Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design
Machine learning algorithms have quickly risen to the top of several fields' decision-making processes in recent years. However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choices. In this work, we examine bias in machine learn...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | E3S Web of Conferences |
| Subjects: | |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/21/e3sconf_icecs2024_02040.pdf |
| _version_ | 1797299457858994176 |
|---|---|
| author | Dhabliya Dharmesh Dari Sukhvinder Singh Dhablia Anishkumar Akhila N. Kachhoria Renu Khetani Vinit |
| author_facet | Dhabliya Dharmesh Dari Sukhvinder Singh Dhablia Anishkumar Akhila N. Kachhoria Renu Khetani Vinit |
| author_sort | Dhabliya Dharmesh |
| collection | DOAJ |
| description | Machine learning algorithms have quickly risen to the top of several fields' decision-making processes in recent years. However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choices. In this work, we examine bias in machine learning in great detail and offer strategies for promoting fair and moral algorithm design. The paper then emphasises the value of fairnessaware machine learning algorithms, which aim to lessen bias by including fairness constraints into the training and evaluation procedures. Reweighting, adversarial training, and resampling are a few strategies that could be used to overcome prejudice. Machine learning systems that better serve society and respect ethical ideals can be developed by promoting justice, transparency, and inclusivity. This paper lays the groundwork for researchers, practitioners, and policymakers to forward the cause of ethical and fair machine learning through concerted effort. |
| first_indexed | 2024-03-07T22:50:57Z |
| format | Article |
| id | doaj.art-ea776974ad484bb2849f22687c60e2f5 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-03-07T22:50:57Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-ea776974ad484bb2849f22687c60e2f52024-02-23T10:21:00ZengEDP SciencesE3S Web of Conferences2267-12422024-01-014910204010.1051/e3sconf/202449102040e3sconf_icecs2024_02040Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical DesignDhabliya Dharmesh0Dari Sukhvinder Singh1Dhablia Anishkumar2Akhila N.3Kachhoria Renu4Khetani Vinit5Professor, Department of Information Technology, Vishwakarma Institute of Information TechnologyDirector, Symbiosis Law School, Nagpur Campus, Symbiosis International (Deemed University)Engineering Manager, Altimetrik India Pvt LtdAssociate Professor, Dept of CSE, Aditya Engineering CollegeDepartment of Artificial Intelligence & Data Science, Vishwakarma Institute of Information TechnologyCybrix TechnologiesMachine learning algorithms have quickly risen to the top of several fields' decision-making processes in recent years. However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choices. In this work, we examine bias in machine learning in great detail and offer strategies for promoting fair and moral algorithm design. The paper then emphasises the value of fairnessaware machine learning algorithms, which aim to lessen bias by including fairness constraints into the training and evaluation procedures. Reweighting, adversarial training, and resampling are a few strategies that could be used to overcome prejudice. Machine learning systems that better serve society and respect ethical ideals can be developed by promoting justice, transparency, and inclusivity. This paper lays the groundwork for researchers, practitioners, and policymakers to forward the cause of ethical and fair machine learning through concerted effort.https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/21/e3sconf_icecs2024_02040.pdfmachine learningethicspromoting fairnessdecision making |
| spellingShingle | Dhabliya Dharmesh Dari Sukhvinder Singh Dhablia Anishkumar Akhila N. Kachhoria Renu Khetani Vinit Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design E3S Web of Conferences machine learning ethics promoting fairness decision making |
| title | Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design |
| title_full | Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design |
| title_fullStr | Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design |
| title_full_unstemmed | Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design |
| title_short | Addressing Bias in Machine Learning Algorithms: Promoting Fairness and Ethical Design |
| title_sort | addressing bias in machine learning algorithms promoting fairness and ethical design |
| topic | machine learning ethics promoting fairness decision making |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/21/e3sconf_icecs2024_02040.pdf |
| work_keys_str_mv | AT dhabliyadharmesh addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign AT darisukhvindersingh addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign AT dhabliaanishkumar addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign AT akhilan addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign AT kachhoriarenu addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign AT khetanivinit addressingbiasinmachinelearningalgorithmspromotingfairnessandethicaldesign |