Adversarial Outlier Detection Methods for Health Care Fraud

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Ekin, Tahir

Abstract: Outlier detection is widely used for identification of unusual suspicious patte ... Expand

Abstract: Outlier detection is widely used for identification of unusual suspicious patterns in health care fraud detection. However, the impact of adversarial perturbations on outliers and the related decisions are not well studied. In the health care fraud detection domain, standard practice does not consider health care billings being subject to intentional data manipulations. This paper presents a decision theoretic approach for outlier detection in adversarial environments. Proposed adversarial risk analysis-based framework allows incomplete information and adversarial perturbations on the data inputs. While the work with actual health care fraud data is ongoing, the proposed novel adversarial outlier detection method has the potential to support health care fraud audit decision support systems. KeywordsAdversarial unsupervised learning, adversarial risk analysis, health care fraud, fraud analytics, Bayesian. Collapse

Topics: fraud detection

Methods: anomaly detection unsupervised learning Monte Carlo simulation machine learning

Theories: game theory

Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models

2023 | HICSS | Citations: 0

Authors: García Pereira, Agustín; Porwol, Lukasz; Ojo, Adegboyega

Abstract: High-quality labelled datasets represent a cornerstone in the development of dee ... Expand

Abstract: High-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate the use of Isolation Forest (IF), an anomaly detection algorithm, to reduce noise in a large-scale, low-resolution alternative ground truth dataset used to train land use deep learning models. We use a modest-size, high-resolution and high-fidelity manually collected ground-truth dataset to calibrate Isolation Forest parameters and evaluate our approach, highlighting the relatively low cost of the methodology. Our data-centric methodology demonstrates the efficacy of deep learning methods coupled with IF to create mid-resolution land-use models and map products for agriculture using an alternative ground-truth dataset. Moreover, we compare our deep learning approach with a traditional algorithm used in remote sensing and evaluate the spatial transferability of the created models. Finally, we reflect upon the lessons learnt and future work. Collapse

Topics: cloud computing Python programming language open source geographic information system

Methods: experiment deep learning computational algorithm isolation forest random forest classification

Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework

2023 | Information Systems Frontiers | Citations: 0

Authors: Hajek, Petr; Abedin, Mohammad Zoynul; Sivarajah, Uthayasankar

Abstract: Mobile payment systems are becoming more popular due to the increase in the numb ... Expand

Abstract: Mobile payment systems are becoming more popular due to the increase in the number of smartphones, which, in turn, attracts the interest of fraudsters. Extant research has therefore developed various fraud detection methods using supervised machine learning. However, sufficient labeled data are rarely available and their detection performance is negatively affected by the extreme class imbalance in financial fraud data. The purpose of this study is to propose an XGBoost-based fraud detection framework while considering the financial consequences of fraud detection systems. The framework was empirically validated on a large dataset of more than 6 million mobile transactions. To demonstrate the effectiveness of the proposed framework, we conducted a comparative evaluation of existing machine learning methods designed for modeling imbalanced data and outlier detection. The results suggest that in terms of standard classification measures, the proposed semi-supervised ensemble model integrating multiple unsupervised outlier detection algorithms and an XGBoost classifier achieves the best results, while the highest cost savings can be achieved by combining random under-sampling and XGBoost methods. This study has therefore financial implications for organizations to make appropriate decisions regarding the implementation of effective fraud detection systems. Collapse

Topics: fraud detection mobile system mobile payment electronic payment Python

Methods: XGBoost machine learning anomaly detection supervised learning experiment

A Systematic Review of Anomaly Detection for Business Process Event Logs

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Ko, Jonghyeon; Comuzzi, Marco

Abstract: While a business process is most often executed following a normal path, anomali ... Expand

Abstract: While a business process is most often executed following a normal path, anomalies may sometimes arise and can be captured in event logs. Event log anomalies stem, for instance, from system malfunctioning or unexpected behavior of human resources involved in a process. To identify and possibly fix these, anomaly detection has emerged recently as a key discipline in process mining. In the paper, the authors present a systematic review of the literature on business process event log anomaly detection. The review aims at selecting systematically studies in the literature that have tackled the issue of event log anomaly detection, classifying existing approaches based on criteria emerging from previous literature reviews, and identifying those research directions in this field that have not been explored extensively. Based on the results of the review, the authors argue that future research should look more specifically into anomaly detection on event streams, extending the number of event log attributes considered to determine anomalies, and producing more standard labeled datasets to benchmark the techniques proposed. Collapse

