Machine learning and prejudice: building theory with algorithm-supported abduction
Machine learning is a powerful analytical tool that can identify robust and replicable patterns in complex datasets, and create models with high predictive power. With interpretable machine learning, these models can be queried to identify the most important predictors of an outcome variable from hu...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/165160 |
| _version_ | 1811696362430922752 |
|---|---|
| author | Degefe, Elizabeth Demissie |
| author2 | Zou Xi |
| author_facet | Zou Xi Degefe, Elizabeth Demissie |
| author_sort | Degefe, Elizabeth Demissie |
| collection | NTU |
| description | Machine learning is a powerful analytical tool that can identify robust and replicable patterns in complex datasets, and create models with high predictive power. With interpretable machine learning, these models can be queried to identify the most important predictors of an outcome variable from hundreds of potential predictors. I propose that these machine learning capabilities can be used to engage in abductive reasoning, that is, identifying the most likely explanations of important phenomena in an empirical manner. I will first review past research in management using machine learning, and then describe two empirical projects in which I used machine learning to generate novel hypotheses about antecedents of sexism and racism in the US context. I verified these hypotheses using conventional research methods and identified the underlying mechanisms. The findings suggest that machine models can help expand the scope of researchers’ explanatory frameworks, and thereby identify neglected directions that can benefit from further theorizing. |
| first_indexed | 2024-10-01T07:38:09Z |
| format | Thesis-Doctor of Philosophy |
| id | ntu-10356/165160 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:38:09Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1651602024-01-12T10:28:31Z Machine learning and prejudice: building theory with algorithm-supported abduction Degefe, Elizabeth Demissie Zou Xi Nanyang Business School zou.xi@ntu.edu.sg Business::Management Machine learning is a powerful analytical tool that can identify robust and replicable patterns in complex datasets, and create models with high predictive power. With interpretable machine learning, these models can be queried to identify the most important predictors of an outcome variable from hundreds of potential predictors. I propose that these machine learning capabilities can be used to engage in abductive reasoning, that is, identifying the most likely explanations of important phenomena in an empirical manner. I will first review past research in management using machine learning, and then describe two empirical projects in which I used machine learning to generate novel hypotheses about antecedents of sexism and racism in the US context. I verified these hypotheses using conventional research methods and identified the underlying mechanisms. The findings suggest that machine models can help expand the scope of researchers’ explanatory frameworks, and thereby identify neglected directions that can benefit from further theorizing. Doctor of Philosophy 2023-03-17T02:02:12Z 2023-03-17T02:02:12Z 2023 Thesis-Doctor of Philosophy Degefe, E. D. (2023). Machine learning and prejudice: building theory with algorithm-supported abduction. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165160 https://hdl.handle.net/10356/165160 10.32657/10356/165160 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University |
| spellingShingle | Business::Management Degefe, Elizabeth Demissie Machine learning and prejudice: building theory with algorithm-supported abduction |
| title | Machine learning and prejudice: building theory with algorithm-supported abduction |
| title_full | Machine learning and prejudice: building theory with algorithm-supported abduction |
| title_fullStr | Machine learning and prejudice: building theory with algorithm-supported abduction |
| title_full_unstemmed | Machine learning and prejudice: building theory with algorithm-supported abduction |
| title_short | Machine learning and prejudice: building theory with algorithm-supported abduction |
| title_sort | machine learning and prejudice building theory with algorithm supported abduction |
| topic | Business::Management |
| url | https://hdl.handle.net/10356/165160 |
| work_keys_str_mv | AT degefeelizabethdemissie machinelearningandprejudicebuildingtheorywithalgorithmsupportedabduction |