A dynamic predictor selection algorithm for predicting stock market movement
Although training a deep network with financial time series is not hard, the important issue is, how much the prediction for the truly new data can be trusted with a trained network. In this study, we propose a dynamic predictor selection algorithm (DPSA) that dynamically evaluates and selects the p...
Uložené v:
| Vydané v: | Expert systems with applications Ročník 186; s. 115836 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
New York
Elsevier Ltd
30.12.2021
Elsevier BV |
| Predmet: | |
| ISSN: | 0957-4174, 1873-6793 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Although training a deep network with financial time series is not hard, the important issue is, how much the prediction for the truly new data can be trusted with a trained network. In this study, we propose a dynamic predictor selection algorithm (DPSA) that dynamically evaluates and selects the prediction model (predictor) for stock daily movement trend prediction. We first build an initial set of potential candidate predictors based on the convolutional long short-term memory networks (ConvLSTMs) by using different values of parameters. To evaluate the candidate predictors, we propose a kernel time-weighted fuzzy c-means clustering algorithm (KTFCM), which improves the kernel FCM algorithm (KFCM), to organize the historical samples according to their relevance to the target sample, which makes the historical samples that are closely related to the target sample have more influence on the predictors. Then, we use the well-organized historical samples to evaluate the candidate predictors. The predictor that yields the best accuracy is selected to predict the target sample. The proposed DPSA algorithm takes less than one minute in total for training the networks, evaluating and selecting the predictors, and performing prediction, which greatly shortens the time of the deep learning prediction. We perform the comparative experiments for the proposed DPSA algorithm and seven popular methods. These experiments test a large real-life financial time series data of various stock markets. The experiment results show that DPSA achieves the best accuracy and the highest return compared to the seven other popular methods.
•A dynamic predictor selection model for financial prediction is proposed.•The model organizes the historical samples according to their relevance.•A clustering algorithm is proposed to improve prediction performance.•The model needs a few iterations to differentiate each of the predictor.•The training time of this model is greatly shorter than in deep learning methods. |
|---|---|
| AbstractList | Although training a deep network with financial time series is not hard, the important issue is, how much the prediction for the truly new data can be trusted with a trained network. In this study, we propose a dynamic predictor selection algorithm (DPSA) that dynamically evaluates and selects the prediction model (predictor) for stock daily movement trend prediction. We first build an initial set of potential candidate predictors based on the convolutional long short-term memory networks (ConvLSTMs) by using different values of parameters. To evaluate the candidate predictors, we propose a kernel time-weighted fuzzy c-means clustering algorithm (KTFCM), which improves the kernel FCM algorithm (KFCM), to organize the historical samples according to their relevance to the target sample, which makes the historical samples that are closely related to the target sample have more influence on the predictors. Then, we use the well-organized historical samples to evaluate the candidate predictors. The predictor that yields the best accuracy is selected to predict the target sample. The proposed DPSA algorithm takes less than one minute in total for training the networks, evaluating and selecting the predictors, and performing prediction, which greatly shortens the time of the deep learning prediction. We perform the comparative experiments for the proposed DPSA algorithm and seven popular methods. These experiments test a large real-life financial time series data of various stock markets. The experiment results show that DPSA achieves the best accuracy and the highest return compared to the seven other popular methods.
