[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122685-en":3,"doc-seo-122685-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122685,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine learning in bank merger prediction - A text-based approach","This paper investigates the role of textual information in a U.S. bank merger prediction task. The approach retrieves text from bank annual reports using 9,207 bank-year observations from 1994–2016. Several machine learning models are trained using textual information together with financial variables to predict bidders and targets. Results show substantially improved performance when both input types are used, with text benefits especially evident for predicting future bidders.","Machine learning in bank merger prediction:  \nA text-based approach  \nby  \nApostolos G. Katsafados1, George N. Leledakis1*, Emmanouil G. Pyrgiotakis2, Ion Androutsopoulos3, Manos Fergadiotis3  \n1 Department of Accounting and Finance, School of Business, Athens University of Economics and Business, Greece  \n2 Essex Business School, University of Essex, U.K.  \n3 Department of Informatics, School of Information Sciences and Technology, Athens University of Economics and Business, Greece  \nAbstract  \nThis paper investigates the role of textual information in a U.S. bank merger prediction task. Our intuition behind this approach is that text could reduce bank opacity and allow us to understand better the strategic options of banking firms. We retrieve textual information from bank annual reports using a sample of 9,207 U.S. bank-year observations during the period 1994-2016. To predict bidders and targets, we use textual information along with financial variables as inputs to several machine learning models. We find that when we jointly use textual information and financial variables as inputs, the performance of our models is substantially improved compared to models using a single type of input. Furthermore, we find that the performance improvement due to the inclusion of text is more noticeable in predicting future bidders, a task which is less explored in the relevant literature. Therefore, our findings highlight the importance of textual information in a bank merger prediction task.  \nJEL classification: C63, G14, G21, G34, G40  \nKeywords: Finance; Bank merger prediction; Textual analysis; Natural language processing; Machine learning  \nThis version: June, 2023  \n*  \nCorresponding author: Department of Accounting and Finance, School of Business, Athens University of Economics and Business, 76 Patission Str., 104 34, Athens, Greece; Tel.: +30 210 8203459. E-mail addresses: [katsafados@aueb.gr](katsafados@aueb.gr) (A.  \nKatsafados), [gleledak@aueb.gr](gleledak@aueb.gr) (G. Leledakis), [e.pyrgiotakis@essex.ac.uk](e.pyrgiotakis@essex.ac.uk) (E. Pyrgiotakis), [ion@aueb.gr](ion@aueb.gr) (I. Androutsopoulos),  \n[fergadiotis@aueb.gr](fergadiotis@aueb.gr) (M. Fergadiotis). We would like to thank Ilias Chalkidis, Nikolaos Gkoumas, Prodromos Malakasiotis, Thanos Verousis, and the participants at the Annual Event of Finance Research Letters 2022 CEMLA Conference: New Advancesin International Finance for their valuable comments and suggestions. Apostolos Katsafados acknowledges financial support cofinanced by Greece and the European Union (European Social Fund-ESF) through the Operational Programme «Human Resources Development, Education and Lifelong Learning» in the context of the project “Strengthening Human Resources Research Potential via Doctorate Research” (MIS-5000432), implemented by the State Scholarships Foundation (ΙΚΥ) . George Leledakis greatly acknowledges financial support received from the Research Center ofthe Athens University of Economics and Business (EP-2256- 01) . All remaining errors and omissions are our own.  \n1. Introduction  \nOver the last decades, the U.S. banking industry has experienced a severe wave of consolidation through mergersand acquisitions (M&A) . Aligned with this trend, the academic literature has given increased attention to the topic of bank M&As. The vast majority of the literature focuses on investigating the shareholder wealth effects around the announcement of bank mergers (Houston et al., 2001; DeLong and DeYoung, 2007; Filson and Olfati, 2014; Leledakisand Pyrgiotakis, 2022), while other studies analyze the merger-related performance changes (Cornett and Tehranian, 1992; Cornett et al., 2006), or the efficiency effects (Rhoades 1993; 1998) .  \nAnother strand of the literature attempts to identify the characteristics of merging U.S. banks, especially from the perspective of the target (Prasad and Melnyk, 1991; Wheelock and Wilson, 2000) . These studies report that smaller, less profitable, an","cbCairHcTo537cgG","https://ap.wps.com/l/cbCairHcTo537cgG","pdf",1330702,1,31,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What is the main focus of the paper?\",\"answer\":\"The paper studies how textual information from bank annual reports affects predictions in a U.S. bank merger prediction task.\"},{\"question\":\"How is textual data collected and what dataset is used?\",\"answer\":\"Textual information is retrieved from bank annual reports, using 9,207 U.S. bank-year observations covering 1994–2016.\"},{\"question\":\"What is the key finding about combining text and financial variables?\",\"answer\":\"Jointly using textual information and financial variables substantially improves model performance compared with using either type alone, especially for predicting future bidders.\"}]","Machine learning in bank merger prediction - A text-based approach | PDF",1785812180,78,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-in-bank-merger-prediction-a-text-based-approach","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-in-bank-merger-prediction-a-text-based-approach/122685/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main focus of the paper?","Question",{"text":75,"@type":76},"The paper studies how textual information from bank annual reports affects predictions in a U.S. bank merger prediction task.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is textual data collected and what dataset is used?",{"text":80,"@type":76},"Textual information is retrieved from bank annual reports, using 9,207 U.S. bank-year observations covering 1994–2016.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the key finding about combining text and financial variables?",{"text":84,"@type":76},"Jointly using textual information and financial variables substantially improves model performance compared with using either type alone, especially for predicting future bidders.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]