The rise of algorithmic decision making led to active researches on how to define and guarantee fairness, mostly focusing on one-shot decision making. In several important applications such as hiring, however, decisions are made in multiple stage with additional information at each stage. In such cases, fairness issues remain poorly understood. In this paper we study fairness in $k$-stage selection problems where additional features are observed at every stage. We first introduce two fairness notions, local (per stage) and global (final stage) fairness, that extend the classical fairness notions to the $k$-stage setting. We propose a simple model based on a probabilistic formulation and show that the locally and globally fair selections that maximize precision can be computed via a linear program. We then define the price of local fairness to measure the loss of precision induced by local constraints; and investigate theoretically and empirically this quantity. In particular, our experiments show that the price of local fairness is generally smaller when the sensitive attribute is observed at the first stage; but globally fair selections are more locally fair when the sensitive attribute is observed at the second stage---hence in both cases it is often possible to have a selection that has a small price of local fairness and is close to locally fair.

As e-commerce has revolutionized the way we buy and sell online, we are no longer bounded by borders or time zones. Goods can be purchased from anywhere around the world at any time of day. Because of this, traditional rules-based fraud detection systems have become outdated and no longer work. Today, real-time payments require real-time fraud detection. Modern payment fraud schemes require modern prevention With so many transactions being done electronically, it's nearly impossible to have humans alone monitor these transactions and keep fraud and error rates down to acceptable levels.

If you're anything like my dad, you've worked in IT for decades but have only tangentially touched data science. Now, your new C-something-O wants you to fire up a data analytics team and work with new a set of buzzwords you've only vaguely heard about at conferences. Or perhaps you're a developer at a fast-moving startup and have spent weeks finalizing an algorithm, only to be stymied by issues with deploying the model onto your web application for real time use. For both cases, H2O.ai is definitely a solution worth looking into. H2O.ai positions itself as a software package that streamlines the machine learning process through its open source package H2O and AutoML.

Simulating dynamic rupture propagation is challenging due to the uncertainties involved in the underlying physics of fault slip, stress conditions, and frictional properties of the fault. A trial and error approach is often used to determine the unknown parameters describing rupture, but running many simulations usually requires human review to determine how to adjust parameter values and is thus not very efficient. To reduce the computational cost and improve our ability to determine reasonable stress and friction parameters, we take advantage of the machine learning approach. We develop two models for earthquake rupture propagation using the artificial neural network (ANN) and the random forest (RF) algorithms to predict if a rupture can break a geometric heterogeneity on a fault. We train the models using a database of 1600 dynamic rupture simulations computed numerically. Fault geometry, stress conditions, and friction parameters vary in each simulation. We cross-validate and test the predictive power of the models using an additional 400 simulated ruptures, respectively. Both RF and ANN models predict rupture propagation with more than 81% accuracy, and model parameters can be used to infer the underlying factors most important for rupture propagation. Both of the models are computationally efficient such that the 400 testings require a fraction of a second, leading to potential applications of dynamic rupture that have previously not been possible due to the computational demands of physics-based rupture simulations.

For enabling automatic deployment and management of cellular networks, the concept of self-organizing network (SON) was introduced. SON capabilities can enhance network performance, improve service quality, and reduce operational and capital expenditure (OPEX/CAPEX). As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation. Data-driven machine learning has been recognized as a powerful tool to bring intelligence into network and to realize self-healing. However, there are major challenges for practical applications of machine learning techniques for self-healing. In this article, we first classify these challenges into five categories: 1) data imbalance, 2) data insufficiency, 3) cost insensitivity, 4) non-real-time response, and 5) multi-source data fusion. Then we provide potential technical solutions to address these challenges. Furthermore, a case study of cost-sensitive fault detection with imbalanced data is provided to illustrate the feasibility and effectiveness of the suggested solutions.