•A dynamic predictor selection model for financial prediction is proposed.•The model organizes the historical samples according to their relevance.•A clustering algorithm is proposed to improve prediction performance.•The model needs a few iterations to differentiate each of the predictor.•The training time of this model is greatly shorter than in deep learning methods. Although training a deep network with financial time series is not hard, the important issue is, how much the prediction for the truly new data can be trusted with a trained network. In this study, we propose a dynamic predictor selection algorithm (DPSA) that dynamically evaluates and selects the prediction model (predictor) for stock daily movement trend prediction. We first build an initial set of potential candidate predictors based on the convolutional long short-term memory networks (ConvLSTMs) by using different values of parameters. To evaluate the candidate predictors, we propose a kernel time-weighted fuzzy c-means clustering algorithm (KTFCM), which improves the kernel FCM algorithm (KFCM), to organize the historical samples according to their relevance to the target sample, which makes the historical samples that are closely related to the target sample have more influence on the predictors. Then, we use the well-organized historical samples to evaluate the candidate predictors. The predictor that yields the best accuracy is selected to predict the target sample. The proposed DPSA algorithm takes less than one minute in total for training the networks, evaluating and selecting the predictors, and performing prediction, which greatly shortens the time of the deep learning prediction. We perform the comparative experiments for the proposed DPSA algorithm and seven popular methods. These experiments test a large real-life financial time series data of various stock markets. The experiment results show that DPSA achieves the best accuracy and the highest return compared to the seven other popular methods. |
| ArticleNumber | 115836 |
| Author | Wang, Haodong Wu, Fang-Xiang Dong, Shuting Luo, Hongze Wang, Jianxin |
| Author_xml | – sequence: 1 givenname: Shuting surname: Dong fullname: Dong, Shuting email: dst21@mails.tsinghua.edu.cn organization: School of Computer Science and Engineering, Central South University, Changsha 410083, China – sequence: 2 givenname: Jianxin orcidid: 0000-0003-1516-0480 surname: Wang fullname: Wang, Jianxin email: jxwang@mail.csu.edu.cn organization: School of Computer Science and Engineering, Central South University, Changsha 410083, China – sequence: 3 givenname: Hongze surname: Luo fullname: Luo, Hongze email: 174611102@csu.edu.cn organization: School of Computer Science and Engineering, Central South University, Changsha 410083, China – sequence: 4 givenname: Haodong surname: Wang fullname: Wang, Haodong email: hwang@eecs.csuohio.edu organization: Department of Electrical Engineering and Computer Science, Cleveland State University, Cleveland, OH 44115, USA – sequence: 5 givenname: Fang-Xiang orcidid: 0000-0002-4593-9332 surname: Wu fullname: Wu, Fang-Xiang email: faw341@mail.usask.ca organization: Division of Biomedical Engineering and Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SKS7N5A9, Canada |
| BookMark | eNp9kD1rwzAQhkVJoUnaP9DJ0NmuPmzLgi4h9AsCXbILRT6ncmIrlZSU_PvKOFOHTAfHPXf3PjM06W0PCD0SnBFMyuc2A_-rMoopyQgpKlbeoCmpOEtLLtgETbEoeJoTnt-hmfctxoRjzKdotUjqc686o5ODg9roYF3iYQ86GNsnar-1zoTvLmli_zJh-m3ig9W7pFNuByHp7Ak66MM9um3U3sPDpc7R-u11vfxIV1_vn8vFKtWMViEVOcMKU15yxhRnQDc5UEUYUbrOG91sSlHhXDSCN3kpAAooBeYbAkTxQgs2R0_j2oOzP0fwQbb26Pp4UdJCiJifxdVzRMcp7az3Dhp5cCY-fJYEy0GabOUgTQ7S5CgtQtU_SJugBhXBKbO_jr6MKMTkJwNOem2g11GZizZlbc01_A9Ixooj |
| CitedBy_id | crossref_primary_10_1016_j_ins_2022_02_015 crossref_primary_10_1007_s44443_025_00045_y crossref_primary_10_3390_systems13030162 crossref_primary_10_3390_ijfs13010028 crossref_primary_10_1016_j_eswa_2022_118312 crossref_primary_10_1016_j_asoc_2024_111550 |
| Cites_doi | 10.1109/IJCNN.2017.7966019 10.1109/TII.2018.2811377 10.1109/TNNLS.2016.2522401 10.1016/j.eswa.2017.10.055 10.1016/S0957-4174(02)00034-9 10.1016/j.cie.2012.10.009 10.1109/72.655043 10.1016/j.engappai.2015.01.006 10.1016/j.eswa.2017.02.044 10.1109/ICOMET.2018.8346382 10.1109/TEVC.2008.928176 10.1109/BigData.2017.8258518 10.1016/j.knosys.2014.07.004 10.1016/j.physa.2017.07.017 10.1007/s00500-018-3335-2 10.1145/2939672.2939785 10.1016/j.cor.2004.03.016 10.18653/v1/P18-1183 10.1109/ICIS.2016.7550882 10.1016/j.eswa.2012.01.039 10.1109/TIP.2012.2219547 10.1109/IICSPI.2018.8690416 10.1016/j.asoc.2019.105652 10.1016/j.eswa.2011.02.068 10.1007/978-3-319-13560-1_60 10.1016/j.najef.2018.06.013 10.1371/journal.pone.0180944 10.1016/j.eswa.2016.08.066 10.1016/j.eswa.2019.03.029 10.1016/j.eswa.2019.01.083 10.1016/j.asoc.2006.03.004 10.1016/S0377-2217(01)00259-4 10.1016/j.eswa.2018.03.037 10.1016/j.jksuci.2015.06.002 10.1109/ICCONS.2017.8250694 10.1016/j.eswa.2014.12.003 10.1016/j.neucom.2017.06.010 10.1007/s10489-008-0150-y 10.1016/j.eswa.2017.03.028 10.12988/ces.2015.510286 10.1016/j.eswa.2015.03.017 10.1109/TII.2018.2794389 10.1109/TFUZZ.2016.2574915 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier Ltd Copyright Elsevier BV Dec 30, 2021 |
| Copyright_xml | – notice: 2021 Elsevier Ltd – notice: Copyright Elsevier BV Dec 30, 2021 |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1016/j.eswa.2021.115836 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-6793 |
