{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:29:30Z","timestamp":1777696170422,"version":"3.51.4"},"reference-count":56,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2022,4,18]]},"abstract":"<jats:p>In this study, we propose a deep learning related framework to analyze S&amp;P500 stocks using bi-dimensional histogram and autoencoder. The bi-dimensional histogram consisting of daily returns of stock price and stock trading volume is plotted for each stock. Autoencoder is applied to the bi-dimensional histogram to reduce data dimension and extract meaningful features of a stock. The histogram distance matrix for stocks are made of the extracted features of stocks, and stock market network is built by applying Planar Maximally Filtered Graph(PMFG) algorithm to the histogram distance matrix. The constructed stock market network represents the latent space of bi-dimensional histogram, and network analysis is performed to investigate the structural properties of the stock market. we discover that the structural properties of stock market network are related to the dispersion of bi-dimensional histogram. Also, we confirm that the autoencoder is effective in extracting the latent feature of the bi-dimensional histogram. Portfolios using the features of bi-dimensional histogram network are constructed and their investment performance is evaluated in comparison with other benchmark portfolios. We observe that the portfolio consisting of stocks corresponding to the peripheral nodes of bi-dimensional histogram network shows better investment performance than other benchmark stock portfolios.<\/jats:p>","DOI":"10.3233\/ida-215819","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T13:25:55Z","timestamp":1650979555000},"page":"723-750","source":"Crossref","is-referenced-by-count":1,"title":["Stock market network based on bi-dimensional histogram and autoencoder"],"prefix":"10.1177","volume":"26","author":[{"given":"Sungyoon","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Seoul, Korea"}]},{"given":"Dongkyu","family":"Gwak","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Seoul, Korea"}]},{"given":"Jae Wook","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Hanyang University, Seoul, Korea"}]},{"given":"Woojin","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Seoul, Korea"},{"name":"Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea"},{"name":"SNU Institute for Research in Finance and Economics, Seoul National University, Seoul, Korea"}]}],"member":"179","reference":[{"issue":"2","key":"10.3233\/IDA-215819_ref1","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1111\/1468-0300.00091","article-title":"Expected shortfall: A natural coherent alternative to value at risk","volume":"31","author":"Acerbi","year":"2002","journal-title":"Economic Notes"},{"key":"10.3233\/IDA-215819_ref2","unstructured":"S.C. AP, S. Lauly, H. Larochelle, M. Khapra, B. Ravindran, V.C. Raykar and A. Saha, An autoencoder approach to learning bilingual word representations, in: Advances in Neural Information Processing Systems, 2014, pp. 1853\u20131861."},{"issue":"7\u20138","key":"10.3233\/IDA-215819_ref4","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1111\/j.1468-5957.2010.02197.x","article-title":"The information content of abnormal trading volume","volume":"37","author":"Bajo","year":"2010","journal-title":"Journal of Business Finance & Accounting"},{"issue":"7","key":"10.3233\/IDA-215819_ref5","doi-asserted-by":"crossref","first-page":"e0180944","DOI":"10.1371\/journal.pone.0180944","article-title":"A deep learning framework for financial time series using stacked autoencoders and long-short term memory","volume":"12","author":"Bao","year":"2017","journal-title":"PloS One"},{"issue":"4","key":"10.3233\/IDA-215819_ref6","doi-asserted-by":"crossref","first-page":"046130","DOI":"10.1103\/PhysRevE.68.046130","article-title":"Topology of correlation-based minimal spanning trees in real and model markets","volume":"68","author":"Bonanno","year":"2003","journal-title":"Physical Review E"},{"issue":"3","key":"10.3233\/IDA-215819_ref7","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1111\/j.1540-6288.2001.tb00024.x","article-title":"The dynamic relation between stock returns, trading volume, and volatility","volume":"36","author":"Chen","year":"2001","journal-title":"Financial Review"},{"issue":"3","key":"10.3233\/IDA-215819_ref8","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0304-405X(01)00066-6","article-title":"Forecasting crashes: Trading volume, past returns, and conditional skewness in stock prices","volume":"61","author":"Chen","year":"2001","journal-title":"Journal of Financial Economics"},{"key":"10.3233\/IDA-215819_ref9","doi-asserted-by":"crossref","unstructured":"S. Chen and H. He, Stock prediction using convolutional neural network, in: IOP Conference Series: Materials Science and Engineering, IOP Publishing, Vol. 435, 2018, p. 