Topics: process mining database system business process management

Methods: event log anomaly detection literature sample literature study survey

Cyber threat detection: Unsupervised hunting of anomalous commands (UHAC)

2023 | Decision Support Systems | Citations: 0

Authors: Kayhan, Varol O.; Agrawal, Manish; Shivendu, Shivendu

Abstract: The cyber security industry is rapidly adopting threat hunting as a proactive to ... Expand

Abstract: The cyber security industry is rapidly adopting threat hunting as a proactive tool for early and faster detection of suspected malicious actors. In this paper, we propose a machine learning-based method, Unsupervised Hunting of Anomalous Commands (UHAC), to detect text-based anomalous commands in security information and event management (SIEM) logs that are good candidates for threat hunting. A unique feature of the proposed method is that it first creates a feature set based on the augmentation of document-term and document-character matrices. Then, an autoencoder-based detector is trained on this feature set using a custom loss function. UHAC consis­ tently outperforms other feature sets and algorithms such as one-class support vector machine, density-based spatial clustering of applications with noise, and word-embedding based models such as word2vec. The UHAC detector identifies 84–89% of anomalies in the top 10% of the data. Findings have implications for cybersecurity analysts who perform threat hunting in SIEM logs for process auditing on endpoint devices. Collapse

Topics: IT security artificial intelligence Python decision support system email phishing

Methods: autoencoder data transformation DBSCAN anomaly detection machine learning

Unsupervised Threat Hunting using Continuous Bag of Terms and Time (CBoTT)

2023 | International Conference on Information Systems | Citations: 0

Authors: Kayhan, Varol; Shivendu, Shivendu; Behnia, Rouzbeh; Daniel, Clinton; Agrawal, Manish

Abstract: Threat hunting is sifting through system logs to detect malicious activities th ... Expand

Abstract: Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised framework, called continuous bag-of-terms-and-time (CBoTT), and publish its application programming interface (API) to help researchers and cybersecurity analysts perform anomaly-based threat hunting among SIEM logs geared toward process auditing on endpoint devices. Analyses show that our framework consistently outperforms benchmark approaches. When logs are sorted by likelihood of being an anomaly (from most likely to least), our approach identifies anomalies at higher percentiles (between 1.82-6.46) while benchmark approaches identify the same anomalies at lower percentiles (between 3.25-80.92). This framework can be used by other researchers to conduct benchmark analyses and cybersecurity analysts to find anomalies in SIEM logs. Collapse

Topics: IT security application programming interface Hadoop Distributed File System website web analytics

Methods: natural language processing artificial neural network support vector machine term frequency–inverse document frequency DBSCAN

What Disrupts Flow in Office Work? The Impact of Frequency and Relevance of IT-Mediated Interruptions

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Nadj, Mario; Rissler, Raphael; Adam, Marc; Knierim, Michael; Li, Maximilian; Maedche, Alexander; Riedl, René

Abstract: Flow, the holistic sensation people experience when they act with total involve ... Expand

Abstract: Flow, the holistic sensation people experience when they act with total involvement, is a known driver for desired work outcomes like task performance. However, the increasing ubiquity of IT at work can disrupt employees' flow. Thus, the impact of IT-mediated interruptions on flow warrants more attention in research and practice. We conducted a NeuroIS laboratory experiment focusing on a typical office work task-an invoice matching task (i.e., matching customer payments to invoices). We manipulated interruption frequency (low, high) and content relevance (irrelevant, relevant) to study the impact of interruptions on self-reported flow, its dimensions, and high-frequency heart rate variability (HF-HRV; calculated from electrocardiography recordings) as a proxy for parasympathetic nervous system (PNS) activation. We found that content relevance moderated the relationship between interruption frequency and self-reported flow and that these results vary along flow dimensions. Content relevance also moderated the relationship between interruption frequency and PNS activation. Furthermore, selfreported flow was positively associated with both perceived and objective task performance, while PNS Collapse

Topics: task productivity cognitive absorption Python technostress information system use

Methods: electrocardiography NeuroIS multivariate analysis of variance experiment descriptive statistic

Theories: flow theory

Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice

2023 | International Conference on Information Systems | Citations: 0

Authors: Schemmer, Max; Bartos, Andrea; Spitzer, Philipp; Hemmer, Patrick; Kühl, Niklas; Liebschner, Jonas; Satzger, Gerhard

Abstract: The true potential of human-AI collaboration lies in exploiting the complementa ... Expand

Abstract: The true potential of human-AI collaboration lies in exploiting the complementary capabilities of humans and AI to achieve a joint performance superior to that of the individual AI or human, i.e., to achieve complementary team performance (CTP). To realize this complementarity potential, humans need to exercise discretion in following AI's advice, i.e., appropriately relying on the AI's advice. While previous work has focused on building a mental model of the AI to assess AI recommendations, recent research has shown that the mental model alone cannot explain appropriate reliance. We hypothesize that, in addition to the mental model, human learning is a key mediator of appropriate reliance and, thus, CTP. In this study, we demonstrate the relationship between learning and appropriate reliance in an experiment with 100 participants. This work provides fundamental concepts for analyzing reliance and derives implications for the effective design of human-AI decision-making. Collapse

Topics: artificial intelligence decision making explainable artificial intelligence missing data organization learning

Methods: experiment structural equation modeling parametric test Student's t-test descriptive statistic

A Human-in-the-Loop Segmented Mixed-Effects Modeling Method for Analyzing Wearables Data

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Srinivasan, Karthik; Currim, Faiz; Ram, Sudha

Abstract: Wearables are an important source of big data, as they provide real-time high-re ... Expand

Abstract: Wearables are an important source of big data, as they provide real-time high-resolution data logs of health indicators of individuals. Higher-order associations between pairs of variables is common in wearables data. Representing higher-order association curves as piecewise linear segments in a regression model makes them more interpretable. However, existing methods for identifying the change points for segmented modeling either overfit or have low external validity for wearables data containing repeated measures. Therefore, we propose a human-in-the-loop method for segmented modeling of higher-order pairwise associations between variables in wearables data. Our method uses the smooth function estimated by a generalized additive mixed model to allow the analyst to annotate change point estimates for a segmented mixed-effects model, and thereafter employs Brent's constrained optimization procedure to fine-tune the manually provided estimates. We validate our method using three real-world wearables datasets. Our method not only outperforms state-of-the-art modeling methods in terms of prediction performance but also provides more interpretable results. Our study contributes to health data science in terms of developing a new method for interpretable modeling of wearables data. Our analysis uncovers interesting insights on higher-order associations for health researchers. Collapse

Topics: smart wearable device mobile system analytical information system human computer interaction human in the loop

Methods: design science wearables based research conceptual modelling hierarchical linear modeling computational algorithm

A Prototypical Dashboard for Knowledge-Based Expert Systems used for Real-Time Anomaly Handling in Smart Manufacturing

2023 | HICSS | Citations: 0

Authors: Stahmann, Philip

Abstract: The use of machine learning in digitized production increases potentials for pro ... Expand

Abstract: The use of machine learning in digitized production increases potentials for production automation. A milestone on the path to autonomous production is real-time anomaly detection. However, increasing complexity of production makes autonomous decisions difficult to understand for humans as central stakeholders. In this paper, we create a dashboard that incorporates elements from knowledge-based systems, requirements for real-time anomaly detection, and design guidelines for dashboards. Using design science research, the dashboard is designed, implemented and comprehensively evaluated with 98 participants. After the second design science iteration, the dashboard is approved in terms of usefulness and ease of use. Our research primarily contributes to practice, as our implementation constitutes a starting point for designing the interface between humans and autonomous production. We also contribute to academia as the dashboard is an instantiation in the research field of interface design for knowledge-based systems, which can be further developed in future research. Collapse

Topics: digital dashboard expert system production management industry 4.0 internet technology

Methods: survey anomaly detection qualitative interview survey design design guideline