No more black boxes! Explaining the predictions of a machine learning XGBoost classifier algorithm in business failure
This study opens the black boxes and fills the literature gap by showing how it is possible to fit a very precise Machine Learning model that is highly interpretable, by using a novel ML technique, Extreme Gradient Boosting (XGBoost), and applying new model interpretability improvements. In addition...
Uloženo v:
| Vydáno v: | Research in international business and finance Ročník 61; s. 101649 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.10.2022
|
| Témata: | |
| ISSN: | 0275-5319, 1878-3384 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | This study opens the black boxes and fills the literature gap by showing how it is possible to fit a very precise Machine Learning model that is highly interpretable, by using a novel ML technique, Extreme Gradient Boosting (XGBoost), and applying new model interpretability improvements. In addition, we identify several significant indicators that could assist in predicting business financial distress. The data were collected from the Eikon database from a sample of 1760 French firms (1585 healthy and 175 failing) in 2018. Identifying the leading indicators of business failure is critical in assisting regulators, and for business managers to act expeditiously before a distressed business reaches crisis point. Our results reveal that higher levels of equity per employee, solvency, the current ratio, net profitability, and a sustainable return on investment are associated with a lower risk of business failure. In contrast, a higher number of employees leads to business failure.
[Display omitted]
•Bankruptcy prediction techniques have recently switched to intelligent machine learning models.•Machine Learning models are often considered a black box due to their complexity.•Model interpretability is a rapidly expanding ML models.•Using XGBoost and model interpretability could assist in predicting business failure. |
|---|---|
| AbstractList | This study opens the black boxes and fills the literature gap by showing how it is possible to fit a very precise Machine Learning model that is highly interpretable, by using a novel ML technique, Extreme Gradient Boosting (XGBoost), and applying new model interpretability improvements. In addition, we identify several significant indicators that could assist in predicting business financial distress. The data were collected from the Eikon database from a sample of 1760 French firms (1585 healthy and 175 failing) in 2018. Identifying the leading indicators of business failure is critical in assisting regulators, and for business managers to act expeditiously before a distressed business reaches crisis point. Our results reveal that higher levels of equity per employee, solvency, the current ratio, net profitability, and a sustainable return on investment are associated with a lower risk of business failure. In contrast, a higher number of employees leads to business failure.
[Display omitted]
•Bankruptcy prediction techniques have recently switched to intelligent machine learning models.•Machine Learning models are often considered a black box due to their complexity.•Model interpretability is a rapidly expanding ML models.•Using XGBoost and model interpretability could assist in predicting business failure. |
| ArticleNumber | 101649 |
| Author | Mardawi, Zeena Carmona, Pedro Dwekat, Aladdin |
| Author_xml | – sequence: 1 givenname: Pedro surname: Carmona fullname: Carmona, Pedro email: pedro.carmona@uv.es organization: Department of Accounting, Universitat de València, València, Spain – sequence: 2 givenname: Aladdin surname: Dwekat fullname: Dwekat, Aladdin email: aladdin.dwekat@najah.edu, aldwe@doctor.upv.es organization: Department of Accounting, An-Najah National University, Nablus, Palestine – sequence: 3 givenname: Zeena surname: Mardawi fullname: Mardawi, Zeena email: zeedwedw@doctor.upv.es organization: Department of Accounting, An-Najah National University, Nablus, Palestine |
| BookMark | eNqFkE1PwkAQhjcGEwH9BV7WH1Dcj5a2Bw9KEE2IXjTxtpnuzsJi6ZLdQvDfW8CTBz1NMnmfybzPgPQa3yAh15yNOOPj29UouArsSDAhjpu0PCN9XuRFImWR9kifiTxLMsnLCzKIccWYKBkXfbJ78XTtA9KqBv1JK7_HeEOn-00NrnHNgrZLpJuAxunW-SZSbynQNeila5DWCOGY-pg9eB9bqmuI0VmHgUK98MG1yzV1Da22scvHSC24ehvwkpxbqCNe_cwheX-cvk2ekvnr7HlyP0-0LHiblCnmpeByrBFEbm1uTcrz3DADmZU2NZwXGjSWsipMxlMjASqhtYFUswy4HBJ5uquDjzGgVZvg1hC-FGfqIEqt1FGdOqhTJ3UdVf6itGvh0L8N3f__sHcnFrtau06EitphozuDAXWrjHd_8t_c8pAK |