| ExternalDocumentID | 10_1016_j_eswa_2021_115836 S0957417421011982 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AAXUO AAYFN ABBOA ABFNM ABMAC ABMVD ABUCO ABYKQ ACDAQ ACGFS ACHRH ACNTT ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGJBL AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM AXJTR BJAXD BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SDS SES SPC SPCBC SSB SSD SSL SST SSV SSZ T5K TN5 ~G- 29G 9DU AAAKG AAQXK AATTM AAXKI AAYWO AAYXX ABJNI ABKBG ABUFD ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET SEW WUQ XPP ZMT ~HD 7SC 8FD AFXIZ AGCQF AGRNS BNPGV JQ2 L7M L~C L~D SSH |
| ID | FETCH-LOGICAL-c328t-9430a0276733a73e2b4e2a131acd4fcfb698049f97f469ee5e6907b1e1a75c93 |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000705533700011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0957-4174 |
| IngestDate | Mon Jul 14 10:00:22 EDT 2025 Sat Nov 29 07:08:56 EST 2025 Tue Nov 18 21:18:31 EST 2025 Fri Feb 23 02:40:46 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Time-weighted Improved KFCM algorithm Financial time series ConvLSTM Dynamic prediction |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c328t-9430a0276733a73e2b4e2a131acd4fcfb698049f97f469ee5e6907b1e1a75c93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-4593-9332 0000-0003-1516-0480 |
| PQID | 2599115367 |
| PQPubID | 2045477 |
| ParticipantIDs | proquest_journals_2599115367 crossref_primary_10_1016_j_eswa_2021_115836 crossref_citationtrail_10_1016_j_eswa_2021_115836 elsevier_sciencedirect_doi_10_1016_j_eswa_2021_115836 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-12-30 |
| PublicationDateYYYYMMDD | 2021-12-30 |
| PublicationDate_xml | – month: 12 year: 2021 text: 2021-12-30 day: 30 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2021 |
| Publisher | Elsevier Ltd Elsevier BV |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier BV |
| References | Deng, Bao, Kong, Ren, Dai (b12) 2017; 28 Podsiadlo, Rybinski (b37) 2016; 66 Tsinaslanidis (b44) 2018; 94 Cervelló-Royo, Guijarro, Michniuk (b7) 2015; 42 Yu, Chen, Wang, Lai (b51) 2009; 13 Lu, Yang, Liu, Pedrycz (b33) 2014; 70 Lee, Ahn, Oh, Kim (b31) 2010; 32 Xu, Y., & Cohen, S. B. (2018). Stock movement prediction from tweets and historical prices. In LeBaron, Weigend (b30) 1998; 9 Nobre, Neves (b35) 2019; 125 Wang, Choi (b45) 2013 Chen, Hao (b9) 2017; 80 (pp. 14–15). Chennai, India. Kamble, R. A. (2017). Short and long term stock trend prediction using decision tree. In Wang, Pedrycz, Liu (b46) 2015; 41 Jiao, Y., & Jakubowicz, J. (2017). Predicting stock movement direction with machine learning: An extensive study on S&P 500 stocks. In Deng, Wang, Wang, Sun (b14) 2019 Xingjian, S., Chen, Z., Wang, H., Yeung, D. -Y., Wong, W. -K., & Woo, W. -c. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Kim, Shin (b28) 2007; 7 Feng, Chen, He, Ding, Sun, Chua (b16) 2018 Jidong, L., & Ran, Z. (2018). Dynamic weighting multi factor stock selection strategy based on XGBoost machine learning algorithm. In Jia (b23) 2016 (pp. 1371–1375). (pp. 4705–4713). Boston, Massachusetts, USA. Taieb, Bontempi, Atiya, Sorjamaa (b41) 2012; 39 (pp. 1419–1426). Anchorage, Alaska. Leigh, Modani, Purvis, Roberts (b32) 2002; 23 Deboeck (b11) 1994 Kim, So, Jeong, Lee, Kim, Kang (b29) 2019 Tay, Shen (b42) 2002; 141 Xie, Gu, Li, Cao, Tan, Nahavandi (b47) 2013; 64 Batra, R., & Daudpota, S. M. (2018). Integrating StockTwits with sentiment analysis for better prediction of stock price movement. In Akita, R., Yoshihara, A., Matsubara, T., & Uehara, K. (2016). Deep learning for stock prediction using numerical and textual information. In Zhang, Zhang, Zhang, Yu, Huang (b52) 2019; 23 Rather, Agarwal, Sastry (b38) 2015; 42 Di Persio, Honchar (b15) 2016; 10 Rout, Dash, Dash, Bisoi (b40) 2015; 29 (pp. 1970–1979). Melbourne, Australia. Yoshihara, A., Fujikawa, K., Seki, K., & Uehara, K. (2014). Predicting stock market trends by recurrent deep neural networks. In (pp. 868–872). Arévalo, García, Guijarro, Peris (b2) 2017; 81 Guresen, Kayakutlu, Daim (b19) 2011; 38 Astakhova, Demidova, Nikulchev (b3) 2015; 8 (pp. 759–969). Gold Coast, Australia. (pp. 1–6). Okayama, Japan. (pp. 785–794). Nelson, D. M., Pereira, A. C., & de Oliveira, R. A. (2017). Stock market’s price movement prediction with LSTM neural networks. In (pp. 802–810). Gong, Liang, Shi, Ma, Ma (b18) 2013; 22 Troiano, Villa, Loia (b43) 2018; 14 Deng, Ren, Kong, Bao, Dai (b13) 2017; 25 Zhong, Enke (b53) 2017; 267 Huang, Nakamori, Wang (b21) 2005; 32 Imandoust, Bolandraftar (b22) 2013; 3 Hoseinzade, Haratizadeh (b20) 2019; 129 Rezaee, Jozmaleki, Valipour (b39) 2018; 489 (pp. 1–5). Antwerp, Belgium. