{"id":18392,"date":"2026-09-09T12:33:44","date_gmt":"2026-09-09T11:33:44","guid":{"rendered":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/?p=18392"},"modified":"2026-09-09T12:33:44","modified_gmt":"2026-09-09T11:33:44","slug":"finance-research-seminar-professor-yizhe-dong","status":"publish","type":"post","link":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/2026\/09\/09\/finance-research-seminar-professor-yizhe-dong\/","title":{"rendered":"Finance Research Seminar \u2013 Professor Yizhe Dong"},"content":{"rendered":"<p><strong>Title<\/strong>: Predicting from Heterogeneous Texts: A Source-preserving Prompt-based Approach<\/p>\n<p><strong>Date<\/strong>: 19 November 2026<\/p>\n<p><strong>Time<\/strong>: 13:30 to 15:30<\/p>\n<p><strong>Venue: <\/strong>NUBS.4.06<\/p>\n<p>If you would like to attend, please register using the following link<\/p>\n<p><a href=\"https:\/\/forms.cloud.microsoft\/pages\/responsepage.aspx?id=yRJQnBa2wkSpF2aBT74-hz-fP_3f-FxPhH06AeweumxUMDdDNzZHWDVOTEIzTzBJV0dMTTEzNTdDVCQlQCNjPTEu&amp;route=shorturl&amp;OR=EXCEL-WEB.BODY.NT&amp;CT=1788951884897\">Predicting from Heterogeneous Texts: A Source-preserving Prompt-based Approach<\/a><\/p>\n<p><strong>Speaker<\/strong><strong>: <\/strong>Professor Yizhe Dong, University of Edinburgh<\/p>\n<p><a href=\"https:\/\/www.research.ed.ac.uk\/en\/persons\/yizhe-dong\/\">Yizhe Dong &#8211; University of Edinburgh Research Explorer<\/a><\/p>\n<p><strong>Abstract<\/strong>:<\/p>\n<p>Textual data used in decision-making is often produced by multiple agents with distinct informational roles and incentives. Existing approaches typically either analyze each text source in isolation or combine heterogeneous texts into shared representations that obscure source-specific meaning and reduce interpretability. We propose a source-preserving, prompt-based framework that converts each text source independently into an interpretable propensity score using cloze-style masked language modeling. We apply the framework to a unique dataset of micro and small enterprise loans containing 15 heterogeneous text variables. Across off-the-shelf and fine-tuned settings, our approach consistently outperforms structured variable-only models and established natural language processing benchmarks. We find that loan officer narratives contain greater predictive information than borrower self-reports, with direct implications for how lenders collect and weight soft information. Profit analysis shows that the predictive gains translate into economically meaningful improvements in lending decisions. These findings contribute to the literature on text-based financial decision-making by showing how heterogeneous narratives can be integrated without collapsing their source-specific information, and by providing an interpretable design for high-stakes predictive analytics.<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Title: Predicting from Heterogeneous Texts: A Source-preserving Prompt-based Approach Date: 19 November 2026 Time: 13:30 to 15:30 Venue: NUBS.4.06 If you would like to attend,&#8230; <br \/><a href=\"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/2026\/09\/09\/finance-research-seminar-professor-yizhe-dong\/\" rel=\"bookmark\"><strong>Read more<\/strong><\/a><\/p>\n","protected":false},"author":11659,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[6],"tags":[47,1038,210],"class_list":["post-18392","post","type-post","status-publish","format-standard","hentry","category-research","tag-finance","tag-finance-research-seminar","tag-research-seminar"],"acf":[],"_links":{"self":[{"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/posts\/18392","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/users\/11659"}],"replies":[{"embeddable":true,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/comments?post=18392"}],"version-history":[{"count":1,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/posts\/18392\/revisions"}],"predecessor-version":[{"id":18393,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/posts\/18392\/revisions\/18393"}],"wp:attachment":[{"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/media?parent=18392"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/categories?post=18392"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/microsites.ncl.ac.uk\/nubsstaffblog\/wp-json\/wp\/v2\/tags?post=18392"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}