| CitedBy_id | crossref_primary_10_1080_01605682_2024_2385467 crossref_primary_10_1111_beer_12439 crossref_primary_10_1080_02102412_2024_2423498 crossref_primary_10_3390_electronics11193181 crossref_primary_10_1016_j_compbiomed_2024_108982 crossref_primary_10_1016_j_future_2024_04_037 crossref_primary_10_1016_j_techfore_2024_123829 crossref_primary_10_1080_17421772_2024_2418906 crossref_primary_10_1016_j_ribaf_2022_101744 crossref_primary_10_1108_IJCHM_06_2022_0737 crossref_primary_10_1016_j_jclepro_2024_141035 crossref_primary_10_2478_picbe_2024_0020 crossref_primary_10_1016_j_jtrangeo_2023_103594 crossref_primary_10_1111_joes_70014 crossref_primary_10_1016_j_istruc_2023_105053 crossref_primary_10_1108_K_08_2023_1428 crossref_primary_10_1108_JFRA_05_2024_0280 crossref_primary_10_1108_MEDAR_04_2022_1654 crossref_primary_10_1016_j_ipm_2024_103820 crossref_primary_10_1016_j_hssust_2025_04_002 crossref_primary_10_1016_j_jhydrol_2025_133927 crossref_primary_10_3390_atmos16040456 crossref_primary_10_3390_su17114948 crossref_primary_10_1108_JFRA_10_2024_0719 crossref_primary_10_1080_17517575_2024_2434742 crossref_primary_10_3390_make6010031 crossref_primary_10_1007_s10462_024_10854_8 crossref_primary_10_1016_j_ifacol_2024_07_526 crossref_primary_10_2147_JHC_S429903 crossref_primary_10_1016_j_frl_2023_104145 crossref_primary_10_18559_ebr_2024_2_1149 crossref_primary_10_3390_jtaer19020066 crossref_primary_10_3390_s24020330 crossref_primary_10_1007_s12525_025_00824_5 crossref_primary_10_1016_j_irfa_2024_103381 crossref_primary_10_3390_systems10060252 crossref_primary_10_1016_j_mtcomm_2023_105793 crossref_primary_10_33399_biibfad_1391666 crossref_primary_10_1016_j_compag_2025_110490 crossref_primary_10_1109_ACCESS_2025_3579712 crossref_primary_10_1016_j_compag_2023_108254 crossref_primary_10_1108_MEDAR_05_2022_1698 crossref_primary_10_3390_ma16227178 crossref_primary_10_3390_youth5030068 crossref_primary_10_1016_j_enpol_2025_114812 crossref_primary_10_1080_00036846_2023_2281291 crossref_primary_10_1007_s10614_024_10620_6 |
| Cites_doi | 10.1016/j.knosys.2017.05.003 10.1016/j.irfa.2015.01.006 10.3389/fnbot.2013.00021 10.1016/j.indmarman.2017.12.019 10.1016/j.jbusres.2018.11.015 10.1016/j.irfa.2018.07.007 10.1214/aos/1013203451 10.1016/j.jbef.2021.100577 10.1016/j.eswa.2017.01.016 10.1145/2939672.2939785 10.1201/9780429027192 10.1016/j.dss.2007.12.002 10.1016/j.eswa.2016.04.001 10.1007/978-3-319-72598-7_13 10.1080/00949655.2012.666550 10.1214/aos/1016120463 10.1007/s11142-017-9407-1 10.1016/j.knosys.2011.09.017 10.1111/j.1365-2656.2008.01390.x 10.1016/j.eswa.2017.02.017 10.1080/21582041.2020.1806346 10.5172/ser.2.1-2.5 10.1016/j.eswa.2016.04.027 10.1016/j.iref.2018.03.008 10.1016/j.ejor.2016.03.008 10.1016/j.eswa.2012.12.009 10.1016/j.irfa.2017.02.004 10.1016/S0167-9473(01)00065-2 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. |
| Copyright_xml | – notice: 2022 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ribaf.2022.101649 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Business |
| EISSN | 1878-3384 |
| ExternalDocumentID | 10_1016_j_ribaf_2022_101649 S027553192200037X |
| GroupedDBID | --K --M .~1 0R~ 123 13V 1B1 1~. 1~5 4.4 457 4G. 5VS 7-5 71M 8P~ AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAPFB AAQFI AAXUO ABFNM ABJNI ABKBG ABMAC ABMVD ABPPZ ABXDB ABYKQ ACDAQ ACGFS ACHRH ACNCT ACNTT ACRLP ACROA ADBBV ADEZE ADFHU ADMUD ADOJD AEBSH AEKER AEYQN AFFNX AFKWA AFTJW AGHFR AGJBL AGTHC AGUBO AGUMN AGYEJ AIEXJ AIIAU AIKHN AITUG AJBFU AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR AXLSJ BKOJK BLXMC BNSAS BZJEE CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FIRID FNPLU FYGXN G-Q GBLVA HVGLF HZ~ IHE IXIXF J1W KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SEB SES SEW SPCBC SSB SSF SSL SSZ T5K WH7 YNT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABUFD ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AHDLI AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c381t-94e792136cea27ff7fd4177d0da5f3f4d118cace93b8d514d3aab2ccda4c05a13 |
| ISICitedReferencesCount | 50 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000805435500019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0275-5319 |
| IngestDate | Sat Nov 29 07:23:32 EST 2025 Tue Nov 18 22:14:20 EST 2025 Fri Feb 23 02:39:35 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | C 45 Model interpretability C46 Business failure G33 XGBoost G32 Machine learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c381t-94e792136cea27ff7fd4177d0da5f3f4d118cace93b8d514d3aab2ccda4c05a13 |
| OpenAccessLink | https://hdl.handle.net/10550/96507 |
| ParticipantIDs | crossref_primary_10_1016_j_ribaf_2022_101649 crossref_citationtrail_10_1016_j_ribaf_2022_101649 elsevier_sciencedirect_doi_10_1016_j_ribaf_2022_101649 |
| PublicationCentury | 2000 |
| PublicationDate | October 2022 2022-10-00 |
| PublicationDateYYYYMMDD | 2022-10-01 |