012026.","DOI":"10.1088\/1757-899X\/435\/1\/012026"},{"issue":"4","key":"10.3233\/IDA-215819_ref11","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1016\/j.jempfin.2010.04.008","article-title":"A network perspective of the stock market","volume":"17","author":"Chi","year":"2010","journal-title":"Journal of Empirical Finance"},{"issue":"5","key":"10.3233\/IDA-215819_ref12","doi-asserted-by":"crossref","first-page":"584","DOI":"10.4236\/me.2012.35077","article-title":"Relationship between trading volume and asymmetric volatility in the korean stock market","volume":"3","author":"Choi","year":"2012","journal-title":"Modern Economy"},{"issue":"1","key":"10.3233\/IDA-215819_ref13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1140\/epjb\/e2009-00286-0","article-title":"The use of dynamical networks to detect the hierarchical organization of financial market sectors","volume":"73","author":"Di Matteo","year":"2010","journal-title":"The European Physical Journal B"},{"key":"10.3233\/IDA-215819_ref14","doi-asserted-by":"crossref","unstructured":"T.-A. Dinh and Y.-K. Kwon, An empirical study on importance of modeling parameters and trading volume-based features in daily stock trading using neural networks. in: Informatics, Multidisciplinary Digital Publishing Institute, Vol. 5, 2018, p. 36.","DOI":"10.3390\/informatics5030036"},{"key":"10.3233\/IDA-215819_ref15","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.irfa.2014.09.003","article-title":"How does trading volume affect financial return distributions","volume":"35","author":"Do","year":"2014","journal-title":"International Review of Financial Analysis"},{"issue":"6","key":"10.3233\/IDA-215819_ref16","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1016\/j.physa.2008.12.006","article-title":"Topological properties of stock networks based on minimal spanning tree and random matrix theory in financial time series","volume":"388","author":"Eom","year":"2009","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"17","key":"10.3233\/IDA-215819_ref17","doi-asserted-by":"crossref","first-page":"3551","DOI":"10.1016\/j.physa.2009.04.028","article-title":"Network structure of cross-correlations among the world market indices","volume":"388","author":"Eryi\u011fit","year":"2009","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"7","key":"10.3233\/IDA-215819_ref18","doi-asserted-by":"crossref","first-page":"1714","DOI":"10.1016\/j.jbankfin.2010.11.007","article-title":"Long memory in volatility and trading volume","volume":"35","author":"Fleming","year":"2011","journal-title":"Journal of Banking & Finance"},{"key":"10.3233\/IDA-215819_ref19","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.chaos.2016.11.007","article-title":"Dynamic asset trees in the us stock market: Structure variation and market phenomena","volume":"94","author":"Huang","year":"2017","journal-title":"Chaos, Solitons & Fractals"},{"issue":"14","key":"10.3233\/IDA-215819_ref20","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1016\/j.physa.2009.03.028","article-title":"A network analysis of the chinese stock market","volume":"388","author":"Huang","year":"2009","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref21","doi-asserted-by":"crossref","first-page":"123387","DOI":"10.1016\/j.physa.2019.123387","article-title":"Measuring systematic risk with neural network factor model","volume":"542","author":"Huh","year":"2020","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref22","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/j.sbspro.2015.11.118","article-title":"The effect of return on equity (roe) and return on investment (roi) on trading volume","volume":"211","author":"Ichsani","year":"2015","journal-title":"Procedia-Social and Behavioral Sciences"},{"issue":"21","key":"10.3233\/IDA-215819_ref23","doi-asserted-by":"crossref","first-page":"4929","DOI":"10.1016\/j.physa.2010.07.024","article-title":"Complex stock trading network among investors","volume":"389","author":"Jiang","year":"2010","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"1","key":"10.3233\/IDA-215819_ref24","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.physa.2005.06.081","article-title":"Characteristics of the korean stock market correlations","volume":"361","author":"Jung","year":"2006","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref25","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.physa.2015.02.052","article-title":"Correlation network analysis for multi-dimensional data in stocks market","volume":"429","author":"Kazemilari","year":"2015","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref26","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.physa.2018.10.019","article-title":"Econophysics and sociophysics: Their milestones & challenges","volume":"516","author":"Kutner","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"5","key":"10.3233\/IDA-215819_ref27","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1111\/0022-1082.00280","article-title":"Price