{"id":{"repo_id":"regina","oai_identifier":"oai:uregina.scholaris.ca:10294/17130"},"canonical_url":"https://search.dev.ndltd.org/etd/regina/oai:uregina.scholaris.ca:10294/17130","repository":{"repo_id":"regina","name":"University of Regina","base_url":"https://uregina.scholaris.ca/server/oai/request"},"display":{"title":"Multi-objective evolutionary computation for the portfolio optimization problem with respect to environmental, social, and governance criteria","abstract":"A common problem that faces many is the tension between doing what aligns with our values and doing what is fiscally best. A system leveraging Multi-Objective Evolutionary Computation, specifically MOEA/D, was proposed to produce highly performant portfolios tailored to an individual’s ESG preferences given a custom survey. The survey, written using the greater context of other risk and ESG relevant surveys, was conducted and used to construct a weighting to normalize a given investor’s own survey responses and allow a single portfolio from the collection of the best portfolios to be matched to that investor. Two potential architectures were considered to build the proposed system: Architecture 1, where the optimization is run for each investor that takes the survey, and Architecture 2 where a multi-objective optimization is run less frequently and the investor is given a portfolio from the Pareto front. This subset consists of all the non-dominated portfolios. The user may have a different experiences, including quality or time waiting, depending on the architecture chosen. The result of the experiment was that both architectures produced high quality portfolios that performed comparably. However, the best portfolio from Architecture 2 was better in most regards than any portfolio from Architecture 1. All Architecture 1 portfolios were more significantly tailored to each of the individuals preferences. For Architecture 2, a limited number of high performing portfolios was generated: as a result, more investors would potentially be recommended the same few portfolios, especially in comparison to Architecture 1.","abstract_html":"A common problem that faces many is the tension between doing what aligns with our values and doing what is fiscally best. A system leveraging Multi-Objective Evolutionary Computation, specifically MOEA/D, was proposed to produce highly performant portfolios tailored to an individual’s ESG preferences given a custom survey. The survey, written using the greater context of other risk and ESG relevant surveys, was conducted and used to construct a weighting to normalize a given investor’s own survey responses and allow a single portfolio from the collection of the best portfolios to be matched to that investor. Two potential architectures were considered to build the proposed system: Architecture 1, where the optimization is run for each investor that takes the survey, and Architecture 2 where a multi-objective optimization is run less frequently and the investor is given a portfolio from the Pareto front. This subset consists of all the non-dominated portfolios. The user may have a different experiences, including quality or time waiting, depending on the architecture chosen. The result of the experiment was that both architectures produced high quality portfolios that performed comparably. However, the best portfolio from Architecture 2 was better in most regards than any portfolio from Architecture 1. All Architecture 1 portfolios were more significantly tailored to each of the individuals preferences. For Architecture 2, a limited number of high performing portfolios was generated: as a result, more investors would potentially be recommended the same few portfolios, especially in comparison to Architecture 1.","abstract_has_math":false,"creators":["Herman, Riley Todd"],"institution":"Faculty of Graduate Studies and Research, University of Regina","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Mouhoub, Malek"],"committee_chairs":[],"committee_members":["Khodamoradi, Kamyar"],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-24T04:03:32Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.82465/151"],"render_values":[{"text":"https://doi.org/10.82465/151","href":"https://doi.org/10.82465/151","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10294/17130","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mouhoub, Malek"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Khodamoradi, Kamyar"]},{"key":"dc:creator","label":"Author","values":["Herman, Riley Todd"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-06-08T19:59:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"key":"dc:publisher","label":"Institution","values":["Faculty of Graduate Studies and Research, University of Regina"]},{"key":"dc:type","label":"Dc Type","values":["master thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Regina"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.82465/151"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10294/17130"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Science in Computer Science, University of Regina. xiv, 112 p."]},{"key":"dc:description.abstract","label":"Abstract","values":["A common problem that faces many is the tension between doing what aligns with our values and doing what is fiscally best. A system leveraging Multi-Objective Evolutionary Computation, specifically MOEA/D, was proposed to produce highly performant portfolios tailored to an individual’s ESG preferences given a custom survey. The survey, written using the greater context of other risk and ESG relevant surveys, was conducted and used to construct a weighting to normalize a given investor’s own survey responses and allow a single portfolio from the collection of the best portfolios to be matched to that investor. Two potential architectures were considered to build the proposed system: Architecture 1, where the optimization is run for each investor that takes the survey, and Architecture 2 where a multi-objective optimization is run less frequently and the investor is given a portfolio from the Pareto front. This subset consists of all the non-dominated portfolios. The user may have a different experiences, including quality or time waiting, depending on the architecture chosen. The result of the experiment was that both architectures produced high quality portfolios that performed comparably. However, the best portfolio from Architecture 2 was better in most regards than any portfolio from Architecture 1. All Architecture 1 portfolios were more significantly tailored to each of the individuals preferences. For Architecture 2, a limited number of high performing portfolios was generated: as a result, more investors would potentially be recommended the same few portfolios, especially in comparison to Architecture 1."]},{"key":"dc:title","label":"Title","values":["Multi-objective evolutionary computation for the portfolio optimization problem with respect to environmental, social, and governance criteria"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mouhoub, Malek"],"dc:contributor.committeemember":["Khodamoradi, Kamyar"],"dc:creator":["Herman, Riley Todd"],"dc:date.accessioned":["2026-06-08T19:59:42Z"],"dc:date.issued":["2025-05"],"dc:description":["A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Science in Computer Science, University of Regina. xiv, 112 p."],"dc:description.abstract":["A common problem that faces many is the tension between doing what aligns with our values and doing what is fiscally best. A system leveraging Multi-Objective Evolutionary Computation, specifically MOEA/D, was proposed to produce highly performant portfolios tailored to an individual’s ESG preferences given a custom survey. The survey, written using the greater context of other risk and ESG relevant surveys, was conducted and used to construct a weighting to normalize a given investor’s own survey responses and allow a single portfolio from the collection of the best portfolios to be matched to that investor. Two potential architectures were considered to build the proposed system: Architecture 1, where the optimization is run for each investor that takes the survey, and Architecture 2 where a multi-objective optimization is run less frequently and the investor is given a portfolio from the Pareto front. This subset consists of all the non-dominated portfolios. The user may have a different experiences, including quality or time waiting, depending on the architecture chosen. The result of the experiment was that both architectures produced high quality portfolios that performed comparably. However, the best portfolio from Architecture 2 was better in most regards than any portfolio from Architecture 1. All Architecture 1 portfolios were more significantly tailored to each of the individuals preferences. For Architecture 2, a limited number of high performing portfolios was generated: as a result, more investors would potentially be recommended the same few portfolios, especially in comparison to Architecture 1."],"dc:identifier.doi":["https://doi.org/10.82465/151"],"dc:identifier.uri":["https://hdl.handle.net/10294/17130"],"dc:language.iso":["en"],"dc:publisher":["Faculty of Graduate Studies and Research, University of Regina"],"dc:title":["Multi-objective evolutionary computation for the portfolio optimization problem with respect to environmental, social, and governance criteria"],"dc:type":["master thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Regina"]},"updated_at":"2026-07-24T04:03:32Z"}