| PublicationDate_xml | – month: 10 year: 2022 text: October 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Research in international business and finance |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Dwekat, Seguí-Mas, Zaid, Tormo-Carbó (bib22) 2021 Faccia, Petratos (bib27) 2021; 11 Chen, T., & Guestrin, C., 2016, XGBoost: A scalable tree boosting system. Foster, D., 2017, NEW R package that makes XGBoost interpretable. Retrieved from 〈https://medium.com/applied-data-science/new-r-package-the-xgboost-explainer-51dd7d1aa211〉. Duan, Goodell, Li, Li (bib18) 2021 Faccia, Manni, Capitanio (bib26) 2021; 13 Rapanyane, Sethole (bib51) 2020; 15 Carmona, Climent, Momparler (bib9) 2019; 61 Friedman (bib30) 2001; 29 Goodell, Kumar, Lim, Pattnaik (bib33) 2021 Berryman (bib3) 1993; 2 Momparler, Carmona, Climent (bib44) 2016; 45 Hosaka (bib36) 2019 Momparler, Carmona, Climent (bib45) 2020; 33 Carvalho, Pereira, Cardoso (bib10) 2019; Vol. 8 Biecek, Burzykowski (bib5) 2021 Campillo, Vargas, Ibáñez (bib8) 2018; 47 Cran.r-project.org. (2020). Introducing Correlation Funnel - Customer Churn Example. Retrieved from Du Jardin (bib19) 2016; 254 Fisher, Rudin, Dominici (bib28) 2018 Friedman (bib31) 2002; 38 Erdogan (bib25) 2013; 83 Stolbov, Shchepeleva (bib53) 2020 Altman (bib2) 1968; 23 Cortés, Martínez, Rubio (bib14) 2008; 37 Gilpin, Bau, Yuan, Bajwa, Specter, Kagal (bib34) 2018 Jones (bib38) 2017; 22 . Syam, Sharma (bib54) 2018; 69 Alfaro, García, Gámez, Elizondo (bib1) 2008; 45 Oyewo, Ajibola, Ajape (bib50) 2020 Zhou, Si, Fujita (bib59) 2017; 128 Boubaker, Buchanan, Nguyen (bib7) 2016 Mosteanu, Faccia (bib46) 2020; 21 Lee, Choi (bib43) 2013; 40 Xia, Liu, Li, Liu (bib58) 2017; 78 Jabeur, Gharib, Mefteh-Wali, Arfi (bib37) 2021 Eling, Jia (bib23) 2018; 59 Mselmi, Lahiani, Hamza (bib48) 2017; 50 Biecek (bib4) 2018; 19 Friedman, J., Hastie, T., & Tibshirani, R., 2000, Additive logistic regression: A statistical view of boosting. In (Vol. 28, pp. 337–407). Boehmke, Greenwell (bib6) 2020 Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H.,. Zhou, T. (2019). xgboost: Extreme gradient boosting. R package version 0.90. 0.2. In. Vega García, Aznarte (bib57) 2020 Tsai, Cheng (bib56) 2012; 27 Mousavi, Ouenniche, Xu (bib47) 2015; 42 Kim, Jo, Shin (bib41) 2016; 59 Elith, J., Leathwick, J.R., & Hastie, T., 2008, A working guide to boosted regression trees. In (Vol. 77, pp. 802–813). Natekin, Knoll (bib49) 2013; 7 Davies (bib16) 1997 Tian, Yu (bib55) 2017 Du Jardin (bib20) 2017; 75 Dwekat, Seguí-Mas, Tormo-Carbó (bib21) 2020; 33 Khoja, Chipulu, Jayasekera (bib40) 2019 Santhanam, G.R., Holland, B., Kothari, S., & Ranade, N., 2017, Human-on-the-loop automation for detecting software side-channel vulnerabilities. Doshi-Velez, Kim (bib17) 2017 Le, Viviani (bib42) 2018 Climent, Momparler, Carmona (bib13) 2019; 101 Kalak, Azevedo, Hudson, Karim (bib39) 2017 Hall, Gill (bib35) 2019 Zięba, Tomczak, Tomczak (bib60) 2016; 58 Du Jardin (10.1016/j.ribaf.2022.101649_bib20) 2017; 75 10.1016/j.ribaf.2022.101649_bib32 Le (10.1016/j.ribaf.2022.101649_bib42) 2018 Zhou (10.1016/j.ribaf.2022.101649_bib59) 2017; 128 Biecek (10.1016/j.ribaf.2022.101649_bib4) 2018; 19 Jones (10.1016/j.ribaf.2022.101649_bib38) 2017; 22 Dwekat (10.1016/j.ribaf.2022.101649_bib22) 2021 Momparler (10.1016/j.ribaf.2022.101649_bib44) 2016; 45 Stolbov (10.1016/j.ribaf.2022.101649_bib53) 2020 Friedman (10.1016/j.ribaf.2022.101649_bib31) 2002; 38 Momparler (10.1016/j.ribaf.2022.101649_bib45) 2020; 33 Altman (10.1016/j.ribaf.2022.101649_bib2) 1968; 23 Hall (10.1016/j.ribaf.2022.101649_bib35) 2019 Oyewo (10.1016/j.ribaf.2022.101649_bib50) 2020 Davies (10.1016/j.ribaf.2022.101649_bib16) 1997 Mselmi (10.1016/j.ribaf.2022.101649_bib48) 2017; 50 Friedman (10.1016/j.ribaf.2022.101649_bib30) 2001; 29 Xia (10.1016/j.ribaf.2022.101649_bib58) 2017; 78 Cortés (10.1016/j.ribaf.2022.101649_bib14) 2008; 37 Tian (10.1016/j.ribaf.2022.101649_bib55) 2017 Fisher (10.1016/j.ribaf.2022.101649_bib28) 2018 Berryman (10.1016/j.ribaf.2022.101649_bib3) 1993; 2 Faccia (10.1016/j.ribaf.2022.101649_bib26) 2021; 13 Boubaker (10.1016/j.ribaf.2022.101649_bib7) 2016 10.1016/j.ribaf.2022.101649_bib29 Erdogan (10.1016/j.ribaf.2022.101649_bib25) 2013; 83 Duan (10.1016/j.ribaf.2022.101649_bib18) 2021 10.1016/j.ribaf.2022.101649_bib24 Climent (10.1016/j.ribaf.2022.101649_bib13) 2019; 101 Eling (10.1016/j.ribaf.2022.101649_bib23) 2018; 59 Carmona (10.1016/j.ribaf.2022.101649_bib9) 2019; 61 Du Jardin (10.1016/j.ribaf.2022.101649_bib19) 2016; 254 Rapanyane (10.1016/j.ribaf.2022.101649_bib51) 2020; 15 Syam (10.1016/j.ribaf.2022.101649_bib54) 2018; 69 10.1016/j.ribaf.2022.101649_bib11 Goodell (10.1016/j.ribaf.2022.101649_bib33) 2021 Gilpin (10.1016/j.ribaf.2022.101649_bib34) 2018 Campillo (10.1016/j.ribaf.2022.101649_bib8) 2018; 47 10.1016/j.ribaf.2022.101649_bib52 Biecek (10.1016/j.ribaf.2022.101649_bib5) 2021 Lee (10.1016/j.ribaf.2022.101649_bib43) 2013; 40 Jabeur (10.1016/j.ribaf.2022.101649_bib37) 2021 Mosteanu (10.1016/j.ribaf.2022.101649_bib46) 2020; 21 10.1016/j.ribaf.2022.101649_bib15 10.1016/j.ribaf.2022.101649_bib12 Natekin (10.1016/j.ribaf.2022.101649_bib49) 2013; 7 Tsai (10.1016/j.ribaf.2022.101649_bib56) 2012; 27 Dwekat (10.1016/j.ribaf.2022.101649_bib21) 2020; 33 Hosaka (10.1016/j.ribaf.2022.101649_bib36) 2019 Doshi-Velez (10.1016/j.ribaf.2022.101649_bib17) 2017 Zięba (10.1016/j.ribaf.2022.101649_bib60) 2016; 58 Carvalho (10.1016/j.ribaf.2022.101649_bib10) 2019; Vol. 8 Khoja (10.1016/j.ribaf.2022.101649_bib40) 2019 Kim (10.1016/j.ribaf.2022.101649_bib41) 2016; 59 Alfaro (10.1016/j.ribaf.2022.101649_bib1) 2008; 45 Boehmke (10.1016/j.ribaf.2022.101649_bib6) 2020 Kalak (10.1016/j.ribaf.2022.101649_bib39) 2017 Mousavi (10.1016/j.ribaf.2022.101649_bib47) 2015; 42 Faccia (10.1016/j.ribaf.2022.101649_bib27) 2021; 11 Vega García (10.1016/j.ribaf.2022.101649_bib57) 2020 |
