The Experts below are selected from a list of 1467 Experts worldwide ranked by ideXlab platform
Sonali Bodkhe - One of the best experts on this subject based on the ideXlab platform.
-
Review on privacy preservation method by applying Discrimination rules in data mining
2015 International Conference on Pervasive Computing (ICPC), 2015Co-Authors: Priya Meshram, Sonali BodkheAbstract:In data mining, for considering the legal and ethical aspects of privacy preservation therefore Discrimination is crucial. It is clear that most of the people do not have a wish to discriminate based on their race, nationality, religion, age and so on. This problem mainly arises when these kind of attributes are used for decision making purpose such as giving them a job, loan, Insurance etc. Discrimination is of two types direct Discrimination and Indirect Discrimination. Direct Discrimination is based on sensitive information. Indirect Discrimination is based on non-sensitive information. In this paper, we mainly focus on anti-Discrimination, a method which also helps to detect and prevent Discrimination.
Priya Meshram - One of the best experts on this subject based on the ideXlab platform.
-
Review on privacy preservation method by applying Discrimination rules in data mining
2015 International Conference on Pervasive Computing (ICPC), 2015Co-Authors: Priya Meshram, Sonali BodkheAbstract:In data mining, for considering the legal and ethical aspects of privacy preservation therefore Discrimination is crucial. It is clear that most of the people do not have a wish to discriminate based on their race, nationality, religion, age and so on. This problem mainly arises when these kind of attributes are used for decision making purpose such as giving them a job, loan, Insurance etc. Discrimination is of two types direct Discrimination and Indirect Discrimination. Direct Discrimination is based on sensitive information. Indirect Discrimination is based on non-sensitive information. In this paper, we mainly focus on anti-Discrimination, a method which also helps to detect and prevent Discrimination.
Sara Hajian - One of the best experts on this subject based on the ideXlab platform.
-
A Methodology for Direct and Indirect Discrimination Prevention in Data Mining
IEEE Transactions on Knowledge and Data Engineering, 2013Co-Authors: Sara Hajian, Josep Domingo-ferrerAbstract:Data mining is an increasingly important technology for extracting useful knowledge hidden in large collections of data. There are, however, negative social perceptions about data mining, among which potential privacy invasion and potential Discrimination. The latter consists of unfairly treating people on the basis of their belonging to a specific group. Automated data collection and data mining techniques such as classification rule mining have paved the way to making automated decisions, like loan granting/denial, insurance premium computation, etc. If the training data sets are biased in what regards discriminatory (sensitive) attributes like gender, race, religion, etc., discriminatory decisions may ensue. For this reason, anti-Discrimination techniques including Discrimination discovery and prevention have been introduced in data mining. Discrimination can be either direct or Indirect. Direct Discrimination occurs when decisions are made based on sensitive attributes. Indirect Discrimination occurs when decisions are made based on nonsensitive attributes which are strongly correlated with biased sensitive ones. In this paper, we tackle Discrimination prevention in data mining and propose new techniques applicable for direct or Indirect Discrimination prevention individually or both at the same time. We discuss how to clean training data sets and outsourced data sets in such a way that direct and/or Indirect discriminatory decision rules are converted to legitimate (nondiscriminatory) classification rules. We also propose new metrics to evaluate the utility of the proposed approaches and we compare these approaches. The experimental evaluations demonstrate that the proposed techniques are effective at removing direct and/or Indirect Discrimination biases in the original data set while preserving data quality.
-
direct and Indirect Discrimination prevention methods
Discrimination and Privacy in the Information Society, 2013Co-Authors: Sara Hajian, Josep DomingoferrerAbstract:Along with privacy, Discrimination is a very important issue when considering the legal and ethical aspects of data mining. It is more than obvious that most people do not want to be discriminated because of their gender, religion, nationality, age and so on, especially when those attributes are used for making decisions about them like giving them a job, loan, insurance, etc. Discovering such potential biases and eliminating them from the training data without harming their decision-making utility is therefore highly desirable. For this reason, anti-Discrimination techniques including Discrimination discovery and prevention have been introduced in data mining. Discrimination prevention consists of inducing patterns that do not lead to discriminatory decisions even if the original training datasets are inherently biased. In this chapter, by focusing on the Discrimination prevention, we present a taxonomy for classifying and examining Discrimination prevention methods. Then, we introduce a group of pre-processing Discrimination prevention methods and specify the different features of each approach and how these approaches deal with direct or Indirect Discrimination. A presentation of metrics used to evaluate the performance of those approaches is also given. Finally, we conclude our study by enumerating interesting future directions in this research body.
