Detecting concept drift is a well known problem that affects production systems. However, two important issues that are frequently not addressed in the literature are 1) the detection of drift when the labels are not immediately available; and 2) the automatic generation of explanations to identify possible causes for the drift. For example, a fraud detection model in online payments could show a drift due to a hot sale item (with an increase in false positives) or due to a true fraud attack (with an increase in false negatives) before labels are available. In this paper we propose SAMM, an automatic model monitoring system for data streams. SAMM detects concept drift using a time and space efficient unsupervised streaming algorithm and it generates alarm reports with a summary of the events and features that are important to explain it. SAMM was evaluated in five real world fraud detection datasets, each spanning periods up to eight months and totaling more than 22 million online transactions. We evaluated SAMM using human feedback from domain experts, by sending them 100 reports generated by the system. Our results show that SAMM is able to detect anomalous events in a model life cycle that are considered useful by the domain experts. Given these results, SAMM will be rolled out in a next version of Feedzai's Fraud Detection solution.

Dynamic ensembling of classifiers is an effective approach in processing label-imbalanced classifications. However, in dynamic ensemble methods, the combination of classifiers is usually determined by the local competence and conventional regularization methods are difficult to apply, leaving the technique prone to overfitting. In this paper, focusing on the binary label-imbalanced classification field, a novel method of Adaptive Ensemble of classifiers with Regularization (AER) has been proposed. The method deals with the overfitting problem from a perspective of implicit regularization. Specifically, it leverages the properties of Stochastic Gradient Descent (SGD) to obtain the solution with the minimum norm to achieve regularization, and interpolates ensemble weights via the global geometry of data to further prevent overfitting. The method enjoys a favorable time and memory complexity, and theoretical proofs show that algorithms implemented with AER paradigm have time and memory complexities upper-bounded by their original implementations. Furthermore, the proposed AER method is tested with a specific implementation based on Gradient Boosting Machine (XGBoost) on the three datasets: UCI Bioassay, KEEL Abalone19, and a set of GMM-sampled artificial dataset. Results show that the proposed AER algorithm can outperform the major existing algorithms based on multiple metrics, and Mcnemar's tests are applied to validate performance superiorities. To summarize, this work complements regularization for dynamic ensemble methods and develops an algorithm superior in grasping both the global and local geometry of data to alleviate overfitting in imbalanced data classification.

Label manipulation attacks are a subclass of data poisoning attacks in adversarial machine learning used against different applications, such as malware detection. These types of attacks represent a serious threat to detection systems in environments having high noise rate or uncertainty, such as complex networks and Internet of Thing (IoT). Recent work in the literature has suggested using the $K$-Nearest Neighboring (KNN) algorithm to defend against such attacks. However, such an approach can suffer from low to wrong detection accuracy. In this paper, we design an architecture to tackle the Android malware detection problem in IoT systems. We develop an attack mechanism based on Silhouette clustering method, modified for mobile Android platforms. We proposed two Convolutional Neural Network (CNN)-type deep learning algorithms against this \emph{Silhouette Clustering-based Label Flipping Attack (SCLFA)}. We show the effectiveness of these two defense algorithms - \emph{Label-based Semi-supervised Defense (LSD)} and \emph{clustering-based Semi-supervised Defense (CSD)} - in correcting labels being attacked. We evaluate the performance of the proposed algorithms by varying the various machine learning parameters on three Android datasets: Drebin, Contagio, and Genome and three types of features: API, intent, and permission. Our evaluation shows that using random forest feature selection and varying ratios of features can result in an improvement of up to 19\% accuracy when compared with the state-of-the-art method in the literature.

In this era of explainable and interpretable Machine Learning, one merely cannot be content with simply training the model and obtaining predictions from it. To be able to really make an impact and obtain good results, we should also be able to probe and investigate our models. Apart from that, algorithmic fairness constraints and bias should also be clearly kept in mind before going ahead with the model. Investigating a model requires asking a lot of questions and one needs to have an acumen of a detective to probe and look for issues and inconsistencies within the models. Also, such a task is usually complex requiring to write a lot of custom code.

Many recent developments in network analysis have focused on multilayer networks, which one can use to encode time-dependent interactions, multiple types of interactions, and other complications that arise in complex systems. Like their monolayer counterparts, multilayer networks in applications often have mesoscale features, such as community structure. A prominent type of method for inferring such structures is the employment of multilayer stochastic block models (SBMs). A common (but inadequate) assumption of these models is the sampling of edges in different layers independently, conditioned on community labels of the nodes. In this paper, we relax this assumption of independence by incorporating edge correlations into an SBM-like model. We derive maximum-likelihood estimates of the key parameters of our model, and we propose a measure of layer correlation that reflects the similarity between connectivity patterns in different layers. Finally, we explain how to use correlated models for edge prediction in multilayer networks. By taking into account edge correlations, prediction accuracy improves both in synthetic networks and in a temporal network of shoppers who are connected to previously-purchased grocery products.