| References_xml | – start-page: 1 year: 2018 end-page: 11 ident: bib34 article-title: Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning publication-title: arXiv:1806. 00069 – volume: 128 start-page: 93 year: 2017 end-page: 101 ident: bib59 article-title: Predicting the listing statuses of Chinese-listed companies using decision trees combined with an improved filter feature selection method publication-title: Knowl. -Based Syst. – year: 2021 ident: bib33 article-title: Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis publication-title: J. Behav. Exp. Financ. – volume: 40 start-page: 2941 year: 2013 end-page: 2946 ident: bib43 article-title: A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis publication-title: Expert Syst. Appl. – reference: Santhanam, G.R., Holland, B., Kothari, S., & Ranade, N., 2017, Human-on-the-loop automation for detecting software side-channel vulnerabilities. – year: 2019 ident: bib35 publication-title: An Introduction to Machine Learning Interpretability – start-page: 66 year: 2019 ident: bib40 article-title: Analysis of financial distress cross countries: Using macroeconomic, industrial indicators and accounting data publication-title: Int. Rev. Financ. Anal. – volume: 33 start-page: 3017 year: 2020 end-page: 3033 ident: bib45 article-title: Revisiting bank failure in the United States: a fuzzy-set analysis publication-title: Econ. Res. -Èkon. Istraz. – year: 2020 ident: bib50 article-title: Characteristics of consulting firms associated with the diffusion of big data analytics publication-title: J. Asian Bus. Econ. Stud., Ahead--Print. (Ahead--Print. ) – volume: 22 start-page: 1366 year: 2017 end-page: 1422 ident: bib38 article-title: Corporate bankruptcy prediction: a high dimensional analysis publication-title: Rev. Account. Stud. – volume: 27 start-page: 333 year: 2012 end-page: 342 ident: bib56 article-title: Simple instance selection for bankruptcy prediction publication-title: Knowl. -Based Syst. – volume: 42 start-page: 64 year: 2015 end-page: 75 ident: bib47 article-title: Performance evaluation of bankruptcy prediction models: An orientation-free super-efficiency DEA-based framework publication-title: Int. Rev. Financ. Anal. – year: 2021 ident: bib5 publication-title: Explan. Model Anal. – reference: Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H.,. Zhou, T. (2019). xgboost: Extreme gradient boosting. R package version 0.90. 0.2. In. – volume: 45 start-page: 63 year: 2016 end-page: 91 ident: bib44 article-title: La Predicción Del Fracaso Bancario Con La Metodología “Boosting Classification Tree” publication-title: Rev. Esp. De. Financ. Y. Contab. – reference: Cran.r-project.org. (2020). Introducing Correlation Funnel - Customer Churn Example. Retrieved from – reference: Friedman, J., Hastie, T., & Tibshirani, R., 2000, Additive logistic regression: A statistical view of boosting. In (Vol. 28, pp. 337–407). – start-page: 166 year: 2021 ident: bib37 article-title: CatBoost model and artificial intelligence techniques for corporate failure prediction publication-title: Technol. Forecast. Soc. Change – year: 2016 ident: bib7 article-title: Risk Management in Emerging Markets: Issues, Framework, and Modeling – year: 1997 ident: bib16 publication-title: Art of Managing Finance – volume: 29 start-page: 1189 year: 2001 end-page: 1232 ident: bib30 article-title: Greedy function approximation: A gradient boosting machine publication-title: Ann. Stat. – year: 2020 ident: bib6 article-title: Hands-On Machine Learning with R – reference: Chen, T., & Guestrin, C., 2016, XGBoost: A scalable tree boosting system. – volume: 38 start-page: 367 year: 2002 end-page: 378 ident: bib31 article-title: Stochastic gradient boosting publication-title: Comput. Stat. Data Anal. – start-page: 42 year: 2017 ident: bib39 article-title: Stock liquidity and SMEs’ likelihood of bankruptcy: Evidence from the US market publication-title: Res. Int. Bus. Financ. – volume: 11 year: 2021 ident: bib27 article-title: Blockchain, enterprise resource planning (ERP) and accounting information systems (AIS): Research on e-procurement and system integration publication-title: Appl. Sci. (Switz. ) – volume: 69 start-page: 135 year: 2018 end-page: 146 ident: bib54 article-title: Waiting for a sales renaissance in the fourth industrial revolution: Machine learning and artificial intelligence in sales research and practice publication-title: Ind. Mark. Manag. – start-page: 1 year: 2017 end-page: 13 ident: bib17 article-title: A Roadmap for a Rigorous Science of Interpretability publication-title: arXiv Prepr. arXiv:1702. 