-
Discrimination and Privacy in the Information Society - Direct and Indirect Discrimination Prevention Methods
Studies in Applied Philosophy Epistemology and Rational Ethics, 2013Co-Authors: Sara Hajian, Josep Domingo-ferrerAbstract:Along with privacy, Discrimination is a very important issue when considering the legal and ethical aspects of data mining. It is more than obvious that most people do not want to be discriminated because of their gender, religion, nationality, age and so on, especially when those attributes are used for making decisions about them like giving them a job, loan, insurance, etc. Discovering such potential biases and eliminating them from the training data without harming their decision-making utility is therefore highly desirable. For this reason, anti-Discrimination techniques including Discrimination discovery and prevention have been introduced in data mining. Discrimination prevention consists of inducing patterns that do not lead to discriminatory decisions even if the original training datasets are inherently biased. In this chapter, by focusing on the Discrimination prevention, we present a taxonomy for classifying and examining Discrimination prevention methods. Then, we introduce a group of pre-processing Discrimination prevention methods and specify the different features of each approach and how these approaches deal with direct or Indirect Discrimination. A presentation of metrics used to evaluate the performance of those approaches is also given. Finally, we conclude our study by enumerating interesting future directions in this research body.
-
rule protection for Indirect Discrimination prevention in data mining
Modeling Decisions for Artificial Intelligence, 2011Co-Authors: Sara Hajian, Josep Domingoferrer, Antoni MartinezballesteAbstract:Services in the information society allow automatically and routinely collecting large amounts of data. Those data are often used to train classification rules in view of making automated decisions, like loan granting/denial, insurance premium computation, etc. If the training datasets are biased in what regards sensitive attributes like gender, race, religion, etc., discriminatory decisions may ensue. Direct Discrimination occurs when decisions are made based on biased sensitive attributes. Indirect Discrimination occurs when decisions are made based on non-sensitive attributes which are strongly correlated with biased sensitive attributes. This paper discusses how to clean training datasets and outsourced datasets in such a way that legitimate classification rules can still be extracted but Indirectly discriminating rules cannot.
-
MDAI - Rule protection for Indirect Discrimination prevention in data mining
Lecture Notes in Computer Science, 2011Co-Authors: Sara Hajian, Josep Domingo-ferrer, Antoni Martínez-ballestéAbstract:Services in the information society allow automatically and routinely collecting large amounts of data. Those data are often used to train classification rules in view of making automated decisions, like loan granting/denial, insurance premium computation, etc. If the training datasets are biased in what regards sensitive attributes like gender, race, religion, etc., discriminatory decisions may ensue. Direct Discrimination occurs when decisions are made based on biased sensitive attributes. Indirect Discrimination occurs when decisions are made based on non-sensitive attributes which are strongly correlated with biased sensitive attributes. This paper discusses how to clean training datasets and outsourced datasets in such a way that legitimate classification rules can still be extracted but Indirectly discriminating rules cannot.
Chihjen Wang - One of the best experts on this subject based on the ideXlab platform.
-
consumer responses to price Discrimination discriminating bases inequality status and information disclosure timing influences
Journal of Business Research, 2012Co-Authors: Yifen Liu, Yingju Chen, Chihjen WangAbstract:Abstract This study broadly explores consumers' perceived unfairness, negative emotions, internal reference price, and store choice under five common methods of price Discrimination using two experimental studies. Study 1 investigates the interaction between discriminating bases and inequality status. Results reveal that discriminating bases only influence perceived unfairness for advantaged consumers, but affect all four responses for disadvantaged consumers. For disadvantaged consumers, direct Discrimination that complies with social norms evokes the weakest unfavorable responses, whereas direct Discrimination against social norms triggers the highest perception of unfairness and negative emotions but has similar effects on internal reference price and store choice to Indirect Discrimination. Study 2 examines the effect of information disclosure timing by comparing pre- and post-purchase disclosure policies. Results show that post-purchase disclosure of Discrimination information elicits higher negative emotions for Indirect Discrimination involving coupon and purchase quantity, but is rather inconsequential for direct Discrimination or Indirect Discrimination through membership.