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Ghosh, R., & Purkayastha, P. (2017). Forecasting profitability in equity trades using random forest, support vector machine and XGBoost. In Peng, Jiang (b36) 2015 Bao, Yue, Rao (b4) 2017; 12 Kia, Haratizadeh, Shouraki (b27) 2018; 105 Basak, Kar, Saha, Khaidem, Dey (b5) 2019; 47 Chou, Nguyen (b10) 2018; 14 Cervelló-Royo (10.1016/j.eswa.2021.115836_b7) 2015; 42 Leigh (10.1016/j.eswa.2021.115836_b32) 2002; 23 Tsinaslanidis (10.1016/j.eswa.2021.115836_b44) 2018; 94 Deboeck (10.1016/j.eswa.2021.115836_b11) 1994 10.1016/j.eswa.2021.115836_b26 Rather (10.1016/j.eswa.2021.115836_b38) 2015; 42 Basak (10.1016/j.eswa.2021.115836_b5) 2019; 47 Peng (10.1016/j.eswa.2021.115836_b36) 2015 10.1016/j.eswa.2021.115836_b25 10.1016/j.eswa.2021.115836_b24 Jia (10.1016/j.eswa.2021.115836_b23) 2016 Lu (10.1016/j.eswa.2021.115836_b33) 2014; 70 Deng (10.1016/j.eswa.2021.115836_b12) 2017; 28 Hoseinzade (10.1016/j.eswa.2021.115836_b20) 2019; 129 Kim (10.1016/j.eswa.2021.115836_b28) 2007; 7 Feng (10.1016/j.eswa.2021.115836_b16) 2018 Rout (10.1016/j.eswa.2021.115836_b40) 2015; 29 Huang (10.1016/j.eswa.2021.115836_b21) 2005; 32 LeBaron (10.1016/j.eswa.2021.115836_b30) 1998; 9 Tay (10.1016/j.eswa.2021.115836_b42) 2002; 141 Wang (10.1016/j.eswa.2021.115836_b46) 2015; 41 10.1016/j.eswa.2021.115836_b34 Arévalo (10.1016/j.eswa.2021.115836_b2) 2017; 81 Bao (10.1016/j.eswa.2021.115836_b4) 2017; 12 10.1016/j.eswa.2021.115836_b50 Zhong (10.1016/j.eswa.2021.115836_b53) 2017; 267 Troiano (10.1016/j.eswa.2021.115836_b43) 2018; 14 10.1016/j.eswa.2021.115836_b6 Xie (10.1016/j.eswa.2021.115836_b47) 2013; 64 Wang (10.1016/j.eswa.2021.115836_b45) 2013 10.1016/j.eswa.2021.115836_b8 Podsiadlo (10.1016/j.eswa.2021.115836_b37) 2016; 66 Rezaee (10.1016/j.eswa.2021.115836_b39) 2018; 489 Yu (10.1016/j.eswa.2021.115836_b51) 2009; 13 Nobre (10.1016/j.eswa.2021.115836_b35) 2019; 125 10.1016/j.eswa.2021.115836_b49 10.1016/j.eswa.2021.115836_b48 Astakhova (10.1016/j.eswa.2021.115836_b3) 2015; 8 10.1016/j.eswa.2021.115836_b1 Deng (10.1016/j.eswa.2021.115836_b14) 2019 Deng (10.1016/j.eswa.2021.115836_b13) 2017; 25 Imandoust (10.1016/j.eswa.2021.115836_b22) 2013; 3 Taieb (10.1016/j.eswa.2021.115836_b41) 2012; 39 Kia (10.1016/j.eswa.2021.115836_b27) 2018; 105 Chou (10.1016/j.eswa.2021.115836_b10) 2018; 14 Chen (10.1016/j.eswa.2021.115836_b9) 2017; 80 Di Persio (10.1016/j.eswa.2021.115836_b15) 2016; 10 Lee (10.1016/j.eswa.2021.115836_b31) 2010; 32 Gong (10.1016/j.eswa.2021.115836_b18) 2013; 22 10.1016/j.eswa.2021.115836_b17 Kim (10.1016/j.eswa.2021.115836_b29) 2019 Zhang (10.1016/j.eswa.2021.115836_b52) 2019; 23 Guresen (10.1016/j.eswa.2021.115836_b19) 2011; 38 |
| References_xml | – reference: Ghosh, R., & Purkayastha, P. (2017). Forecasting profitability in equity trades using random forest, support vector machine and XGBoost. In – volume: 64 start-page: 280 year: 2013 end-page: 289 ident: b47 article-title: Concurrent control chart patterns recognition with singular spectrum analysis and support vector machine publication-title: Computers & Industrial Engineering – volume: 70 start-page: 242 year: 2014 end-page: 255 ident: b33 article-title: The modeling and prediction of time series based on synergy of high-order fuzzy cognitive map and fuzzy C-means clustering publication-title: Knowledge-Based Systems – reference: (pp. 1419–1426). Anchorage, Alaska. – volume: 94 start-page: 193 year: 2018 end-page: 204 ident: b44 article-title: Subsequence dynamic time warping for charting: Bullish and bearish class predictions for NYSE stocks publication-title: Expert Systems with Applications – year: 2018 ident: b16 article-title: Enhancing stock movement prediction with adversarial training – reference: Batra, R., & Daudpota, S. M. (2018). Integrating StockTwits with sentiment analysis for better prediction of stock price movement. In – reference: (pp. 1371–1375). – volume: 10 start-page: 403 year: 2016 end-page: 413 ident: b15 article-title: Artificial neural networks architectures for stock price prediction: Comparisons and applications publication-title: International Journal of Circuits, Systems and Signal Processing – year: 1994 ident: b11 article-title: Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets – reference: (pp. 868–872). – volume: 42 start-page: 3234 year: 2015 end-page: 3241 ident: b38 article-title: Recurrent neural network and a hybrid model for prediction of stock returns publication-title: Expert Systems with Applications – volume: 8 start-page: 1659 year: 2015 end-page: 1677 ident: b3 article-title: Forecasting of time series’ groups with application of fuzzy c-mean algorithm publication-title: Contemporary Engineering Sciences – reference: (pp. 14–15). Chennai, India. – volume: 25 start-page: 1006 year: 2017 end-page: 1012 ident: b13 article-title: A hierarchical fused fuzzy deep neural network for data classification publication-title: IEEE Transactions on Fuzzy Systems – volume: 489 start-page: 78 year: 2018 end-page: 93 ident: b39 article-title: Integrating dynamic fuzzy C-means, data envelopment analysis and artificial neural network to online prediction performance of companies in stock exchange publication-title: Physica A. Statistical Mechanics and its Applications – volume: 14 start-page: 1551 year: 2018 end-page: 3203 ident: b43 article-title: Replicating a trading strategy by means of LSTM for financial industry applications publication-title: IEEE Transactions on Industrial Informatics – year: 2013 ident: b45 article-title: Market index and stock price direction prediction using machine learning techniques: An empirical study on the KOSPI and HSI – volume: 28 start-page: 653 year: 2017 end-page: 664 ident: b12 article-title: Deep direct reinforcement learning for financial signal representation and trading publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 81 start-page: 177 year: 2017 end-page: 192 ident: b2 article-title: A dynamic trading rule based on filtered flag pattern recognition for stock market price forecasting publication-title: Expert Systems with Applications – volume: 23 start-page: 6979 year: 2019 end-page: 6994 ident: b52 article-title: A novel method based on FTS with both GA-FCM and multifactor BPNN for stock forecasting publication-title: Soft Computing – volume: 32 start-page: 2513 year: 2005 end-page: 2522 ident: b21 article-title: Forecasting stock market movement direction with support vector machine publication-title: Computers & Operations Research – volume: 22 start-page: 573 year: 2013 end-page: 584 ident: b18 article-title: Fuzzy C-means clustering with local information and kernel metric for image segmentation publication-title: IEEE Transactions on Image Processing – reference: Akita, R., Yoshihara, A., Matsubara, T., & Uehara, K. (2016). Deep learning for stock prediction using numerical and textual information. In – reference: Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In – reference: (pp. 4705–4713). Boston, Massachusetts, USA. – volume: 38 start-page: 10389 year: 2011 end-page: 10397 ident: b19 article-title: Using artificial neural network models in stock market index prediction publication-title: Expert Systems with Applications – volume: 129 start-page: 273 year: 2019 end-page: 285 ident: b20 article-title: CNNpred: CNN-based stock market prediction using a diverse set of variables publication-title: Expert Systems with Applications – year: 2015 ident: b36 article-title: Leverage financial news to predict stock price movements using word embeddings and deep neural networks – reference: Kamble, R. A. (2017). Short and long term stock trend prediction using decision tree. In – reference: (pp. 785–794). – volume: 7 start-page: 569 year: 2007 end-page: 576 ident: b28 article-title: A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets publication-title: Applied Soft Computing – volume: 29 start-page: 536 year: 2015 end-page: 552 ident: b40 article-title: Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach publication-title: Journal of King Saud University - Computer and Information Sciences – volume: 80 start-page: 340 year: 2017 end-page: 355 ident: b9 article-title: A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction publication-title: Expert Systems with Applications – volume: 14 start-page: 3132 year: 2018 end-page: 3142 ident: b10 article-title: Forward forecast of stock price using sliding-window metaheuristic-optimized machine learning regression publication-title: IEEE Transactions on Industrial Informatics – volume: 66 start-page: 219 year: 2016 end-page: 233 ident: b37 article-title: Financial time series forecasting using rough sets with time-weighted rule voting publication-title: Expert Systems with Applications – volume: 125 start-page: 181 year: 2019 end-page: 194 ident: b35 article-title: Combining principal component analysis, discrete wavelet transform and XGBoost to trade in the financial markets publication-title: Expert Systems with Applications – reference: (pp. 1970–1979). Melbourne, Australia. – volume: 32 start-page: 364 year: 2010 end-page: 377 ident: b31 article-title: Using rough set to support investment strategies of real-time trading in futures market publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies – volume: 23 start-page: 155 year: 2002 end-page: 159 ident: b32 article-title: Stock market trading rule discovery using technical charting heuristics publication-title: Expert Systems with Applications – reference: (pp. 802–810). – year: 2019 ident: b14 article-title: A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market publication-title: Applied Soft Computing – reference: Xingjian, S., Chen, Z., Wang, H., Yeung, D. -Y., Wong, W. -K., & Woo, W. -c. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In – year: 2016 ident: b23 article-title: Investigation into the effectiveness of long short term memory networks for stock price prediction – reference: (pp. 1–6). Okayama, Japan. – volume: 41 start-page: 17 year: 2015 end-page: 24 ident: b46 article-title: Time series long-term forecasting model based on information granules and fuzzy clustering publication-title: Engineering Applications of Artificial Intelligence – volume: 12 start-page: 1 year: 2017 end-page: 24 ident: b4 article-title: A deep learning framework for financial time series using stacked autoencoders and long-short term memory publication-title: PLoS One – reference: Yoshihara, A., Fujikawa, K., Seki, K., & Uehara, K. (2014). Predicting stock market trends by recurrent deep neural networks. In – reference: Nelson, D. M., Pereira, A. C., & de Oliveira, R. A. (2017). Stock market’s price movement prediction with LSTM neural networks. In – reference: (pp. 759–969). Gold Coast, Australia. – volume: 9 start-page: 213 