08608v1 – volume: 21 year: 2020 ident: bib46 article-title: Digital systems and new challenges of financial management – fintech, XBRL, blockchain and cryptocurrencies publication-title: Qual. - Access Success – volume: 47 start-page: 507 year: 2018 end-page: 532 ident: bib8 article-title: Analysis of the algorithm Gradient Boosting Machine (GBM) in business failure prediction publication-title: Rev. Esp. De. Financ. Y. Contab. – volume: 33 start-page: 3580 year: 2020 end-page: 3603 ident: bib21 article-title: The effect of the board on corporate social responsibility: bibliometric and social network analysis publication-title: Econ. Res. -Èkon. Istraz. – start-page: 56 year: 2020 ident: bib57 article-title: Shapley additive explanations for NO2 forecasting publication-title: Ecol. Inform. – volume: 7 start-page: 21 year: 2013 ident: bib49 article-title: Gradient boosting machines, a tutorial publication-title: Front. Neurorobotics – volume: 59 start-page: 58 year: 2018 end-page: 76 ident: bib23 article-title: Business failure, efficiency, and volatility: Evidence from the European insurance industry publication-title: Int. Rev. Financ. Anal. – volume: 13 year: 2021 ident: bib26 article-title: Mandatory esg reporting and xbrl taxonomies combination: Esg ratings and income statement, a sustainable value-added disclosure publication-title: Sustain. (Switz. ) – volume: 83 year: 2013 ident: bib25 article-title: Prediction of bankruptcy using support vector machines: An application to bank bankruptcy publication-title: J. Stat. Comput. Simul. – volume: 37 start-page: 13 year: 2008 end-page: 32 ident: bib14 article-title: FIAMM return persistence analysis and the determinants of the fees charged publication-title: Span. J. Financ. Account. / Rev. Esp. De. Financ. Y. Contab. – year: 2021 ident: bib22 article-title: Corporate governance and corporate social responsibility: mapping the most critical drivers in the board academic literature publication-title: Meditari Account. Res. – start-page: 20 year: 2018 ident: bib28 article-title: Model Class Reliance: Variable Importance Measures for any Machine Learning Model Class, from the “Rashomon” Perspective publication-title: J. Mach. Learn. Res. – volume: 19 start-page: 1 year: 2018 end-page: 5 ident: bib4 article-title: Dalex: Explainers for complex predictive models in R publication-title: J. Mach. Learn. Res. – volume: 101 start-page: 885 year: 2019 end-page: 896 ident: bib13 article-title: Anticipating bank distress in the Eurozone: An Extreme Gradient Boosting approach publication-title: J. Bus. Res. – reference: Foster, D., 2017, NEW R package that makes XGBoost interpretable. Retrieved from 〈https://medium.com/applied-data-science/new-r-package-the-xgboost-explainer-51dd7d1aa211〉. – volume: 45 start-page: 110 year: 2008 end-page: 122 ident: bib1 article-title: Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks publication-title: Decis. Support Syst. – year: 2021 ident: bib18 article-title: Assessing machine learning for forecasting economic risk: Evidence from an expanded Chinese financial information set publication-title: Financ. Res. Lett. – volume: 15 start-page: 489 year: 2020 end-page: 501 ident: bib51 article-title: The rise of artificial intelligence and robots in the 4th Industrial Revolution: implications for future South African job creation publication-title: Contemp. Soc. Sci. – volume: 78 start-page: 225 year: 2017 end-page: 241 ident: bib58 article-title: A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring publication-title: Expert Syst. Appl. – volume: Vol. 8 year: 2019 ident: bib10 publication-title: Mach. Learn. Interpret.: A Surv. Methods Metr. – volume: 61 start-page: 304 year: 2019 end-page: 323 ident: bib9 article-title: Predicting failure in the US banking sector: An extreme gradient boosting approach publication-title: Int. Rev. Econ. Financ. – volume: 59 start-page: 226 year: 2016 end-page: 234 ident: bib41 article-title: Optimization of cluster-based evolutionary undersampling for the artificial neural networks in corporate bankruptcy prediction publication-title: Expert Syst. Appl. – volume: 50 start-page: 67 year: 2017 end-page: 80 ident: bib48 article-title: Financial distress prediction: The case of French small and medium-sized firms publication-title: Int. Rev. Financ. Anal. – start-page: 51 year: 2017 ident: bib55 article-title: Financial ratios and bankruptcy predictions: An international evidence publication-title: Int. Rev. Econ. Financ. – volume: 58 start-page: 93 year: 2016 end-page: 101 ident: bib60 article-title: Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction publication-title: Expert Syst. Appl. – start-page: 44 year: 2018 ident: bib42 article-title: Predicting bank failure: An improvement by implementing a machine-learning approach to classical financial ratios publication-title: Res. Int. Bus. Financ. – volume: 254 start-page: 236 year: 2016 end-page: 252 ident: bib19 article-title: A two-stage classification technique for bankruptcy prediction publication-title: Eur. J. Oper. Res. – volume: 23 start-page: 589 year: 1968 end-page: 609 ident: bib2 publication-title: Financ. Ratios, Discrim. Anal. Predict. Corp. Bankruptcy – reference: . – volume: 75 start-page: 25 year: 2017 end-page: 43 ident: bib20 article-title: Dynamics of firm financial evolution