{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/112947"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/112947","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Machine learning and information-theoretic approaches for financial applications","abstract":"Firm-specific information contributes to resource allocation in capital markets. The prediction and inference of future firm-specific information are often critical factors that can lead to a prosperous economy. Machine Learning and Information Theory offer new, alternative methods to aid in the prediction and inference of future firm-specific information. Thus, we explore approaches from machine learning and information theory to improve existing research areas in accounting and finance. In Chapter 2, we utilized random forest trees to predict the annual direction of profitability for firms with a minimal amount of information. We demonstrate that we can out-perform benchmark models typically used in financial accounting research. Major public firms announce their annual earnings during the first quarter of the year. The embedding information in these announcements effects the announcing firm and is transferred to or incorporated by other firms. Existing literature in finance and accounting focuses on measuring information transfers as effects stemming from firm-specific information releases. In Chapter 3, we discuss a solution to estimate information transfer via transfer entropy between random processes. We show that our solution to estimate information transfer scales better with data set size and is up to 1,072 times faster than all existing, open source solutions for large datasets. In Chapter 4, we present an alternative approach to estimate information transfer between firms centered around earnings announcements. We show that information transfer between firms is stronger for firms on days with unexpected earnings news. We also demonstrate that communities of firms significantly differ depending on the presence of earnings releases.","abstract_html":"Firm-specific information contributes to resource allocation in capital markets. The prediction and inference of future firm-specific information are often critical factors that can lead to a prosperous economy. Machine Learning and Information Theory offer new, alternative methods to aid in the prediction and inference of future firm-specific information. Thus, we explore approaches from machine learning and information theory to improve existing research areas in accounting and finance. In Chapter 2, we utilized random forest trees to predict the annual direction of profitability for firms with a minimal amount of information. We demonstrate that we can out-perform benchmark models typically used in financial accounting research. Major public firms announce their annual earnings during the first quarter of the year. The embedding information in these announcements effects the announcing firm and is transferred to or incorporated by other firms. Existing literature in finance and accounting focuses on measuring information transfers as effects stemming from firm-specific information releases. In Chapter 3, we discuss a solution to estimate information transfer via transfer entropy between random processes. We show that our solution to estimate information transfer scales better with data set size and is up to 1,072 times faster than all existing, open source solutions for large datasets. In Chapter 4, we present an alternative approach to estimate information transfer between firms centered around earnings announcements. We show that information transfer between firms is stronger for firms on days with unexpected earnings news. We also demonstrate that communities of firms significantly differ depending on the presence of earnings releases.","abstract_has_math":false,"creators":["Ikegwu, Kelechi Moise"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Informatics","degree_department":null,"school":null,"contributors":["Brunner, Robert","Sougiannis, Theodore","McMullin, Jeff","Yun, Joseph"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T21:40:28Z","date_published":"2022-01-12T21:40:28Z","updated_at":"2026-07-22T22:24:52Z","subjects":["Machine Learning","Information Theory","Random Walk","Network Science","Finance","Accounting","Financial Accounting"],"languages":["en"],"rights":["Copyright 2021 Kelechi Ikegwu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/112947","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Brunner, Robert","Sougiannis, Theodore","McMullin, Jeff","Yun, Joseph"]},{"key":"dc:creator","label":"Author","values":["Ikegwu, Kelechi Moise"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T21:40:28Z","2021-05-14","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Informatics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Information Theory","Random Walk","Network Science","Finance","Accounting","Financial Accounting"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Kelechi Ikegwu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/112947"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Firm-specific information contributes to resource allocation in capital markets. The prediction and inference of future firm-specific information are often critical factors that can lead to a prosperous economy. Machine Learning and Information Theory offer new, alternative methods to aid in the prediction and inference of future firm-specific information. Thus, we explore approaches from machine learning and information theory to improve existing research areas in accounting and finance. In Chapter 2, we utilized random forest trees to predict the annual direction of profitability for firms with a minimal amount of information. We demonstrate that we can out-perform benchmark models typically used in financial accounting research. Major public firms announce their annual earnings during the first quarter of the year. The embedding information in these announcements effects the announcing firm and is transferred to or incorporated by other firms. Existing literature in finance and accounting focuses on measuring information transfers as effects stemming from firm-specific information releases. In Chapter 3, we discuss a solution to estimate information transfer via transfer entropy between random processes. We show that our solution to estimate information transfer scales better with data set size and is up to 1,072 times faster than all existing, open source solutions for large datasets. In Chapter 4, we present an alternative approach to estimate information transfer between firms centered around earnings announcements. We show that information transfer between firms is stronger for firms on days with unexpected earnings news. We also demonstrate that communities of firms significantly differ depending on the presence of earnings releases.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Kelechi Ikegwu, accepted the attached license on 2021-05-13 at 10:59.","The student, Kelechi Ikegwu, submitted this Dissertation for approval on 2021-05-13 at 11:34.","This Dissertation was approved for publication on 2021-05-14 at 14:39.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16644 on 2022-01-12 at 12:42:29","Made available in DSpace on 2022-01-12T21:40:28Z (GMT). No. of bitstreams: 3 IKEGWU-DISSERTATION-2021.pdf: 6769972 bytes, checksum: 4f4fae79d54267f574f223ac3d8c6f47 (MD5) LICENSE.txt: 4211 bytes, checksum: fb71436cb7843c39158cbfa0e0ef8586 (MD5) PROQUEST_LICENSE.txt: 4557 bytes, checksum: d1ae4b060386bd9cf0ec742445cd2cc4 (MD5) Previous issue date: 2021-05-14"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Machine learning and information-theoretic approaches for financial applications"]}]}],"canonical_facts":{"dc:contributor":["Brunner, Robert","Sougiannis, Theodore","McMullin, Jeff","Yun, Joseph"],"dc:creator":["Ikegwu, Kelechi Moise"],"dc:date":["2022-01-12T21:40:28Z","2021-05-14","2021-08"],"dc:description":["Firm-specific information contributes to resource allocation in capital markets. The prediction and inference of future firm-specific information are often critical factors that can lead to a prosperous economy. Machine Learning and Information Theory offer new, alternative methods to aid in the prediction and inference of future firm-specific information. Thus, we explore approaches from machine learning and information theory to improve existing research areas in accounting and finance. In Chapter 2, we utilized random forest trees to predict the annual direction of profitability for firms with a minimal amount of information. We demonstrate that we can out-perform benchmark models typically used in financial accounting research. Major public firms announce their annual earnings during the first quarter of the year. The embedding information in these announcements effects the announcing firm and is transferred to or incorporated by other firms. Existing literature in finance and accounting focuses on measuring information transfers as effects stemming from firm-specific information releases. In Chapter 3, we discuss a solution to estimate information transfer via transfer entropy between random processes. We show that our solution to estimate information transfer scales better with data set size and is up to 1,072 times faster than all existing, open source solutions for large datasets. In Chapter 4, we present an alternative approach to estimate information transfer between firms centered around earnings announcements. We show that information transfer between firms is stronger for firms on days with unexpected earnings news. We also demonstrate that communities of firms significantly differ depending on the presence of earnings releases.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Kelechi Ikegwu, accepted the attached license on 2021-05-13 at 10:59.","The student, Kelechi Ikegwu, submitted this Dissertation for approval on 2021-05-13 at 11:34.","This Dissertation was approved for publication on 2021-05-14 at 14:39.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16644 on 2022-01-12 at 12:42:29","Made available in DSpace on 2022-01-12T21:40:28Z (GMT). No. of bitstreams: 3 IKEGWU-DISSERTATION-2021.pdf: 6769972 bytes, checksum: 4f4fae79d54267f574f223ac3d8c6f47 (MD5) LICENSE.txt: 4211 bytes, checksum: fb71436cb7843c39158cbfa0e0ef8586 (MD5) PROQUEST_LICENSE.txt: 4557 bytes, checksum: d1ae4b060386bd9cf0ec742445cd2cc4 (MD5) Previous issue date: 2021-05-14"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/112947"],"dc:language":["en"],"dc:rights":["Copyright 2021 Kelechi Ikegwu"],"dc:subject":["Machine Learning","Information Theory","Random Walk","Network Science","Finance","Accounting","Financial Accounting"],"dc:title":["Machine learning and information-theoretic approaches for financial applications"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Informatics"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:52Z"}