"pone.0345252.ref019","unstructured":"Xu W, Liu W, Wang L, Xia Y, Bian J, Yin J. Hist: A graph-based framework for stock trend forecasting via mining concept-oriented shared information. 2021."},{"key":"pone.0345252.ref020","doi-asserted-by":"crossref","unstructured":"Alaygut T, Sefer E. Hypergraph neural networks to predict stock movements by exploring higher-order relationships. In: Proceedings of the 6th ACM International Conference on AI in Finance, 2025. 700\u20138. https:\/\/doi.org\/10.1145\/3768292.3770389","DOI":"10.1145\/3768292.3770389"},{"key":"pone.0345252.ref021","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.eswa.2017.04.030","article-title":"Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies","volume":"83","author":"E Chong","year":"2017","journal-title":"Expert Systems with Applications"},{"key":"pone.0345252.ref022","doi-asserted-by":"crossref","unstructured":"Selvin S, Vinayakumar R, Gopalakrishnan EA, Menon VK, Soman KP. Stock price prediction using LSTM, RNN and CNN-sliding window model. In: 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017. 1643\u20137. https:\/\/doi.org\/10.1109\/icacci.2017.8126078","DOI":"10.1109\/ICACCI.2017.8126078"},{"key":"pone.0345252.ref023","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention Is All You Need. arXiv preprint. 2017. doi: 10.48550\/arXiv.1706.03762"},{"key":"pone.0345252.ref024","doi-asserted-by":"crossref","first-page":"77132","DOI":"10.1109\/ACCESS.2023.3298445","article-title":"Transformer-gated recurrent unit method for predicting stock price based on news sentiments and technical indicators","volume":"11","author":"AT Haryono","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0345252.ref025","doi-asserted-by":"crossref","first-page":"100177","DOI":"10.1016\/j.jfds.2026.100177","article-title":"Pairs trading with time-series deep learning models","volume":"11","author":"S Yilmaz","year":"2025","journal-title":"J Finance and Data Sci"},{"issue":"20","key":"pone.0345252.ref026","doi-asserted-by":"crossref","first-page":"21528","DOI":"10.1609\/aaai.v39i20.35455","article-title":"Revisiting attention for multivariate time series forecasting","volume":"39","author":"H Wu","year":"2025","journal-title":"AAAI"},{"key":"pone.0345252.ref027","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI Technical Report. 2019."},{"key":"pone.0345252.ref028","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"T Brown","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0345252.ref029","unstructured":"van den Oord A, Vinyals O, Kavukcuoglu K. Neural discrete representation learning. Adv Neural Inform Process Systems (NeurIPS). 2017."},{"issue":"4","key":"pone.0345252.ref030","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/BF02289263","article-title":"Who belongs in the family?","volume":"18","author":"RL Thorndike","year":"1953","journal-title":"Psychometrika"},{"key":"pone.0345252.ref031","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"PJ Rousseeuw","year":"1987","journal-title":"J Comp Appl Math"},{"issue":"1","key":"pone.0345252.ref032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1497577.1497578","article-title":"Clustering high-dimensional data: A survey on subspace clustering, pattern-based clustering, and correlation clustering","volume":"3","author":"HP Kriegel","year":"2009","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"1","key":"pone.0345252.ref033","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/3606274.3606278","article-title":"Stop using the elbow criterion for k-means and how to choose the number of clusters instead","volume":"25","author":"E Schubert","year":"2023","journal-title":"SIGKDD Explor Newsl"},{"key":"pone.0345252.ref034","doi-asserted-by":"crossref","unstructured":"Nelson DMQ, Pereira ACM, de Oliveira RA. Stock market\u2019s price movement prediction with LSTM neural networks. In: 2017 International Joint Conference on Neural Networks (IJCNN), 2017. 1419\u201326. https:\/\/doi.org\/10.1109\/ijcnn.2017.7966019","DOI":"10.1109\/IJCNN.2017.7966019"},{"key":"pone.0345252.ref035","doi-asserted-by":"crossref","unstructured":"Qin Y, Song D, Chen H, Cheng W, Jiang G, Cottrell G. A dual-stage attention-based recurrent neural network for time series prediction. 2017. doi: 10.48550\/arXiv.1704.02971","DOI":"10.24963\/ijcai.2017\/366"},{"key":"pone.0345252.ref036","unstructured":"Nie Y, Nguyen NH, Sinthong P, Kalagnanam J. A time series is worth 64 words: Long-term forecasting with transformers. 2022. doi: 10.48550\/arXiv.2211.14730"},{"issue":"12","key":"pone.0345252.ref037","doi-asserted-by":"crossref","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"H Zhou","year":"2021","journal-title":"AAAI"},{"key":"pone.0345252.ref038","unstructured":"Wu H, Xu J, Wang J, Long M. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In: Advances in neural information processing systems. 2021."},{"key":"pone.0345252.ref039","unstructured":"Zhou T, Ma Z, Wen Q, Wang X, Sun L, Jin R. FEDformer: frequency enhanced decomposed transformer for long-term series forecasting. In: Proceedings of the 39th International Conference on Machine Learning, 2022."},{"issue":"5","key":"pone.0345252.ref040","doi-asserted-by":"crossref","first-page":"1731","DOI":"10.1111\/j.1540-6261.1992.tb04681.x","article-title":"Simple Technical Trading Rules and the Stochastic Properties of Stock Returns","volume":"47","author":"W Brock","year":"1992","journal-title":"The Journal of Finance"},{"key":"pone.0345252.ref041","doi-asserted-by":"crossref","unstructured":"Ariyo AA, Adewumi AO, Ayo CK. Stock price prediction using the ARIMA model. In: 2014 UKSim-AMSS 16th International conference on computer modelling and simulation. 2014. 106\u201312. https:\/\/doi.org\/10.1109\/uksim.2014.67","DOI":"10.1109\/UKSim.2014.67"},{"issue":"7","key":"pone.0345252.ref042","article-title":"A deep learning framework for financial time series using stacked autoencoders and long-short term memory","volume":"12","author":"W Bao","year":"2017","journal-title":"PLoS One"},{"issue":"3","key":"pone.0345252.ref043","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1093\/biomet\/81.3.425","article-title":"Ideal spatial adaptation by wavelet shrinkage","volume":"81","author":"DL Donoho","year":"1994","journal-title":"Biometrika"},{"key":"pone.0345252.ref044","volume-title":"Forecasting, structural time series models and the kalman filter","author":"AC Harvey","year":"1989"},{"issue":"1","key":"pone.0345252.ref045","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1257\/089533003321164958","article-title":"The efficient market hypothesis and its critics","volume":"17","author":"BG Malkiel","year":"2003","journal-title":"J Economic Persp"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:46:28Z","timestamp":1791481588000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345252"}},"subtitle":[],"editor":[{"given":"Mohammad Enamul","family":"Hoque","sequence":"first","affiliation":[{"name":"BRAC University","place":["BANGLADESH"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":45,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0345252","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]}}}