and bankruptcy prediction publication-title: Expert Syst. Appl. – reference: Elith, J., Leathwick, J.R., & Hastie, T., 2008, A working guide to boosted regression trees. In (Vol. 77, pp. 802–813). – start-page: 117 year: 2019 ident: bib36 article-title: Bankruptcy prediction using imaged financial ratios and convolutional neural networks publication-title: Expert Syst. Appl. – volume: 2 start-page: 5 year: 1993 end-page: 27 ident: bib3 article-title: Small Business Failure and Bankruptcy: What Progress Has Been Made in a Decade? publication-title: Small Enterp. Res. – start-page: 52 year: 2020 ident: bib53 article-title: Systemic risk, economic policy uncertainty and firm bankruptcies: Evidence from multivariate causal inference publication-title: Res. Int. Bus. Financ. – volume: 33 start-page: 3580 issue: 1 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib21 article-title: The effect of the board on corporate social responsibility: bibliometric and social network analysis publication-title: Econ. Res. -Èkon. Istraz. – start-page: 166 year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib37 article-title: CatBoost model and artificial intelligence techniques for corporate failure prediction publication-title: Technol. Forecast. Soc. Change – volume: 128 start-page: 93 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib59 article-title: Predicting the listing statuses of Chinese-listed companies using decision trees combined with an improved filter feature selection method publication-title: Knowl. -Based Syst. doi: 10.1016/j.knosys.2017.05.003 – volume: 47 start-page: 507 issue: 4 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib8 article-title: Analysis of the algorithm Gradient Boosting Machine (GBM) in business failure prediction publication-title: Rev. Esp. De. Financ. Y. Contab. – start-page: 1 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib34 article-title: Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning publication-title: arXiv:1806. 00069 – volume: 11 issue: 15 year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib27 article-title: Blockchain, enterprise resource planning (ERP) and accounting information systems (AIS): Research on e-procurement and system integration publication-title: Appl. Sci. (Switz. ) – volume: 42 start-page: 64 year: 2015 ident: 10.1016/j.ribaf.2022.101649_bib47 article-title: Performance evaluation of bankruptcy prediction models: An orientation-free super-efficiency DEA-based framework publication-title: Int. Rev. Financ. Anal. doi: 10.1016/j.irfa.2015.01.006 – volume: 7 start-page: 21 year: 2013 ident: 10.1016/j.ribaf.2022.101649_bib49 article-title: Gradient boosting machines, a tutorial publication-title: Front. Neurorobotics doi: 10.3389/fnbot.2013.00021 – volume: Vol. 8 year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib10 publication-title: Mach. Learn. Interpret.: A Surv. Methods Metr. – year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib18 article-title: Assessing machine learning for forecasting economic risk: Evidence from an expanded Chinese financial information set publication-title: Financ. Res. Lett. – volume: 69 start-page: 135 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib54 article-title: Waiting for a sales renaissance in the fourth industrial revolution: Machine learning and artificial intelligence in sales research and practice publication-title: Ind. Mark. Manag. doi: 10.1016/j.indmarman.2017.12.019 – year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib22 article-title: Corporate governance and corporate social responsibility: mapping the most critical drivers in the board academic literature publication-title: Meditari Account. Res. – volume: 101 start-page: 885 year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib13 article-title: Anticipating bank distress in the Eurozone: An Extreme Gradient Boosting approach publication-title: J. Bus. Res. doi: 10.1016/j.jbusres.2018.11.015 – start-page: 42 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib39 article-title: Stock liquidity and SMEs’ likelihood of bankruptcy: Evidence from the US market publication-title: Res. Int. Bus. Financ. – volume: 59 start-page: 58 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib23 article-title: Business failure, efficiency, and volatility: Evidence from the European insurance industry publication-title: Int. Rev. Financ. Anal. doi: 10.1016/j.irfa.2018.07.007 – start-page: 117 year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib36 article-title: Bankruptcy prediction using imaged financial ratios and convolutional neural networks publication-title: Expert Syst. Appl. – start-page: 44 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib42 article-title: Predicting bank failure: An improvement by implementing a machine-learning approach to classical financial ratios publication-title: Res. Int. Bus. Financ. – volume: 29 start-page: 1189 issue: 5 year: 2001 ident: 10.1016/j.ribaf.2022.101649_bib30 article-title: Greedy function