Data Mining Practical Machine Learning Tools and Techniques

2 1 The innovative transport systems and the CityMobil project 10 1.1 The research questions 10 2 The state of art in the field of automatic transport systems 12 2.1 Case studies and demand studies for innovative transport systems 12 3 The design and implementation of surveys 14 3.1 Definition of experimental design 14 3.2 Questionnaire design and delivery 16 3.3 First analyses on the collected sample 18 4 Calibration of Logit Multionomial demand models 21 4.1 Methodology 21 4.2 Calibration of the “full” model. 22 4.3 Calibration of the “final” model 24 4.4 The demand analysis through the final Multinomial Logit model 25 5 The analysis of interaction between the demand and socioeconomic attributes 31 5.1 Methodology 31 5.2 Application of Mixed Logit models to the demand 31 5.3 Analysis of the interactions between demand and socioeconomic attributes through Mixed Logit models 32 5.4 Mixed Logit model and interaction between age and the demand for the CTS 38 5.5 Demand analysis with Mixed Logit model 39 6 Final analyses and conclusions 45 6.1 Comparison between the results of the analyses 45 6.2 Conclusions 48 6.3 Answers to the research questions and future developments 52

The European commission

With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain groups or populations. We have recently seen work in machine learning, natural language processing, and deep learning that addresses such challenges in different subdomains. With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them. In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and how they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

A Survey on Bias and Fairness in Machine Learning

We summarize the potential impact that the European Union’s new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user-level predictors) which “significantly affect” users. The law will also effectively create a “right to explanation,” whereby a user can ask for an explanation of an algorithmic decision that was made about them. We argue that while this law will pose large challenges for industry, it highlights opportunities for computer scientists to take the lead in designing algorithms and evaluation frameworks which avoid discrimination and enable explanation.

/pdf/european-union-regulations-on-algorithmic-decision-making-66w9rc75zo.pdf

European Union Regulations on Algorithmic Decision-Making and a “Right to Explanation”

527 articles related to imbalanced data and rare events are reviewed.Viewing reviewed papers from both technical and practical perspectives.Summarizing existing methods and corresponding statistics by a new taxonomy idea.Categorizing 162 application papers into 13 domains and giving introduction.Some opening questions are discussed at the end of this manuscript. Rare events, especially those that could potentially negatively impact society, often require humans decision-making responses. Detecting rare events can be viewed as a prediction task in data mining and machine learning communities. As these events are rarely observed in daily life, the prediction task suffers from a lack of balanced data. In this paper, we provide an in depth review of rare event detection from an imbalanced learning perspective. Five hundred and seventeen related papers that have been published in the past decade were collected for the study. The initial statistics suggested that rare events detection and imbalanced learning are concerned across a wide range of research areas from management science to engineering. We reviewed all collected papers from both a technical and a practical point of view. Modeling methods discussed include techniques such as data preprocessing, classification algorithms and model evaluation. For applications, we first provide a comprehensive taxonomy of the existing application domains of imbalanced learning, and then we detail the applications for each category. Finally, some suggestions from the reviewed papers are incorporated with our experiences and judgments to offer further research directions for the imbalanced learning and rare event detection fields.

Learning from class-imbalanced data

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. The aim of this tutorial is to survey algorithmic bias, presenting its most common variants, with an emphasis on the algorithmic techniques and key ideas developed to derive efficient solutions. The tutorial covers two main complementary approaches: algorithms for discrimination discovery and discrimination prevention by means of fairness-aware data mining. We conclude by summarizing promising paths for future research.

Algorithmic Bias: From Discrimination Discovery to Fairness-aware Data Mining

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.

A Methodology for Direct and Indirect Discrimination Prevention in Data Mining

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. Our ranked group fairness definition extends group fairness using the standard notion of protected groups and is based on ensuring that the proportion of protected candidates in every prefix of the top-k ranking remains statistically above or indistinguishable from a given minimum. 
Utility is operationalized in two ways: (i) every candidate included in the top-$k$ should be more qualified than every candidate not included; and (ii) for every pair of candidates in the top-k, the more qualified candidate should be ranked above. An efficient algorithm is presented for producing the Fair Top-k Ranking, and tested experimentally on existing datasets as well as new datasets released with this paper, showing that our approach yields small distortions with respect to rankings that maximize utility without considering fairness criteria. 
To the best of our knowledge, this is the first algorithm grounded in statistical tests that can mitigate biases in the representation of an under-represented group along a ranked list.

/pdf/fa-ir-a-fair-top-k-ranking-algorithm-3igj5x1qyz.pdf

FA*IR: A Fair Top-k Ranking Algorithm

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. Our ranked group fairness definition extends group fairness using the standard notion of protected groups and is based on ensuring that the proportion of protected candidates in every prefix of the top-k ranking remains statistically above or indistinguishable from a given minimum. Utility is operationalized in two ways: (i) every candidate included in the top-k should be more qualified than every candidate not included; and (ii) for every pair of candidates in the top-k, the more qualified candidate should be ranked above. An efficient algorithm is presented for producing the Fair Top-k Ranking, and tested experimentally on existing datasets as well as new datasets released with this paper, showing that our approach yields small distortions with respect to rankings that maximize utility without considering fairness criteria. To the best of our knowledge, this is the first algorithm grounded in statistical tests that can mitigate biases in the representation of an under-represented group along a ranked list.

/pdf/fa-ir-a-fair-top-k-ranking-algorithm-2v742pxoj0.pdf

Data mining is gaining societal momentum due to the ever increasing availability of large amounts of human data, easily collected by a variety of sensing technologies. We are therefore faced with unprecedented opportunities and risks: a deeper understanding of human behavior and how our society works is darkened by a greater chance of privacy intrusion and unfair discrimination based on the extracted patterns and profiles. Consider the case when a set of patterns extracted from the personal data of a population of individual persons is released for a subsequent use into a decision making process, such as, e.g., granting or denying credit. First, the set of patterns may reveal sensitive information about individual persons in the training population and, second, decision rules based on such patterns may lead to unfair discrimination, depending on what is represented in the training cases. Although methods independently addressing privacy or discrimination in data mining have been proposed in the literature, in this context we argue that privacy and discrimination risks should be tackled together, and we present a methodology for doing so while publishing frequent pattern mining results. We describe a set of pattern sanitization methods, one for each discrimination measure used in the legal literature, to achieve a fair publishing of frequent patterns in combination with two possible privacy transformations: one based on $$k$$k-anonymity and one based on differential privacy. Our proposed pattern sanitization methods based on $$k$$k-anonymity yield both privacy- and discrimination-protected patterns, while introducing reasonable (controlled) pattern distortion. Moreover, they obtain a better trade-off between protection and data quality than the sanitization methods based on differential privacy. Finally, the effectiveness of our proposals is assessed by extensive experiments.

Sara Hajian

Papers

Algorithmic Bias: From Discrimination Discovery to Fairness-aware Data Mining

A Methodology for Direct and Indirect Discrimination Prevention in Data Mining

FA*IR: A Fair Top-k Ranking Algorithm

FA*IR: A Fair Top-k Ranking Algorithm

Discrimination- and privacy-aware patterns