Motivated by the need of the linking records across various databases, we propose a novel graphical model based classifier that uses a mixture of Poisson distributions with latent variables. The idea is to derive insight into each pair of hypothesis records that match by inferring its underlying latent rate of error using Bayesian Modeling techniques. The novel approach of using gamma priors for learning the latent variables along with supervised labels is unique and allows for active learning. The naive assumption is made deliberately as to the independence of the fields to propose a generalized theory for this class of problems and not to undermine the hierarchical dependencies that could be present in different scenarios. This classifier is able to work with sparse and streaming data. The application to record linkage is able to meet several challenges of sparsity, data streams and varying nature of the data-sets.

Recent advances in supervised machine learning have improved diagnostic accuracy and prediction of treatment outcomes, in some cases surpassing the performance of clinicians.1 In supervised machine learning, a mathematical function is constructed via automated analysis of training data, which consists of input features (such as retinal images) and output labels (such as the grade of macular edema). With large training data sets and minimal human guidance, a computer learns to generalize from the information contained in the training data. The result is a mathematical function, a model, that can be used to map a new record to the corresponding diagnosis, such as an image to grade macular edema. Although machine learning–based models for classification or for predicting a future health state are being developed for diverse clinical applications, evidence is lacking that deployment of these models has improved care and patient outcomes.2 One barrier to demonstrating such improvement is the basis used to assess the performance of a model.

Human mobility has a significant impact on several layers of society, from infrastructural planning and economics to the spread of diseases and crime. Representing the system as a complex network, in which nodes are assigned to regions (e.g., a city) and links indicate the flow of people between two of them, physics-inspired models have been proposed to quantify the number of people migrating from one city to the other. Despite the advances made by these models, our ability to predict the number of commuters and reconstruct mobility networks remains limited. Here, we propose an alternative approach using machine learning and 22 urban indicators to predict the flow of people and reconstruct the intercity commuters network. Our results reveal that predictions based on machine learning algorithms and urban indicators can reconstruct the commuters network with 90.4% of accuracy and describe 77.6% of the variance observed in the flow of people between cities. We also identify essential features to recover the network structure and the urban indicators mostly related to commuting patterns. As previously reported, distance plays a significant role in commuting, but other indicators, such as Gross Domestic Product (GDP) and unemployment rate, are also driven-forces for people to commute. We believe that our results shed new lights on the modeling of migration and reinforce the role of urban indicators on commuting patterns. Also, because link-prediction and network reconstruction are still open challenges in network science, our results have implications in other areas, like economics, social sciences, and biology, where node attributes can give us information about the existence of links connecting entities in the network.

This paper introduces a new dataset called "ToyADMOS" designed for anomaly detection in machine operating sounds (ADMOS). To the best our knowledge, no large-scale datasets are available for ADMOS, although large-scale datasets have contributed to recent advancements in acoustic signal processing. This is because anomalous sound data are difficult to collect. To build a large-scale dataset for ADMOS, we collected anomalous operating sounds of miniature machines (toys) by deliberately damaging them. The released dataset consists of three sub-datasets for machine-condition inspection, fault diagnosis of machines with geometrically fixed tasks, and fault diagnosis of machines with moving tasks. Each sub-dataset includes over 180 hours of normal machine-operating sounds and over 4,000 samples of anomalous sounds collected with four microphones at a 48-kHz sampling rate. The dataset is freely available for download at https://github.com/YumaKoizumi/ToyADMOS-dataset

Waveform physiological data is important in the treatment of critically ill patients in the intensive care unit. Such recordings are susceptible to artefacts, which must be removed before the data can be re-used for alerting or reprocessed for other clinical or research purposes. The current gold-standard is human annotation, which is painstaking when recordings span many days and has question marks over its reproducibility. In this work, we present DeepClean; a prototype self-supervised artefact detection system using a convolutional variational autoencoder deep neural network that avoids costly manual annotation, requiring only easily-obtained `good' data for training. For a test case with invasive arterial blood pressure, we demonstrate that our algorithm can detect the presence of an artefact within a 10-second sample of data with sensitivity and specificity around 90\%. Furthermore, DeepClean was able to identify regions of artefact within such samples with high accuracy and we show that it significantly outperforms a baseline principle component analysis approach in both signal reconstruction and artefact detection. DeepClean learns a generative model and therefore may also be used for imputation of missing data. Accurate removal of artefacts reduces both bias and uncertainty in clinical assessment and the false negative rate of intensive care unit alarms, and is therefore a key component in providing optimal clinical care.