Performance metrics measuring in Financial Integrity systems are crucial for maintaining an efficient and cost effective operation. An important performance metric is False Positive Rate. This metric cannot be directly monitored since we don't know for sure if a user is bad once blocked. We present a statistical method based on survey theory and causal inference methods to estimate the false positive rate of the system or a single blocking policy. We also suggest a new approach of outcome matching that in some cases including empirical data outperformed other commonly used methods. The approaches described in this paper can be applied in other Integrity domains such as Cyber Security.

Disease identification is a core, routine activity in observational health research. Cohorts impact downstream analyses, such as how a condition is characterized, how patient risk is defined, and what treatments are studied. It is thus critical to ensure that selected cohorts are representative of all patients, independently of their demographics or social determinants of health. While there are multiple potential sources of bias when constructing phenotype definitions which may affect their fairness, it is not standard in the field of phenotyping to consider the impact of different definitions across subgroups of patients. In this paper, we propose a set of best practices to assess the fairness of phenotype definitions. We leverage established fairness metrics commonly used in predictive models and relate them to commonly used epidemiological cohort description metrics. We describe an empirical study for Crohn's disease and diabetes type 2, each with multiple phenotype definitions taken from the literature across two sets of patient subgroups (gender and race). We show that the different phenotype definitions exhibit widely varying and disparate performance according to the different fairness metrics and subgroups. We hope that the proposed best practices can help in constructing fair and inclusive phenotype definitions.

In a recent Nature Medicine journal study, researchers develop an artificial intelligence (AI)-based model to detect Parkinson's disease (PD) and track its progression from nocturnal breathing signals. Since PD is the fastest-growing neurological disease worldwide, there is an urgent need for novel diagnostic biomarkers that can detect the disease at an early stage. Currently, there are no drugs capable of reversing or ceasing PD progression. Furthermore, PD is typically diagnosed based on changes in motor functions, such as tremors and rigidity. The assessment of PD progression primarily relies on patient self-reporting; however, clinicians also use the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) for qualitative PD assessment. Some existing PD biomarkers, including cerebrospinal fluid, blood biochemical, and neuroimaging, have shown promising results for their potential utility in the early diagnosis of this disease.

Defect prediction is one of the most popular research topics due to its potential to minimize software quality assurance efforts. Existing approaches have examined defect prediction from various perspectives such as complexity and developer metrics. However, none of these consider programming style for defect prediction. This paper aims at analyzing the impact of stylistic metrics on both within-project and crossproject defect prediction. For prediction, 4 widely used machine learning algorithms namely Naive Bayes, Support Vector Machine, Decision Tree and Logistic Regression are used. The experiment is conducted on 14 releases of 5 popular, open source projects. F1, Precision and Recall are inspected to evaluate the results. Results reveal that stylistic metrics are a good predictor of defects.

Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity. Achieving group fairness in Federated Learning (FL) is challenging because mitigating bias inherently requires using the sensitive attribute values of all clients, while FL is aimed precisely at protecting privacy by not giving access to the clients' data. As we show in this paper, this conflict between fairness and privacy in FL can be resolved by combining FL with Secure Multiparty Computation (MPC) and Differential Privacy (DP). In doing so, we propose a method for training group-fair ML models in cross-device FL under complete and formal privacy guarantees, without requiring the clients to disclose their sensitive attribute values. Empirical evaluations on real world datasets demonstrate the effectiveness of our solution to train fair and accurate ML models in federated cross-device setups with privacy guarantees to the users.

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may not be ideal for data sets in which the number of speakers is very small. This study investigates ten different data split methods for five languages with minimal ASR training resources. We find that (1) model performance varies greatly depending on which speaker is selected for testing; (2) the average word error rate (WER) across all held-out speakers is comparable not only to the average WER over multiple random splits but also to any given individual random split; (3) WER is also generally comparable when the data is split heuristically or adversarially; (4) utterance duration and intensity are comparatively more predictive factors of variability regardless of the data split. These results suggest that the widely used hold-speakers-out approach to ASR data partitioning can yield results that do not reflect model performance on unseen data or speakers. Random splits can yield more reliable and generalizable estimates when facing data sparsity.

Objective: To develop and validate an automated method for bedside monitoring of sleep state fluctuations in neonatal intensive care units. Methods: A deep learning -based algorithm was designed and trained using 53 EEG recordings from a long-term (a)EEG monitoring in 30 near-term neonates. The results were validated using an external dataset from 30 polysomnography recordings. In addition to training and validating a single EEG channel quiet sleep detector, we constructed Sleep State Trend (SST), a bedside-ready means for visualizing classifier outputs. Results: The accuracy of quiet sleep detection in the training data was 90%, and the accuracy was comparable (85-86%) in all bipolar derivations available from the 4-electrode recordings. The algorithm generalized well to an external dataset, showing 81% overall accuracy despite different signal derivations. SST allowed an intuitive, clear visualization of the classifier output. Conclusions: Fluctuations in sleep states can be detected at high fidelity from a single EEG channel, and the results can be visualized as a transparent and intuitive trend in the bedside monitors. Significance: The Sleep State Trend (SST) may provide caregivers a real-time view of sleep state fluctuations and its cyclicity.

Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased decisions. We present a novel debiasing technique, Fairness-aware Rate Maximization (FaRM), that removes protected information by making representations of instances belonging to the same protected attribute class uncorrelated, using the rate-distortion function. FaRM is able to debias representations with or without a target task at hand. FaRM can also be adapted to remove information about multiple protected attributes simultaneously. Empirical evaluations show that FaRM achieves state-of-the-art performance on several datasets, and learned representations leak significantly less protected attribute information against an attack by a non-linear probing network.

Currency is used almost everywhere to facilitate business. In most developing countries, especially the ones in Africa, tangible notes are predominantly used in everyday financial transactions. One of these countries, Ethiopia, is believed to have one of the world highest rates of blindness (1.6%) and low vision (3.7%). There are around 4 million visually impaired people; With 1.7 million people being in complete vision loss. Those people face a number of challenges when they are in a bus station, in shopping centers, or anywhere which requires the physical exchange of money. In this paper, we try to provide a solution to this issue using AI/ML applications. We developed an Android and IOS compatible mobile application with a model that achieved 98.9% classification accuracy on our dataset. The application has a voice integrated feature that tells the type of the scanned currency in Amharic, the working language of Ethiopia. The application is developed to be easily accessible by its users. It is build to reduce the burden of visually impaired people in Ethiopia.

Tabular data typically contains private and important information; thus, precautions must be taken before they are shared with others. Although several methods (e.g., differential privacy and k-anonymity) have been proposed to prevent information leakage, in recent years, tabular data synthesis models have become popular because they can well trade-off between data utility and privacy. However, recent research has shown that generative models for image data are susceptible to the membership inference attack, which can determine whether a given record was used to train a victim synthesis model. In this paper, we investigate the membership inference attack in the context of tabular data synthesis. We conduct experiments on 4 state-of-the-art tabular data synthesis models under two attack scenarios (i.e., one black-box and one white-box attack), and find that the membership inference attack can seriously jeopardize these models. We next conduct experiments to evaluate how well two popular differentially-private deep learning training algorithms, DP-SGD and DP-GAN, can protect the models against the attack. Our key finding is that both algorithms can largely alleviate this threat by sacrificing the generation quality.