In this work, we define and solve the Fair Top-k Ranking problem, in which we want to determine a subset of k candidates from a large pool of n » k candidates, maximizing utility (i.e., select the "best" candidates) subject to group fairness criteria.

Algorithms and decision making based on Big Data have become pervasive in all aspects of our daily lives lives (offline and online), as they have become essential tools in personal finance, health care, hiring, housing, education, and policies. It is therefore of societal and ethical importance to ask whether these algorithms can be discriminative on grounds such as gender, ethnicity, or health status. It turns out that the answer is positive: for instance, recent studies in the context of online advertising show that ads for high-income jobs are presented to men much more often than to women [Datta et al., 2015]; and ads for arrest records are significantly more likely to show up on searches for distinctively black names [Sweeney, 2013]. This algorithmic bias exists even when there is no discrimination intention in the developer of the algorithm. Sometimes it may be inherent to the data sources used (software making decisions based on data can reflect, or even amplify, the results of historical discrimination), but even when the sensitive attributes have been suppressed from the input, a well trained machine learning algorithm may still discriminate on the basis of such sensitive attributes because of correlations existing in the data. These considerations call for the development of data mining systems which are discrimination-conscious by-design. This is a novel and challenging research area for the data mining community.

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.

Automated data collection has fostered the use of data mining for intrusion and crime detection. Indeed, banks, large corporations, insurance companies, casinos, etc. are increasingly mining data about their customers or employees in view of detecting potential intrusion, fraud or even crime. Mining algorithms are trained from datasets which may be biased in what regards gender, race, religion or other attributes. Furthermore, mining is often outsourced or carried out in cooperation by several entities. For those reasons, discrimination concerns arise. Potential intrusion, fraud or crime should be inferred from objective misbehavior, rather than from sensitive attributes like gender, race or religion. This paper discusses how to clean training datasets and outsourced datasets in such a way that legitimate classification rules can still be extracted but discriminating rules based on sensitive attributes cannot.

Despite the benefits of data mining in a wide range of applications, this technique has raised some issues related to the privacy and security of individuals. Due to these issues, data owners may prevent to share their sensitive information with data miners. On the other hand, in distributed enviro nments, other issues related to the distribution of data will raise, which will make the preservation of privacy more challengeable. To solve these problems, different privacy preserving data mining (PPDM) techniques have been introduced. In this paper, a new privacy preserving clustering (PPC) technique for horizontally and vertically distributed datasets is proposed. The proposed technique uses Haar wavelet transforms (HWT) and scaling data perturbation (SDP) to achieve both data hiding and data reduction for protecting private numerical attribute values in distributed datasets. The results of our evaluations demonstrated that the proposed technique provides a proper degree of privacy and quality of clustering for distributed datasets and also runs fast. Our experiments have also shown that the proposed technique provides better privacy and clustering results comparing to the other existing privacy preserving clustering techniques applicable to distributed datasets. The proposed algorithms and the results of their experimental evaluations using different datasets are presented in this paper.