momentum and trading volume","volume":"55","author":"Lee","year":"2000","journal-title":"the Journal of Finance"},{"issue":"2","key":"10.3233\/IDA-215819_ref28","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.physa.2006.10.089","article-title":"Extracting hidden fluctuation patterns of hang seng stock index from network topologies","volume":"378","author":"Li","year":"2007","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref29","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1016\/j.physa.2018.10.014","article-title":"Portfolio optimization based on network topology","volume":"515","author":"Li","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"5","key":"10.3233\/IDA-215819_ref30","doi-asserted-by":"crossref","first-page":"991","DOI":"10.3233\/IDA-184240","article-title":"Variational autoencoder-based outlier detection for high-dimensional data","volume":"23","author":"Li","year":"2019","journal-title":"Intelligent Data Analysis"},{"key":"10.3233\/IDA-215819_ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.chaos.2018.10.012","article-title":"A clustering-based portfolio strategy incorporating momentum effect and market trend prediction","volume":"117","author":"Lu","year":"2018","journal-title":"Chaos, Solitons & Fractals"},{"issue":"1","key":"10.3233\/IDA-215819_ref32","doi-asserted-by":"crossref","first-page":"19","DOI":"10.3233\/IDA-184403","article-title":"Dnn models based on dimensionality reduction for stock trading","volume":"24","author":"Lv","year":"2020","journal-title":"Intelligent Data Analysis"},{"key":"10.3233\/IDA-215819_ref33","doi-asserted-by":"crossref","first-page":"101494","DOI":"10.1016\/j.pacfin.2021.101494","article-title":"Stock return predictability: Evidence from moving averages of trading volume","volume":"65","author":"Ma","year":"2021","journal-title":"Pacific-Basin Finance Journal"},{"issue":"1","key":"10.3233\/IDA-215819_ref34","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s100510050929","article-title":"Hierarchical structure in financial markets","volume":"11","author":"Mantegna","year":"1999","journal-title":"The European Physical Journal B-Condensed Matter and Complex Systems"},{"key":"10.3233\/IDA-215819_ref36","doi-asserted-by":"crossref","first-page":"124392","DOI":"10.1016\/j.physa.2020.124392","article-title":"Predictive intraday correlations in stable and volatile market environments: Evidence from deep learning","volume":"547","author":"Moews","year":"2020","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"3","key":"10.3233\/IDA-215819_ref37","doi-asserted-by":"crossref","first-page":"e0116201","DOI":"10.1371\/journal.pone.0116201","article-title":"Relation between financial market structure and the real economy: Comparison between clustering methods","volume":"10","author":"Musmeci","year":"2015","journal-title":"PloS One"},{"issue":"1","key":"10.3233\/IDA-215819_ref38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep36320","article-title":"Interplay between past market correlation structure changes and future volatility outbursts","volume":"6","author":"Musmeci","year":"2016","journal-title":"Scientific Reports"},{"issue":"2011","key":"10.3233\/IDA-215819_ref39","first-page":"1","article-title":"Sparse autoencoder","volume":"72","author":"Ng","year":"2011","journal-title":"CS294A Lecture Notes"},{"key":"10.3233\/IDA-215819_ref40","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.physa.2014.03.083","article-title":"Effects of global financial crisis on network structure in a local stock market","volume":"407","author":"Nobi","year":"2014","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"5","key":"10.3233\/IDA-215819_ref41","doi-asserted-by":"crossref","first-page":"056110","DOI":"10.1103\/PhysRevE.68.056110","article-title":"Dynamics of market correlations: Taxonomy and portfolio analysis","volume":"68","author":"Onnela","year":"2003","journal-title":"Physical Review E"},{"issue":"3","key":"10.3233\/IDA-215819_ref42","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1140\/epjb\/e2002-00380-9","article-title":"Dynamic asset trees and portfolio analysis","volume":"30","author":"Onnela","year":"2002","journal-title":"The European Physical Journal B-Condensed Matter and Complex Systems"},{"key":"10.3233\/IDA-215819_ref43","doi-asserted-by":"crossref","unstructured":"F. Pozzi, T. Aste, G. Rotundo and T. Di Matteo, Dynamical correlations in financial systems, in: Complex Systems II, International Society for Optics and Photonics, Vol. 6802, 2008, p. 68021E.","DOI":"10.1117\/12.758822"},{"key":"10.3233\/IDA-215819_ref44","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1038\/srep01665","article-title":"Spread of risk across financial markets: Better to invest in the peripheries","volume":"3","author":"Pozzi","year":"2013","journal-title":"Scientific