Machine learning models are extensively being used in decision making, especially for prediction tasks. These models could be biased or unfair towards a specific sensitive group either of a specific race, gender or age. Researchers have put efforts into characterizing a particular definition of fairness and enforcing them into the models. In this work, mainly we are concerned with the following three definitions, Disparate Impact, Demographic Parity and Equalized Odds. Researchers have shown that Equalized Odds cannot be satisfied in calibrated classifiers unless the classifier is perfect. Hence the primary challenge is to ensure a degree of fairness while guaranteeing as much accuracy as possible. Fairness constraints are complex and need not be convex. Incorporating them into a machine learning algorithm is a significant challenge. Hence, many researchers have tried to come up with a surrogate loss which is convex in order to build fair classifiers. Besides, certain papers try to build fair representations by preprocessing the data, irrespective of the classifier used. Such methods, not only require a lot of unrealistic assumptions but also require human engineered analytical solutions to build a machine learning model. We instead propose an automated solution which is generalizable over any fairness constraint. We use a neural network which is trained on batches and directly enforces the fairness constraint as the loss function without modifying it further. We have also experimented with other complex performance measures such as H-mean loss, Q-mean-loss, F-measure; without the need for any surrogate loss functions. Our experiments prove that the network achieves similar performance as state of the art. Thus, one can just plug-in appropriate loss function as per required fairness constraint and performance measure of the classifier and train a neural network to achieve that.

Recently, many AI researchers and practitioners have embarked on research visions that involve doing AI for "Good". This is part of a general drive towards infusing AI research and practice with ethical thinking. One frequent theme in current ethical guidelines is the requirement that AI be good for all, or: contribute to the Common Good. But what is the Common Good, and is it enough to want to be good? Via four lead questions, I will illustrate challenges and pitfalls when determining, from an AI point of view, what the Common Good is and how it can be enhanced by AI. The questions are: What is the problem / What is a problem?, Who defines the problem?, What is the role of knowledge?, and What are important side effects and dynamics? The illustration will use an example from the domain of "AI for Social Good", more specifically "Data Science for Social Good". Even if the importance of these questions may be known at an abstract level, they do not get asked sufficiently in practice, as shown by an exploratory study of 99 contributions to recent conferences in the field. Turning these challenges and pitfalls into a positive recommendation, as a conclusion I will draw on another characteristic of computer-science thinking and practice to make these impediments visible and attenuate them: "attacks" as a method for improving design. This results in the proposal of ethics pen-testing as a method for helping AI designs to better contribute to the Common Good.

Most of the jobs that get displaced by computers or robots are menial labor that requires little or no education. However, now that machine learning algorithms are becoming more sophisticated, even highly educated positions could be replaced by automation. A recent study by LawGeex pitted its machine-learning AI against 20 human lawyers to see how it would fair going over contract law. Each lawyer and the LawGeex AI were given five nondisclosure agreements to review for risks. The humans were given four hours to study the contracts.

Lawyers need not fear an immediate rise of the machines, it emerged today, after a discussion on making arbitration fit for the future concluded that artificial intelligence (AI) will not be able to issue rulings in the near-future. Although panellists said AI would undoubtedly cause changes to the legal profession and have an impact in arbitration disputes, it was accepted a final decision could not be handed over to a machine. International firm Hogan Lovells, which hosted a discussion at its Hong Kong office, asked whether given that AI can assess likely outcomes of cases and perform document reviews, it is realistic to ask if this could be extended to actually making a final ruling. The discussion comes against a continuous debate about the impact of'lawtech'. James Kwan, partner at Hogan Lovells, said there are'few laws' that explicitly ban robots from being decision makers.

When Shawn Hudson decided to buy a Tesla Model S last year, Autopilot was a key selling point. His commute was brutal--125 miles each way, nearly all of it on the highway--and he figured the semi-autonomous driving system would make his life easier. Over 98,000 miles of driving, he used it regularly, letting the computer keep the car in its lane and away from other cars. "I was sold," he told reporters at a press conference Tuesday morning. He would relax during the long ride, checking his phone and sending emails.

How to balance accuracy vs explainability of Machine Learning models? Deep Learning methods build very good prediction and classification models, but they are very hard for humans to understand. The European GDPR laws enacted in May 2018, which give consumers some right to explanation of decision made about them by algorithms, and recent story about Amazon scrapping their internal recruiting tool because of bias against women, highlight the importance of understanding Machine Learning models in many areas. New KDnuggets poll below aims to measure the current importance of understanding of ML models. Poll When building Machine Learning / Data Science models in 2018, how often was it important that the model be humanly understandable/explainable?

Recent studies have shown that the labels collected from crowdworkers can be discriminatory with respect to sensitive attributes such as gender and race. This raises questions about the suitability of using crowdsourced data for further use, such as for training machine learning algorithms. In this work, we address the problem of fair and diverse data collection from a crowd under budget constraints. We propose a novel algorithm which maximizes the expected accuracy of the collected data, while ensuring that the errors satisfy desired notions of fairness. We provide guarantees on the performance of our algorithm and show that the algorithm performs well in practice through experiments on real dataset.

Nicole (Niki) Black is an attorney in Rochester, New York and the legal technology evangelist at MyCase.com, a law.

Match says its lawsuit is anything but baseless -- detailing, in hundreds of pages of court documents, numerous similarities between the two apps. In the process, Match has accused Bumble of "almost every type of [intellectual property] infringement you could think of," says Sarah Burstein, a professor at the University of Oklahoma College of Law whose research focuses on design patents. One of the central questions revolves around Tinder's patented system for connecting people over the Internet. The matching is based on mutual interest, as expressed through a swiping motion.

Artificial intelligence is transforming the traditional delivery of legal services. In general terms, the set of tools broadly called "legal analytics" promises to do two things: increase the efficiency of tasks that once required substantial time and human effort, and mine masses of data to discover new insights that were previously inaccessible. As legal scholars, we're excited about the promise of applying these tools to legal research questions. Students are involved, too, so that we can educate the next generation of lawyers to leverage these tools in their own practices. Suppose that a company wants to forecast which employee complaints lead to lawsuits.