We study the effect of the introduction of university tuition fees on the enrollment behavior of students in Germany. For this, an appropriate Lasso-technique is crucial in order to identify the magnitude and significance of the effect due to potentially many relevant controlling factors and only a short time frame where fees existed. We show that a post-double selection strategy combined with stability selection determines a significant negative impact of fees on student enrollment and identifies relevant variables. This is in contrast to previous empirical studies and a plain linear panel regression which cannot detect any effect of tuition fees in this case. In our study, we explicitly deal with data challenges in the response variable in a transparent way and provide respective robust results. Moreover, we control for spatial cross-effects capturing the heterogeneity in the introduction scheme of fees across federal states ("Bundesl\"ander"), which can set their own educational policy. We also confirm the validity of our Lasso approach in a comprehensive simulation study.

Balancing user experience with strong transaction and login protection is a constant battle for financial institutions – one that can have tangible consequences for both bank and customer. Take, for example, User X. It's Cyber Monday, and User X wants to buy the latest smartphone on his favorite discount online store. The site has limited stock, so he logs in at 4am to ensure he'll be able to get a phone. He excitedly places the item in his cart, goes to check out, and clicks pay – only to receive a message that the purchase was flagged as suspicious and blocked.

"The interests of truth require a diversity of opinions." Banks and lenders are increasingly turning to AI and machine learning to automate their core functions and make more accurate predictions in credit underwriting and fraud detection. ML practitioners can take advantage of a growing number of modeling algorithms, such as simple decision trees, random forests, gradient boosting machines, deep neural networks, and support vector machines. Each method has its strengths and weaknesses, which is why it often makes sense to combine ML algorithms to provide even greater predictive performance than any single ML method could provide on its own. This method of combining algorithms is known as ensembling.

The US Food and Drug Administration (FDA) has cleared an artificial intelligence (AI) algorithm from GE Healthcare that analyzes chest x-rays for pneumothorax and helps flag suspected cases for radiologists to prioritize reading, the company announced today. The algorithm, part of a set of other quality-assurance algorithms named the Critical Care Suite, was developed to run on a GE Healthcare mobile x-ray device. The software is not yet for sale, and an outside expert expressed concern about its false positive rate. The idea for the application came from bedside clinician experience of waiting for radiologists to read chest x-rays, said Rachael Callcut, MD, MSPH, a surgeon and director of data science for the Center for Digital Health Innovation at the University of California, San Francisco. UCSF proposed developing the feature as part of a development partnership with GE Healthcare.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples raises our concerns in adopting deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for three most popular data types, including images, graphs and text.

The widespread use of ML-based decision making in domains with high societal impact such as recidivism, job hiring and loan credit has raised a lot of concerns regarding potential discrimination. In particular, in certain cases it has been observed that ML algorithms can provide different decisions based on sensitive attributes such as gender or race and therefore can lead to discrimination. Although, several fairness-aware ML approaches have been proposed, their focus has been largely on preserving the overall classification accuracy while improving fairness in predictions for both protected and non-protected groups (defined based on the sensitive attribute(s)). The overall accuracy however is not a good indicator of performance in case of class imbalance, as it is biased towards the majority class. As we will see in our experiments, many of the fairness-related datasets suffer from class imbalance and therefore, tackling fairness requires also tackling the imbalance problem. To this end, we propose AdaFair, a fairness-aware classifier based on AdaBoost that further updates the weights of the instances in each boosting round taking into account a cumulative notion of fairness based upon all current ensemble members, while explicitly tackling class-imbalance by optimizing the number of ensemble members for balanced classification error. Our experiments show that our approach can achieve parity in true positive and true negative rates for both protected and non-protected groups, while it significantly outperforms existing fairness-aware methods up to 25% in terms of balanced error.

The devastating effects of cyber-attacks, highlight the need for novel attack detection and prevention techniques. Over the last years, considerable work has been done in the areas of attack detection as well as in collaborative defense. However, an analysis of the state of the art suggests that many challenges exist in prioritizing alert data and in studying the relation between a recently discovered attack and the probability of it occurring again. In this article, we propose a system that is intended for characterizing network entities and the likelihood that they will behave maliciously in the future. Our system, namely Network Entity Reputation Database System (NERDS), takes into account all the available information regarding a network entity (e. g. IP address) to calculate the probability that it will act maliciously. The latter part is achieved via the utilization of machine learning. Our experimental results show that it is indeed possible to precisely estimate the probability of future attacks from each entity using information about its previous malicious behavior and other characteristics. Ranking the entities by this probability has practical applications in alert prioritization, assembly of highly effective blacklists of a limited length and other use cases.

Most real-world networks are incompletely observed. Algorithms that can accurately predict which links are missing can dramatically speedup the collection of network data and improve the validity of network models. Many algorithms now exist for predicting missing links, given a partially observed network, but it has remained unknown whether a single best predictor exists, how link predictability varies across methods and networks from different domains, and how close to optimality current methods are. We answer these questions by systematically evaluating 203 individual link predictor algorithms, representing three popular families of methods, applied to a large corpus of 548 structurally diverse networks from six scientific domains. We first show that individual algorithms exhibit a broad diversity of prediction errors, such that no one predictor or family is best, or worst, across all realistic inputs. We then exploit this diversity via meta-learning to construct a series of "stacked" models that combine predictors into a single algorithm. Applied to a broad range of synthetic networks, for which we may analytically calculate optimal performance, these stacked models achieve optimal or nearly optimal levels of accuracy. Applied to real-world networks, stacked models are also superior, but their accuracy varies strongly by domain, suggesting that link prediction may be fundamentally easier in social networks than in biological or technological networks. These results indicate that the state-of-the-art for link prediction comes from combining individual algorithms, which achieves nearly optimal predictions. We close with a brief discussion of limitations and opportunities for further improvement of these results.

We address the problem of learning to benchmark the best achievable classifier performance. In this problem the objective is to establish statistically consistent estimates of the Bayes misclassification error rate without having to learn a Bayes-optimal classifier. Our learning to benchmark framework improves on previous work on learning bounds on Bayes misclassification rate since it learns the {\it exact} Bayes error rate instead of a bound on error rate. We propose a benchmark learner based on an ensemble of $\epsilon$-ball estimators and Chebyshev approximation. Under a smoothness assumption on the class densities we show that our estimator achieves an optimal (parametric) mean squared error (MSE) rate of $O(N^{-1})$, where $N$ is the number of samples. Experiments on both simulated and real datasets establish that our proposed benchmark learning algorithm produces estimates of the Bayes error that are more accurate than previous approaches for learning bounds on Bayes error probability.

Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted medical decision making. For classification tasks, prior studies on UQ are difficult to compare with each other, due to the lack of a unified quantitative evaluation metric. Considering that well-performing UQ models ought to know when the classification models act incorrectly, we design a new evaluation metric, area under Confidence-Classification Characteristic curves (AUCCC), to quantitatively evaluate the performance of the UQ models. AUCCC is threshold-free, robust to perturbation, and insensitive to the classification performance. We evaluate several UQ methods (e.g., max softmax output) with AUCCC to validate its effectiveness. Furthermore, a simple scheme, named Uncertainty Distillation (UDist), is developed to boost the UQ performance, where a confidence model is distilling the confidence estimated by deep ensembles. The proposed method is easy to implement; it consistently outperforms strong baselines on natural and medical image datasets in our experiments.