year: 1998 end-page: 220 ident: b30 article-title: A bootstrap evaluation of the effect of data splitting on financial time series publication-title: IEEE Transactions on Neural Networks – reference: Xu, Y., & Cohen, S. B. (2018). Stock movement prediction from tweets and historical prices. In – volume: 42 start-page: 5963 year: 2015 end-page: 5975 ident: b7 article-title: Stock market trading rule based on pattern recognition and technical analysis: Forecasting the DJIA index with intraday data publication-title: Expert Systems with Applications – volume: 47 start-page: 552 year: 2019 end-page: 567 ident: b5 article-title: Predicting the direction of stock market prices using tree-based classifiers publication-title: The North American Journal of Economics and Finance – volume: 141 start-page: 641 year: 2002 end-page: 659 ident: b42 article-title: Economic and financial prediction using rough sets model publication-title: European Journal of Operational Research – reference: (pp. 1–5). Antwerp, Belgium. – volume: 39 start-page: 7067 year: 2012 end-page: 7083 ident: b41 article-title: A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition publication-title: Expert Systems with Applications – volume: 13 start-page: 87 year: 2009 end-page: 102 ident: b51 article-title: Evolving least squares support vector machines for stock market trend mining publication-title: IEEE Transactions on Evolutionary Computation – volume: 267 start-page: 152 year: 2017 end-page: 168 ident: b53 article-title: A comprehensive cluster and classification mining procedure for daily stock market return forecasting publication-title: Neurocomputing – volume: 3 start-page: 605 year: 2013 end-page: 610 ident: b22 article-title: Application of k-nearest neighbor (KNN) approach for predicting economic events: Theoretical background publication-title: International Journal of Engineering Research and Applications – reference: Jiao, Y., & Jakubowicz, J. (2017). Predicting stock movement direction with machine learning: An extensive study on S&P 500 stocks. In – year: 2019 ident: b29 article-title: HATS: A hierarchical graph attention network for stock movement prediction – reference: Jidong, L., & Ran, Z. (2018). Dynamic weighting multi factor stock selection strategy based on XGBoost machine learning algorithm. In – volume: 105 start-page: 159 year: 2018 end-page: 173 ident: b27 article-title: A hybrid supervised semi-supervised graph-based model to predict one-day ahead movement of global stock markets and commodity prices publication-title: Expert Systems with Applications – ident: 10.1016/j.eswa.2021.115836_b34 doi: 10.1109/IJCNN.2017.7966019 – volume: 14 start-page: 1551 issue: 7 year: 2018 ident: 10.1016/j.eswa.2021.115836_b43 article-title: Replicating a trading strategy by means of LSTM for financial industry applications publication-title: IEEE Transactions on Industrial Informatics doi: 10.1109/TII.2018.2811377 – volume: 28 start-page: 653 issue: 3 year: 2017 ident: 10.1016/j.eswa.2021.115836_b12 article-title: Deep direct reinforcement learning for financial signal representation and trading publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2016.2522401 – volume: 10 start-page: 403 year: 2016 ident: 10.1016/j.eswa.2021.115836_b15 article-title: Artificial neural networks architectures for stock price prediction: Comparisons and applications publication-title: International Journal of Circuits, Systems and Signal Processing – volume: 94 start-page: 193 year: 2018 ident: 10.1016/j.eswa.2021.115836_b44 article-title: Subsequence dynamic time warping for charting: Bullish and bearish class predictions for NYSE stocks publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2017.10.055 – volume: 23 start-page: 155 issue: 2 year: 2002 ident: 10.1016/j.eswa.2021.115836_b32 article-title: Stock market trading rule discovery using technical charting heuristics publication-title: Expert Systems with Applications doi: 10.1016/S0957-4174(02)00034-9 – volume: 3 start-page: 605 issue: 5 year: 2013 ident: 10.1016/j.eswa.2021.115836_b22 article-title: Application of k-nearest neighbor (KNN) approach for predicting economic events: Theoretical background publication-title: International Journal of Engineering Research and Applications – volume: 64 start-page: 280 year: 2013 ident: 10.1016/j.eswa.2021.115836_b47 article-title: Concurrent control chart patterns recognition with singular spectrum analysis and support vector machine publication-title: Computers & Industrial Engineering doi: 10.1016/j.cie.2012.10.009 – volume: 9 start-page: 213 issue: 1 year: 1998 ident: 10.1016/j.eswa.2021.115836_b30 article-title: A bootstrap evaluation of the effect of data splitting on financial time series publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.655043 – volume: 41 start-page: 17 year: 2015 ident: 10.1016/j.eswa.2021.115836_b46 article-title: Time series long-term forecasting model based on information granules and fuzzy clustering publication-title: Engineering Applications of Artificial Intelligence