approximation: A gradient boosting machine publication-title: Ann. Stat. doi: 10.1214/aos/1013203451 – ident: 10.1016/j.ribaf.2022.101649_bib12 – year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib33 article-title: Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis publication-title: J. Behav. Exp. Financ. doi: 10.1016/j.jbef.2021.100577 – volume: 37 start-page: 13 issue: 137 year: 2008 ident: 10.1016/j.ribaf.2022.101649_bib14 article-title: FIAMM return persistence analysis and the determinants of the fees charged publication-title: Span. J. Financ. Account. / Rev. Esp. De. Financ. Y. Contab. – volume: 23 start-page: 589 issue: 4 year: 1968 ident: 10.1016/j.ribaf.2022.101649_bib2 publication-title: Financ. Ratios, Discrim. Anal. Predict. Corp. Bankruptcy – volume: 75 start-page: 25 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib20 article-title: Dynamics of firm financial evolution and bankruptcy prediction publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2017.01.016 – start-page: 20 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib28 article-title: Model Class Reliance: Variable Importance Measures for any Machine Learning Model Class, from the “Rashomon” Perspective publication-title: J. Mach. Learn. Res. – start-page: 56 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib57 article-title: Shapley additive explanations for NO2 forecasting publication-title: Ecol. Inform. – start-page: 51 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib55 article-title: Financial ratios and bankruptcy predictions: An international evidence publication-title: Int. Rev. Econ. Financ. – year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib35 – volume: 33 start-page: 3017 issue: 1 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib45 article-title: Revisiting bank failure in the United States: a fuzzy-set analysis publication-title: Econ. Res. -Èkon. Istraz. – year: 2016 ident: 10.1016/j.ribaf.2022.101649_bib7 – start-page: 66 year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib40 article-title: Analysis of financial distress cross countries: Using macroeconomic, industrial indicators and accounting data publication-title: Int. Rev. Financ. Anal. – ident: 10.1016/j.ribaf.2022.101649_bib11 doi: 10.1145/2939672.2939785 – start-page: 52 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib53 article-title: Systemic risk, economic policy uncertainty and firm bankruptcies: Evidence from multivariate causal inference publication-title: Res. Int. Bus. Financ. – volume: 21 issue: 174 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib46 article-title: Digital systems and new challenges of financial management – fintech, XBRL, blockchain and cryptocurrencies publication-title: Qual. - Access Success – year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib5 publication-title: Explan. Model Anal. doi: 10.1201/9780429027192 – volume: 45 start-page: 110 issue: 1 year: 2008 ident: 10.1016/j.ribaf.2022.101649_bib1 article-title: Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks publication-title: Decis. Support Syst. doi: 10.1016/j.dss.2007.12.002 – volume: 58 start-page: 93 year: 2016 ident: 10.1016/j.ribaf.2022.101649_bib60 article-title: Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2016.04.001 – ident: 10.1016/j.ribaf.2022.101649_bib52 doi: 10.1007/978-3-319-72598-7_13 – volume: 83 issue: 8 year: 2013 ident: 10.1016/j.ribaf.2022.101649_bib25 article-title: Prediction of bankruptcy using support vector machines: An application to bank bankruptcy publication-title: J. Stat. Comput. Simul. doi: 10.1080/00949655.2012.666550 – ident: 10.1016/j.ribaf.2022.101649_bib32 doi: 10.1214/aos/1016120463 – year: 1997 ident: 10.1016/j.ribaf.2022.101649_bib16 – volume: 22 start-page: 1366 issue: 3 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib38 article-title: Corporate bankruptcy prediction: a high dimensional analysis publication-title: Rev. Account. Stud. doi: 10.1007/s11142-017-9407-1 – volume: 27 start-page: 333 year: 2012 ident: 10.1016/j.ribaf.2022.101649_bib56 article-title: Simple instance selection for bankruptcy prediction publication-title: Knowl. -Based Syst. doi: 10.1016/j.knosys.2011.09.017 – ident: 10.1016/j.ribaf.2022.101649_bib24 doi: 10.1111/j.1365-2656.2008.01390.x – start-page: 1 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib17 article-title: A Roadmap for a Rigorous Science of Interpretability publication-title: arXiv Prepr. arXiv:1702. 