Reports"},{"issue":"12","key":"10.3233\/IDA-215819_ref45","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1016\/j.physa.2009.02.038","article-title":"Statistical properties of trading volume of chinese stocks","volume":"388","author":"Qiu","year":"2009","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.3233\/IDA-215819_ref46","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.chaos.2015.12.024","article-title":"Trading volume in financial markets: An introductory review","volume":"88","author":"Queir\u00f3s","year":"2016","journal-title":"Chaos, Solitons & Fractals"},{"issue":"8","key":"10.3233\/IDA-215819_ref47","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1016\/S0378-4266(99)00071-0","article-title":"Trading volume and autocorrelation: Empirical evidence from the stockholm stock exchange","volume":"24","author":"S\u00e4fvenblad","year":"2000","journal-title":"Journal of Banking & Finance"},{"issue":"1","key":"10.3233\/IDA-215819_ref48","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1086\/294846","article-title":"Mutual fund performance","volume":"39","author":"Sharpe","year":"1966","journal-title":"The Journal of Business"},{"issue":"2","key":"10.3233\/IDA-215819_ref49","doi-asserted-by":"crossref","first-page":"026108","DOI":"10.1103\/PhysRevE.84.026108","article-title":"Evolution of worldwide stock markets, correlation structure, and correlation-based graphs","volume":"84","author":"Song","year":"2011","journal-title":"Physical Review E"},{"issue":"3","key":"10.3233\/IDA-215819_ref50","doi-asserted-by":"crossref","first-page":"e31929","DOI":"10.1371\/journal.pone.0031929","article-title":"Hierarchical information clustering by means of topologically embedded graphs","volume":"7","author":"Song","year":"2012","journal-title":"PloS One"},{"issue":"30","key":"10.3233\/IDA-215819_ref51","doi-asserted-by":"crossref","first-page":"10421","DOI":"10.1073\/pnas.0500298102","article-title":"A tool for filtering information in complex systems","volume":"102","author":"Tumminello","year":"2005","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"10.3233\/IDA-215819_ref52","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1140\/epjb\/e2006-00414-4","article-title":"Correlation based networks of equity returns sampled at different time horizons","volume":"55","author":"Tumminello","year":"2007","journal-title":"The European Physical Journal B"},{"issue":"1","key":"10.3233\/IDA-215819_ref53","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.jebo.2010.01.004","article-title":"Correlation, hierarchies, and networks in financial markets","volume":"75","author":"Tumminello","year":"2010","journal-title":"Journal of Economic Behavior & Organization"},{"issue":"1","key":"10.3233\/IDA-215819_ref54","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1111\/j.1354-7798.2006.00312.x","article-title":"Stock price and volume effects associated with compositional changes in european stock indices","volume":"12","author":"Vespro","year":"2006","journal-title":"European Financial Management"},{"key":"10.3233\/IDA-215819_ref55","doi-asserted-by":"crossref","unstructured":"X. Wang, P.K.H. Phua and W. Lin, Stock market prediction using neural networks: Does trading volume help in short-term prediction? in: Proceedings of the International Joint Conference on Neural Networks, 2003, IEEE, Vol. 4, 2003, pp.\u00a02438\u20132442.","DOI":"10.1109\/IJCNN.2003.1223946"},{"key":"10.3233\/IDA-215819_ref56","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","article-title":"Auto-encoder based dimensionality reduction","volume":"184","author":"Wang","year":"2016","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-215819_ref57","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1016\/j.physa.2018.09.140","article-title":"The stability of chinese stock network and its mechanism","volume":"515","author":"Zhang","year":"2019","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"2","key":"10.3233\/IDA-215819_ref58","doi-asserted-by":"crossref","first-page":"023402","DOI":"10.1088\/1742-5468\/aa9db0","article-title":"The q-dependent detrended cross-correlation analysis of stock market","volume":"2018","author":"Zhao","year":"2018","journal-title":"Journal of Statistical Mechanics: Theory and Experiment"},{"key":"10.3233\/IDA-215819_ref59","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.physa.2018.05.039","article-title":"Stock market as temporal network","volume":"506","author":"Zhao","year":"2018","journal-title":"Physica A: Statistical Mechanics and its Applications"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-215819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:19:27Z","timestamp":1777454367000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-215819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,18]]},"references-count":56,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/ida-215819","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,18]]}}}