Kernel-based support vector machines (SVMs) are supervised machine learning algorithms for classification and regression problems. We present a method to train SVMs on a D-Wave 2000Q quantum annealer and study its performance in comparison to SVMs trained on conventional computers. The method is applied to both synthetic data and real data obtained from biology experiments. We find that the quantum annealer produces an ensemble of different solutions that often generalizes better to unseen data than the single global minimum of an SVM trained on a conventional computer, especially in cases where only limited training data is available. For cases with more training data than currently fits on the quantum annealer, we show that a combination of classifiers for subsets of the data almost always produces stronger joint classifiers than the conventional SVM for the same parameters.

Point estimation of class prevalences in the presence of data set shift has been a popular research topic for more than two decades. Less attention has been paid to the construction of confidence and prediction intervals for estimates of class prevalences. One little considered question is whether or not it is necessary for practical purposes to distinguish confidence and prediction intervals. Another question so far not yet conclusively answered is whether or not the discriminatory power of the classifier or score at the basis of an estimation method matters for the accuracy of the estimates of the class prevalences. This paper presents a simulation study aimed at shedding some light on these and other related questions.

Credit risk modelling is an integral part of the global financial system. While there has been great attention paid to neural network models for credit default prediction, such models often lack the required interpretation mechanisms and measures of the uncertainty around their predictions. This work develops and compares Bayesian Neural Networks(BNNs) for credit card default modelling. This includes a BNNs trained by Gaussian approximation and the first implementation of BNNs trained by Hybrid Monte Carlo(HMC) in credit risk modelling. The results on the Taiwan Credit Dataset show that BNNs with Automatic Relevance Determination(ARD) outperform normal BNNs without ARD. The results also show that BNNs trained by Gaussian approximation display similar predictive performance to those trained by the HMC. The results further show that BNN with ARD can be used to draw inferences about the relative importance of different features thus critically aiding decision makers in explaining model output to consumers. The robustness of this result is reinforced by high levels of congruence between the features identified as important using the two different approaches for training BNNs.

In this paper we consider the problem of maximizing the Area under the ROC curve (AUC) which is a widely used performance metric in imbalanced classification and anomaly detection. Due to the pairwise nonlinearity of the objective function, classical SGD algorithms do not apply to the task of AUC maximization. We propose a novel stochastic proximal algorithm for AUC maximization which is scalable to large scale streaming data. Our algorithm can accommodate general penalty terms and is easy to implement with favorable $O(d)$ space and per-iteration time complexities. We establish a high-probability convergence rate $O(1/\sqrt{T})$ for the general convex setting, and improve it to a fast convergence rate $O(1/T)$ for the cases of strongly convex regularizers and no regularization term (without strong convexity). Our proof does not need the uniform boundedness assumption on the loss function or the iterates which is more fidelity to the practice. Finally, we perform extensive experiments over various benchmark data sets from real-world application domains which show the superior performance of our algorithm over the existing AUC maximization algorithms.

Kernel ridge regression (KRR) is a well-known and popular nonparametric regression approach with many desirable properties, including minimax rate-optimality in estimating functions that belong to common reproducing kernel Hilbert spaces (RKHS). The approach, however, is computationally intensive for large data sets, due to the need to operate on a dense $n \times n$ kernel matrix, where $n$ is the sample size. Recently, various approximation schemes for solving KRR have been considered, and some analyzed. Some approaches such as Nystr\"{o}m approximation and sketching have been shown to preserve the rate optimality of KRR. In this paper, we consider the simplest approximation, namely, spectrally truncating the kernel matrix to its largest $r < n$ eigenvalues. We derive an exact expression for the maximum risk of this truncated KRR, over the unit ball of the RKHS. This result can be used to study the exact trade-off between the level of spectral truncation and the regularization parameter of the KRR. We show that, as long as the RKHS is infinite-dimensional, there is a threshold on $r$, above which, the spectrally-truncated KRR, surprisingly, outperforms the full KRR in terms of the minimax risk, where the minimum is taken over the regularization parameter. This strengthens the existing results on approximation schemes, by showing that not only one does not lose in terms of the rates, truncation can in fact improve the performance, for all finite samples (above the threshold). In other words, there is nothing to be gained by running the full KRR and one should always truncate. Our proof is elementary and distribution-free, only requiring the noise vector to be isotropic.