doi: 10.1016/j.engappai.2015.01.006 – volume: 80 start-page: 340 year: 2017 ident: 10.1016/j.eswa.2021.115836_b9 article-title: A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2017.02.044 – ident: 10.1016/j.eswa.2021.115836_b6 doi: 10.1109/ICOMET.2018.8346382 – year: 2013 ident: 10.1016/j.eswa.2021.115836_b45 – volume: 13 start-page: 87 issue: 1 year: 2009 ident: 10.1016/j.eswa.2021.115836_b51 article-title: Evolving least squares support vector machines for stock market trend mining publication-title: IEEE Transactions on Evolutionary Computation doi: 10.1109/TEVC.2008.928176 – ident: 10.1016/j.eswa.2021.115836_b24 doi: 10.1109/BigData.2017.8258518 – volume: 70 start-page: 242 year: 2014 ident: 10.1016/j.eswa.2021.115836_b33 article-title: The modeling and prediction of time series based on synergy of high-order fuzzy cognitive map and fuzzy C-means clustering publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2014.07.004 – volume: 489 start-page: 78 year: 2018 ident: 10.1016/j.eswa.2021.115836_b39 article-title: Integrating dynamic fuzzy C-means, data envelopment analysis and artificial neural network to online prediction performance of companies in stock exchange publication-title: Physica A. Statistical Mechanics and its Applications doi: 10.1016/j.physa.2017.07.017 – volume: 23 start-page: 6979 year: 2019 ident: 10.1016/j.eswa.2021.115836_b52 article-title: A novel method based on FTS with both GA-FCM and multifactor BPNN for stock forecasting publication-title: Soft Computing doi: 10.1007/s00500-018-3335-2 – ident: 10.1016/j.eswa.2021.115836_b17 – year: 1994 ident: 10.1016/j.eswa.2021.115836_b11 – ident: 10.1016/j.eswa.2021.115836_b8 doi: 10.1145/2939672.2939785 – volume: 32 start-page: 2513 issue: 10 year: 2005 ident: 10.1016/j.eswa.2021.115836_b21 article-title: Forecasting stock market movement direction with support vector machine publication-title: Computers & Operations Research doi: 10.1016/j.cor.2004.03.016 – ident: 10.1016/j.eswa.2021.115836_b49 doi: 10.18653/v1/P18-1183 – ident: 10.1016/j.eswa.2021.115836_b1 doi: 10.1109/ICIS.2016.7550882 – volume: 39 start-page: 7067 issue: 8 year: 2012 ident: 10.1016/j.eswa.2021.115836_b41 article-title: A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2012.01.039 – volume: 22 start-page: 573 issue: 2 year: 2013 ident: 10.1016/j.eswa.2021.115836_b18 article-title: Fuzzy C-means clustering with local information and kernel metric for image segmentation publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2012.2219547 – ident: 10.1016/j.eswa.2021.115836_b25 doi: 10.1109/IICSPI.2018.8690416 – ident: 10.1016/j.eswa.2021.115836_b48 – year: 2019 ident: 10.1016/j.eswa.2021.115836_b14 article-title: A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market publication-title: Applied Soft Computing doi: 10.1016/j.asoc.2019.105652 – volume: 38 start-page: 10389 issue: 8 year: 2011 ident: 10.1016/j.eswa.2021.115836_b19 article-title: Using artificial neural network models in stock market index prediction publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2011.02.068 – year: 2019 ident: 10.1016/j.eswa.2021.115836_b29 – ident: 10.1016/j.eswa.2021.115836_b50 doi: 10.1007/978-3-319-13560-1_60 – volume: 47 start-page: 552 year: 2019 ident: 10.1016/j.eswa.2021.115836_b5 article-title: Predicting the direction of stock market prices using tree-based classifiers publication-title: The North American Journal of Economics and Finance doi: 10.1016/j.najef.2018.06.013 – volume: 12 start-page: 1 issue: 7 year: 2017 ident: 10.1016/j.eswa.2021.115836_b4 article-title: A deep learning framework for financial time series using stacked autoencoders and long-short term memory publication-title: PLoS One doi: 10.1371/journal.pone.0180944 – volume: 66 start-page: 219 year: 2016 ident: 10.1016/j.eswa.2021.115836_b37 article-title: Financial time series forecasting using rough sets with time-weighted rule voting publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2016.08.066 – year: 2018 ident: 10.1016/j.eswa.2021.115836_b16 – volume: 129 start-page: 273 year: 2019 ident: 10.1016/j.eswa.2021.115836_b20 article-title: CNNpred: CNN-based stock market prediction using a diverse set of variables publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2019.03.029 – volume: 125 start-page: 181 year: 2019 ident: 10.1016/j.eswa.2021.115836_b35 article-title: Combining principal component analysis, discrete wavelet transform and XGBoost to trade in the financial markets publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2019.01.083 – volume: 7 start-page: 569 issue: 2 year: 2007 ident: 10.1016/j.eswa.2021.115836_b28 article-title: A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets publication-title: Applied Soft Computing doi: 10.1016/j.asoc.2006.03.004 – year: 2015 ident: 10.1016/j.eswa.2021.115836_b36 – volume: 141 start-page: 641 issue: 3 year: 2002 ident: 10.1016/j.eswa.2021.115836_b42 article-title: Economic and financial prediction using rough sets model publication-title: European Journal of Operational