08608v1 – volume: 78 start-page: 225 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib58 article-title: A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2017.02.017 – year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib6 – volume: 15 start-page: 489 issue: 4 year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib51 article-title: The rise of artificial intelligence and robots in the 4th Industrial Revolution: implications for future South African job creation publication-title: Contemp. Soc. Sci. doi: 10.1080/21582041.2020.1806346 – volume: 2 start-page: 5 issue: 1–2 year: 1993 ident: 10.1016/j.ribaf.2022.101649_bib3 article-title: Small Business Failure and Bankruptcy: What Progress Has Been Made in a Decade? publication-title: Small Enterp. Res. doi: 10.5172/ser.2.1-2.5 – ident: 10.1016/j.ribaf.2022.101649_bib29 – volume: 59 start-page: 226 year: 2016 ident: 10.1016/j.ribaf.2022.101649_bib41 article-title: Optimization of cluster-based evolutionary undersampling for the artificial neural networks in corporate bankruptcy prediction publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2016.04.027 – volume: 61 start-page: 304 year: 2019 ident: 10.1016/j.ribaf.2022.101649_bib9 article-title: Predicting failure in the US banking sector: An extreme gradient boosting approach publication-title: Int. Rev. Econ. Financ. doi: 10.1016/j.iref.2018.03.008 – volume: 254 start-page: 236 issue: 1 year: 2016 ident: 10.1016/j.ribaf.2022.101649_bib19 article-title: A two-stage classification technique for bankruptcy prediction publication-title: Eur. J. Oper. Res. doi: 10.1016/j.ejor.2016.03.008 – volume: 40 start-page: 2941 issue: 8 year: 2013 ident: 10.1016/j.ribaf.2022.101649_bib43 article-title: A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2012.12.009 – volume: 50 start-page: 67 year: 2017 ident: 10.1016/j.ribaf.2022.101649_bib48 article-title: Financial distress prediction: The case of French small and medium-sized firms publication-title: Int. Rev. Financ. Anal. doi: 10.1016/j.irfa.2017.02.004 – volume: 38 start-page: 367 issue: 4 year: 2002 ident: 10.1016/j.ribaf.2022.101649_bib31 article-title: Stochastic gradient boosting publication-title: Comput. Stat. Data Anal. doi: 10.1016/S0167-9473(01)00065-2 – ident: 10.1016/j.ribaf.2022.101649_bib15 – volume: 19 start-page: 1 issue: 84 year: 2018 ident: 10.1016/j.ribaf.2022.101649_bib4 article-title: Dalex: Explainers for complex predictive models in R publication-title: J. Mach. Learn. Res. – volume: 45 start-page: 63 issue: 1 year: 2016 ident: 10.1016/j.ribaf.2022.101649_bib44 article-title: La Predicción Del Fracaso Bancario Con La Metodología “Boosting Classification Tree” publication-title: Rev. Esp. De. Financ. Y. Contab. – year: 2020 ident: 10.1016/j.ribaf.2022.101649_bib50 article-title: Characteristics of consulting firms associated with the diffusion of big data analytics publication-title: J. Asian Bus. Econ. Stud., Ahead--Print. (Ahead--Print. ) – volume: 13 issue: 16 year: 2021 ident: 10.1016/j.ribaf.2022.101649_bib26 article-title: Mandatory esg reporting and xbrl taxonomies combination: Esg ratings and income statement, a sustainable value-added disclosure publication-title: Sustain. (Switz. ) |
| SSID | ssj0029012 |
| Score | 2.4712517 |
| Snippet | This study opens the black boxes and fills the literature gap by showing how it is possible to fit a very precise Machine Learning model that is highly... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 101649 |
| SubjectTerms | Business failure Machine learning Model interpretability XGBoost |
| Title | No more black boxes! Explaining the predictions of a machine learning XGBoost classifier algorithm in business failure |
| URI | https://dx.doi.org/10.1016/j.ribaf.2022.101649 |
| Volume | 61 |
| WOSCitedRecordID | wos000805435500019&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: ScienceDirect Freedom Collection 2021 customDbUrl: eissn: 1878-3384 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0029012 issn: 0275-5319 databaseCode: AIEXJ dateStart: 20040401 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWLUJcEE9RCshI3EKqxEnq5Fiq8pJYcSjSiks0frUpaVKl6XZ_Cj8XO7G9W4pW9MAlWmVtx8p8mcxMPn9G6C0FAomMi5CJWISpUizMi0iFUaQIcEoNTWfYbILOZvl8XnybTH65tTCLmjZNvlwW5__V1PqcNrZZOnsLc_tB9Qn9WxtdH7XZ9fGfDD9rA0OeDZgpzQWsXRpHEBtN43rcDcKujjJfaDwNDoKzgVUp3TYSx8H84_u2vegDbuLrSplVKVAft13Vn5yZKglzlHkFVW11SVyY6_h8pl11reboe5mCvRrkPjy0DqDTdwlG2rDoWh9kX8mfMMoj1Ib_5PH8VcMbrgY-wg-dj8N6CUNnv44M5zwdoVlonMG6Wx412q1fNTWGUdr0hssfqw-nu13FwGiyErK7an1dYPuPF5-nIzqm22k5DFKaQcpxkDtoS0-uyKdoa__z4fyLT-Z1HDV8oXJTd4pWA3fwxlz-HvWsRTJHD9EDm4Lg_RE6j9BENo_RPbcC4glazFpsEIQHBOEBQW_wCj9Y4wev4Qe3CgO2-MEOP9jiB6_wgz1-cNVghwRs8fMUff9weHTwKbTbc4Rch3l9WKSSFiRO9rgEQpWiSqQxpSISkKlEpULnrhy4LBKWCx2XiwSAEc4FpDzKIE6eoWnTNvI5wjzl-p9MAMtlykzWFxFFcgWRzLI8KrYRcbev5Fa73myhUpcbTLeN3vlO56N0y-bme84upY0-x6iy1Ejb1PHF7a6zg-6vnoGXaNp3l_IVussXfXXRvbYw-w2luavg |
| 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=No+more+black+boxes%21+Explaining+the+predictions+of+a+machine+learning+XGBoost+classifier+algorithm+in+business+failure&rft.jtitle=Research+in+international+business+and+finance&rft.au=Carmona%2C+Pedro&rft.au=Dwekat%2C+Aladdin&rft.au=Mardawi%2C+Zeena&rft.date=2022-10-01&rft.issn=0275-5319&rft.volume=61&rft.spage=101649&rft_id=info:doi/10.1016%2Fj.ribaf.2022.101649&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ribaf_2022_101649 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0275-5319&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0275-5319&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0275-5319&client=summon |