Search results

This chapter introduces a risk control framework on credit card fraud instead of providing a solely binary classifier model. The anomaly detection approach is adopted to identify fraud events as the outliers of the reconstruction error of a trained autoencoder (AE). The trained AE shows fitness and robustness on the normal transactions and heterogeneous behavior on fraud activities. The cost of false-positive normal transactions is controlled, and the loss of false-negative frauds can be evaluated by the thresholds from the percentiles of reconstruction error of trained AE on normal transactions. To align the risk assessment of the economic and financial situation, the risk manager can adjust the threshold to meet the risk control requirements. Using the 95th percentile as the threshold, the rate of wrongly detecting normal transactions is controlled at 5% and the true positive rate is 86%. For the 99th percentile threshold, the well-controlled false positive rate is around 1% and 83% for the truly detecting fraud activities. The performance of a false positive rate and the true positive rate is competitive with other supervised learning algorithms.

In the International Classification of Functioning, Disability and Health (ICF) 2001, the World Health Organization (WHO) defines disability as: ‘an umbrella term for impairments, activity limitations and participation restrictions. It denotes the negative aspects of the interaction between an individual (with a health condition) and that individual's contextual factors (environmental and personal factors)’, with environmental factors including assistance from other people, from equipment and from formal sources. WHO previously defined disability, in the context of health experience, as “any restriction or lack (resulting from impairment) of ability to perform an action in the manner or within the range considered normal for a human being” (World Health Organization, 1980, p. 28).

This paper discusses data-collection strategies that use digitized historical newspaper archives to study social conflicts and social movements from a global and historical perspective focusing on nationalist movements. I present an analysis of State-Seeking Nationalist Movements (SSNMs) dataset I, which includes news articles reporting on state-seeking activities throughout the world from 1804 to 2013 using the New York Times and the Guardian/Observer. In discussing this new source of data and its relative value, I explain the various benefits and challenges involved with using digitized historical newspaper archives for world-historical analysis of social movements. I also introduce strategies that can be used to detect and minimize some potential sources of bias. I demonstrate the utility of the strategies introduced in this paper by assessing the reliability of the SSNM dataset I and by comparing it to alternative datasets. The analysis presented in the paper also compares the labor-intensive manual data-coding strategies to automated approaches. In doing so, it explains why labor-intensive manual coding strategies will continue to be an invaluable tool for world-historical sociologists in a world of big data.

Control charts are designed to be effective in detecting a shift in the distribution of a process. Typically, these charts assume that the data for these processes follow an approximately normal distribution or some known distribution. However, if a data-generating process has a large proportion of zeros, that is, the data is intermittent, then traditional control charts may not adequately monitor these processes. The purpose of this study is to examine proposed control chart methods designed for monitoring a process with intermittent data to determine if they have a sufficiently small percentage of false out-of-control signals. Forecasting techniques for slow-moving/intermittent product demand have been extensively explored as intermittent data is common to operational management applications (Syntetos & Boylan, 2001, 2005, 2011; Willemain, Smart, & Schwarz, 2004). Extensions and modifications of traditional forecasting models have been proposed to model intermittent or slow-moving demand, including the associated trends, correlated demand, seasonality and other characteristics (Altay, Litteral, & Rudisill, 2012). Croston’s (1972) method and its adaptations have been among the principal procedures used in these applications. This paper proposes adapting Croston’s methodology to design control charts, similar to Exponentially Weighted Moving Average (EWMA) control charts, to be effective in monitoring processes with intermittent data. A simulation study is conducted to assess the performance of these proposed control charts by evaluating their Average Run Lengths (ARLs), or equivalently, their percent of false positive signals.

The practice of insuring essentially involves the determination and assignment of risk to individuals. Such determinations are made almost exclusively on the basis of statistical models. As such, the determination of an individual's risk in relation to a particular form of insurance, and thus ultimately to the determination of the cost and availability of that insurance for the individual, is made in relation to her inclusion in certain statistical groups. However, a number of questions, both practical and philosophical, can be raised about the way in which an individual is assessed upon the basis of such statistical modeling. In this paper, I explore some of these issues in relation to questions of fairness. I begin by examining the basic structure of statistical risk assessment for insurance purposes. I argue that the underlying ethical concern involved with such cases involves the manner in which the attributes of the statistical groups used for insurance purposes can be said to fairly represent the individual qua individual. As such, I go on to explore the general philosophical issues involved in applying statistical models to individuals and the fairness of using such applications to make determinations about individuals for insurance purposes.

Resource constraints at all levels of the criminal justice system as well as the lack of a widely accepted, validated screening scale have made it difficult to screen adequately for serious mental illnesses (SMI) in offender populations. This study examined the use of the K6 scale, a recently developed and validated screening tool for SMI, using a sample of past-year arrestees. Among the main findings were that 18% of the sample screened positive for SMI. In contrast, commonly used screening questions misidentified a large proportion of arrestees with SMI. Based on these findings, we recommend the use of K6 scale to more accurately identify offenders with SMI.

Students with emotional and behavioral disorders (E/BD) receive educational and related services within a continuum of placement options per the Individual with Disabilities Education Act. The continuum of placement options ranges from fully included general education type classrooms to more restrictive environments such as alternative education settings, residential facilities, and schools within secure juvenile justice facilities. A specific placement option is based on the individualized academic and social needs of the student and includes the least restrictive environment to meet those needs. After the IFSP or IEP team develops a student's IFSP or IEP, then the team makes a placement decision. Multiple factors influence initial placement decisions including an overall reluctance to identify students with E/BD, false positives and negatives, co-morbidity, and disproportionality. Other factors may influence a temporary or long-term change in placement such as inappropriate student behavior and/or academic failure. No matter the placement, the educational services provided within each should be evidence-based, implemented with fidelity, be individualized, and be socially valid.

Goffman (1963) provided us with an explanation of the operation of stigma in microinteractional contexts. However, his definition and explication of the experiences and processes of stigmatization predate what many consider to be the most major shift in discourse and categorization to develop in the twentieth century – the rise of the language of risk. In this chapter, I discuss the intersections of risk discourse and stigma. Drawing on my empirical research with families affected by incarceration, I illustrate the shift toward structural stigma as an exercise of power and governance. I argue that contemporary “common-sense” understandings and usage of the term stigma emphasize negative individual interactions while ignoring the ways that risk categorizations, even in seemingly benign contexts, create structural disadvantage and serve to “other” stigmatized individuals. Singular focus on stigma at the microinteractional level, particularly in destigmatization campaigns, obscures the pervasive structural stigma couched in the language of risk management that permits systematic marginalization.

This research navigates the confluence of data analytics, machine learning, and artificial intelligence to revolutionize the management of urban services in smart cities. The study thoroughly investigated with advanced tools to scrutinize key performance indicators integral to the functioning of smart cities, thereby enhancing leadership and decision-making strategies. Our work involves the implementation of various machine learning models such as Logistic Regression, Support Vector Machine, Decision Tree, Naive Bayes, and Artificial Neural Networks (ANN), to the data. Notably, the Support Vector Machine and Bernoulli Naive Bayes models exhibit robust performance with an accuracy rate of 70% precision score. In particular, the study underscores the employment of an ANN model on our existing dataset, optimized using the Adam optimizer. Although the model yields an overall accuracy of 61% and a precision score of 58%, implying correct predictions for the positive class 58% of the time, a comprehensive performance assessment using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metrics was necessary. This evaluation results in a score of 0.475 at a threshold of 0.5, indicating that there's room for model enhancement. These models and their performance metrics serve as a key cog in our data analytics pipeline, providing decision-makers and city leaders with actionable insights that can steer urban service management decisions. Through real-time data availability and intuitive visualization dashboards, these leaders can promptly comprehend the current state of their services, pinpoint areas requiring improvement, and make informed decisions to bolster these services. This research illuminates the potential for data analytics, machine learning, and AI to significantly upgrade urban service management in smart cities, fostering sustainable and livable communities. Moreover, our findings contribute valuable knowledge to other cities aiming to adopt similar strategies, thus aiding the continued development of smart cities globally.