Josep Domingo-ferrer - One of the best experts on this subject based on the ideXlab platform.
-
A Methodology for Direct and Indirect Discrimination Prevention in Data Mining
IEEE Transactions on Knowledge and Data Engineering, 2013Co-Authors: Sara Hajian, Josep Domingo-ferrerAbstract:Data mining is an increasingly important technology for extracting useful knowledge hidden in large collections of data. There are, however, negative social perceptions about data mining, among which potential privacy invasion and potential Discrimination. The latter consists of unfairly treating people on the basis of their belonging to a specific group. Automated data collection and data mining techniques such as classification rule mining have paved the way to making automated decisions, like loan granting/denial, insurance premium computation, etc. If the training data sets are biased in what regards discriminatory (sensitive) attributes like gender, race, religion, etc., discriminatory decisions may ensue. For this reason, anti-Discrimination techniques including Discrimination discovery and prevention have been introduced in data mining. Discrimination can be either direct or Indirect. Direct Discrimination occurs when decisions are made based on sensitive attributes. Indirect Discrimination occurs when decisions are made based on nonsensitive attributes which are strongly correlated with biased sensitive ones. In this paper, we tackle Discrimination prevention in data mining and propose new techniques applicable for direct or Indirect Discrimination prevention individually or both at the same time. We discuss how to clean training data sets and outsourced data sets in such a way that direct and/or Indirect discriminatory decision rules are converted to legitimate (nondiscriminatory) classification rules. We also propose new metrics to evaluate the utility of the proposed approaches and we compare these approaches. The experimental evaluations demonstrate that the proposed techniques are effective at removing direct and/or Indirect Discrimination biases in the original data set while preserving data quality.
-
Discrimination and Privacy in the Information Society - Direct and Indirect Discrimination Prevention Methods
Studies in Applied Philosophy Epistemology and Rational Ethics, 2013Co-Authors: Sara Hajian, Josep Domingo-ferrerAbstract:Along with privacy, Discrimination is a very important issue when considering the legal and ethical aspects of data mining. It is more than obvious that most people do not want to be discriminated because of their gender, religion, nationality, age and so on, especially when those attributes are used for making decisions about them like giving them a job, loan, insurance, etc. Discovering such potential biases and eliminating them from the training data without harming their decision-making utility is therefore highly desirable. For this reason, anti-Discrimination techniques including Discrimination discovery and prevention have been introduced in data mining. Discrimination prevention consists of inducing patterns that do not lead to discriminatory decisions even if the original training datasets are inherently biased. In this chapter, by focusing on the Discrimination prevention, we present a taxonomy for classifying and examining Discrimination prevention methods. Then, we introduce a group of pre-processing Discrimination prevention methods and specify the different features of each approach and how these approaches deal with direct or Indirect Discrimination. A presentation of metrics used to evaluate the performance of those approaches is also given. Finally, we conclude our study by enumerating interesting future directions in this research body.
-
MDAI - Rule protection for Indirect Discrimination prevention in data mining
Lecture Notes in Computer Science, 2011Co-Authors: Sara Hajian, Josep Domingo-ferrer, Antoni Martínez-ballestéAbstract:Services in the information society allow automatically and routinely collecting large amounts of data. Those data are often used to train classification rules in view of making automated decisions, like loan granting/denial, insurance premium computation, etc. If the training datasets are biased in what regards sensitive attributes like gender, race, religion, etc., discriminatory decisions may ensue. Direct Discrimination occurs when decisions are made based on biased sensitive attributes. Indirect Discrimination occurs when decisions are made based on non-sensitive attributes which are strongly correlated with biased sensitive attributes. This paper discusses how to clean training datasets and outsourced datasets in such a way that legitimate classification rules can still be extracted but Indirectly discriminating rules cannot.