Research doi: 10.1016/S0377-2217(01)00259-4 – volume: 105 start-page: 159 year: 2018 ident: 10.1016/j.eswa.2021.115836_b27 article-title: A hybrid supervised semi-supervised graph-based model to predict one-day ahead movement of global stock markets and commodity prices publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2018.03.037 – volume: 29 start-page: 536 issue: 4 year: 2015 ident: 10.1016/j.eswa.2021.115836_b40 article-title: Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach publication-title: Journal of King Saud University - Computer and Information Sciences doi: 10.1016/j.jksuci.2015.06.002 – year: 2016 ident: 10.1016/j.eswa.2021.115836_b23 – ident: 10.1016/j.eswa.2021.115836_b26 doi: 10.1109/ICCONS.2017.8250694 – volume: 42 start-page: 3234 issue: 6 year: 2015 ident: 10.1016/j.eswa.2021.115836_b38 article-title: Recurrent neural network and a hybrid model for prediction of stock returns publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2014.12.003 – volume: 267 start-page: 152 year: 2017 ident: 10.1016/j.eswa.2021.115836_b53 article-title: A comprehensive cluster and classification mining procedure for daily stock market return forecasting publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.06.010 – volume: 32 start-page: 364 issue: 3 year: 2010 ident: 10.1016/j.eswa.2021.115836_b31 article-title: Using rough set to support investment strategies of real-time trading in futures market publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies doi: 10.1007/s10489-008-0150-y – volume: 81 start-page: 177 year: 2017 ident: 10.1016/j.eswa.2021.115836_b2 article-title: A dynamic trading rule based on filtered flag pattern recognition for stock market price forecasting publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2017.03.028 – volume: 8 start-page: 1659 issue: 35 year: 2015 ident: 10.1016/j.eswa.2021.115836_b3 article-title: Forecasting of time series’ groups with application of fuzzy c-mean algorithm publication-title: Contemporary Engineering Sciences doi: 10.12988/ces.2015.510286 – volume: 42 start-page: 5963 issue: 14 year: 2015 ident: 10.1016/j.eswa.2021.115836_b7 article-title: Stock market trading rule based on pattern recognition and technical analysis: Forecasting the DJIA index with intraday data publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2015.03.017 – volume: 14 start-page: 3132 issue: 7 year: 2018 ident: 10.1016/j.eswa.2021.115836_b10 article-title: Forward forecast of stock price using sliding-window metaheuristic-optimized machine learning regression publication-title: IEEE Transactions on Industrial Informatics doi: 10.1109/TII.2018.2794389 – volume: 25 start-page: 1006 issue: 4 year: 2017 ident: 10.1016/j.eswa.2021.115836_b13 article-title: A hierarchical fused fuzzy deep neural network for data classification publication-title: IEEE Transactions on Fuzzy Systems doi: 10.1109/TFUZZ.2016.2574915 |
| SSID | ssj0017007 |
| Score | 2.406757 |
| Snippet | Although training a deep network with financial time series is not hard, the important issue is, how much the prediction for the truly new data can be trusted... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 115836 |
| SubjectTerms | Algorithms Clustering ConvLSTM Deep learning Dynamic prediction Financial time series Improved KFCM algorithm Kernels Machine learning Performance prediction Prediction models Stock exchanges Time series Time-weighted Training |
| Title | A dynamic predictor selection algorithm for predicting stock market movement |
| URI | https://dx.doi.org/10.1016/j.eswa.2021.115836 https://www.proquest.com/docview/2599115367 |
| Volume | 186 |
| WOSCitedRecordID | wos000705533700011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-6793 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9wwEBbtpode-i5JmwYdejMOtixb1nEpKdsQQqF72JuRbanZJesNa2-69Nd39LCcbElIDrkYY0aD8HwajUbzQOgrq5XI4roKs5qrkCpYijxRNISlVPEojQSxicJn7Pw8n834T3dj2pp2Aqxp8u2WXz2pqOEbCFunzj5C3J4pfIB3EDo8QezwfJDgx0Ftu8zr_P96rp3yQWu63ZjI48vfq_W8u1ia-EJHYX0KoBmDpUmCDpar6yEkZuGj9eS6c6Wf-6S4G9ff3iR2Qb6_LjZdvy8aj72L_QU8budDINDG-GonMOiv3KWdCDg0OxbOM0FiU_8wuuViZCGNbReeQdve1Jdgj-a2AMp_qtx6FRbHsv2j60OR-Hggvl03e2c_81GGfQDbotA8Cs2jsDyeoz3CUp6P0N74x8ns1N87scgm2Pczd2lWNiJwdyZ3mTI7m7qxVKZv0Ct3xMBjC4236Jls3qHXffsO7LT5e3Q2xg4p2CMFe6RgjxQMSMEDUrBBCrZIwT1SPqDp95Ppt0nommuEVULyLtRl90VEWMaSRLBEkpJKIuIkFlVNVaXKjOdwelScKZpxKVOp_ShlLGPB0oonH9GoWTVyH2HdGTnPgIIKQTkpBStlqUitmL6yJvQAxf1vKipXeF73P7ks7hbQAQr8mCtbduVe6rT_-4UzHK1BWACY7h132IuqcCu4LUgKRyawAzL26VGT-IxeDovgEI269UZ-QS-q627ero8c0P4BA1-bbg |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+dynamic+predictor+selection+algorithm+for+predicting+stock+market+movement&rft.jtitle=Expert+systems+with+applications&rft.au=Dong%2C+Shuting&rft.au=Wang%2C+Jianxin&rft.au=Luo%2C+Hongze&rft.au=Wang%2C+Haodong&rft.date=2021-12-30&rft.issn=0957-4174&rft.volume=186&rft.spage=115836&rft_id=info:doi/10.1016%2Fj.eswa.2021.115836&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_eswa_2021_115836 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |