[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125883-en":3,"doc-seo-125883-105":30,"detail-sidebar-cat-0-en-105":92},{"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":11,"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},125883,1099523885336,"Violet","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Investigating Bias in Mortgage-Rate Machine Learning Models - Senior Thesis","Banks and fintech lenders increasingly rely on computer-aided models in lending decisions. Traditional models were interpretable, while modern machine learning models are often opaque and can embed historical inequities found in training data. This thesis calibrates two random forest classifiers using public HMDA loan data and public Fannie Mae performance data, then applies LIME and SHAP to identify feature drivers behind model decisions and preliminary racial-factor impacts.","Dartmouth College  \nDartmouth Digital Commons  \n\n| Computer Science Senior Theses | Computer Science |\n| --- | --- |\n| Spring 5-29-2024\u003Cbr>Investigating Bias in Mortgage-Rate Machine Learning Models\u003Cbr>Will Kalikman\u003Cbr>Dartmouth College, [william.s.kalikman.24@dartmouth.edu](william.s.kalikman.24@dartmouth.edu)\u003Cbr>Follow this and additional works at: [https://digitalcommons.dartmouth.edu/cs_senior_theses](https://digitalcommons.dartmouth.edu/cs_senior_theses)\u003Cbr> Part of the Computer Sciences Commons |  |\n\nRecommended Citation  \nKalikman, Will, \"Investigating Bias in Mortgage-Rate Machine Learning Models\" (2024) . Computer Science Senior Theses. 29.  \n[https://digitalcommons.dartmouth.edu/cs_senior_theses/29](https://digitalcommons.dartmouth.edu/cs_senior_theses/29)  \nThis Thesis (Undergraduate) is brought to you for free and open access by the Computer Science at Dartmouth Digital Commons. It has been accepted for inclusion in Computer Science Senior Theses by an authorized administrator of Dartmouth Digital Commons. For more information, please contact [dartmouthdigitalcommons@groups.dartmouth.edu](dartmouthdigitalcommons@groups.dartmouth.edu).  \nInvestigating Bias in Mortgage-Rate Machine Learning  \nModels  \nWilliam Smith Kalikman∗  \nMay 29, 2024  \nAbstract  \nBanks and fintech lenders increasingly rely on computer-aided models in lending decisions. Traditional models were interpretable: decisions were based on observable factors, such as whether a borrower’s credit score was above a threshold value, and explainable in terms of combinations of these factors. In contrast, modern machine learning models are opaque and non-interpretable. Their opaqueness and reliance on historical data that is the artifact of past racial discrimination means these new models risk embedding and exacerbating such discrimination, even if lenders do not intend to discriminate.  \nWe calibrate two random forest classifiers using publicly available HMDA loan data and publicly available Fannie Mae loan performance data. We use two Explainable Artificial Intelligence (XAI) models, LIME and SHAP, to characterize what features drive the decisions produced by these calibrated ML lending models. Our preliminary findings suggest a significant impact of various racial factors within a model’s decisionmaking process when it has access to such information, as seen in the model trained on HMDA data. These results highlight the need for further investigation to understand and address these influences in depth.  \n1 Introduction  \nRacial discrimination in mortgage lending has deep historical roots, significantly impacting minority homeownership rates in the United States. One of the most egregious examples was the practice of “redlining” that began in the 1930s. This practice involved the Federal Housing Administration (FHA) and private banks creating maps that used red ink to delineate  \n∗ Dartmouth College.  \nareas deemed risky for mortgage lending based on racial composition rather than financial solvency. The residents of these predominantly minority neighborhoods were systematically denied mortgages, which limited their ability to buy homes and accumulate wealth (Hillier (2003)) .  \nThe effects of these discriminatory practices have been long-lasting. Despite the Fair Housing Act of 1968 and the Equal Credit Opportunity Act of 1974, which were designed to eliminate discrimination in lending, disparities persist. Studies have shown that even after controlling for income, credit score, and other financial factors, African-American and Hispanic borrowers are more likely to receive higher interest rates and less favorable loan terms than their White counterparts (Pager and Shepherd (2008)) .  \nA contemporary case exemplifying ongoing challenges is that of Navy Federal Credit Union, the largest credit union in the U.S. , which faced allegations of racial discrimination. Reports revealed that Navy Federal had approved 77% of mortgage applications from White borrower","cbCaiebvDghas2f4","https://ap.wps.com/l/cbCaiebvDghas2f4","pdf",291643,1,15,"English","en",105,"# Abstract\n# Introduction\n## Historical roots of mortgage discrimination\n## Fair lending regulations and persistent disparities\n## Contemporary case of alleged discrimination\n# Methodology\n## Data sources: HMDA and Fannie Mae\n## Calibrated random forest classifiers\n## Explainable AI: LIME and SHAP\n# Preliminary findings\n## Impact of racial factors on decisions","[{\"question\":\"Why can mortgage-rate machine learning models increase discrimination risk?\",\"answer\":\"Because opaque models may learn patterns from historical data shaped by past racial discrimination, potentially embedding and amplifying those biases even when discrimination is not intended.\"},{\"question\":\"What data and modeling approach does the thesis use?\",\"answer\":\"It calibrates two random forest classifiers using publicly available HMDA loan data and publicly available Fannie Mae loan performance datasets to build mortgage-related predictive models.\"},{\"question\":\"How does the thesis interpret what drives the model predictions?\",\"answer\":\"It uses Explainable Artificial Intelligence methods, LIME and SHAP, to characterize which features influence decisions produced by the calibrated machine learning models.\"}]","Investigating Bias in Mortgage-Rate Machine Learning Models - Senior Thesis | PDF",1785901822,38,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"investigating-bias-in-mortgage-rate-machine-learning-models-senior-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@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/investigating-bias-in-mortgage-rate-machine-learning-models-senior-thesis/125883/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why can mortgage-rate machine learning models increase discrimination risk?","Question",{"text":76,"@type":77},"Because opaque models may learn patterns from historical data shaped by past racial discrimination, potentially embedding and amplifying those biases even when discrimination is not intended.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What data and modeling approach does the thesis use?",{"text":81,"@type":77},"It calibrates two random forest classifiers using publicly available HMDA loan data and publicly available Fannie Mae loan performance datasets to build mortgage-related predictive models.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the thesis interpret what drives the model predictions?",{"text":85,"@type":77},"It uses Explainable Artificial Intelligence methods, LIME and SHAP, to characterize which features influence decisions produced by the calibrated machine learning models.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]