A Social Science Approach Using Big Data for City Planning

2022 | International Conference on Information Systems | Citations: 0

Authors: Goh, Kim Huat; Boh, Waifong; Dommaraju, Premchand

Abstract: Cities bring about economic dynamism through positive economic externalities; h ... Expand

Abstract: Cities bring about economic dynamism through positive economic externalities; however, the concentration of people in dense locations has its costs -epidemics, social unrest, pollution, and congestion are some of the ills of cities. As cities evolve, they experience stress, and fault lines appear; the ability to pulse a city and provide early warning of these fault lines can prove advantageous for policymakers in managing and planning for cities. This paper outlines a research program that developed a city scanning tool to measure cities and detect aberrations as they surface. We aggregated data from various industry partners, governmental agencies, and public online sources to develop the measurement metric and applied social science theories to analyze and interpret the results. The results of this study contribute to information system (IS) research by showcasing the role IS research in city planning and for societal good. Collapse

Topics: social media healthcare data big data privacy Health Insurance Portability and Accountability Act

Methods: natural language processing archival research literature study latent dirichlet allocation survey

Theories: symbolic interaction theory social sciences theory theory of economic growth

Anomaly Detection in Cybersecurity Datasets via Cooperative Co-evolution-based Feature Selection

2022 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Rashid, A. N. M. Bazlur; Ahmed, Mohiuddin; Sikos, Leslie F.; Haskell-Dowland, Paul

Abstract: Anomaly detection from Big Cybersecurity Datasets is very important; however, th ... Expand

Abstract: Anomaly detection from Big Cybersecurity Datasets is very important; however, this is a very challenging and computationally expensive task. Feature selection (FS) is an approach to remove irrelevant and redundant features and select a subset of features, which can improve the machine learning algorithms’ performance. In fact, FS is an effective preprocessing step of anomaly detection techniques. This article’s main objective is to improve and quantify the accuracy and scalability of both supervised and unsupervised anomaly detection techniques. In this effort, a novel anomaly detection approach using FS, called Anomaly Detection Using Feature Selection (ADUFS), has been introduced. Experimental analysis was performed on five different benchmark cybersecurity datasets with and without feature selection and the performance of both supervised and unsupervised anomaly detection techniques were investigated. The experimental results indicate that instead of using the original dataset, a dataset with a reduced number of features yields better performance in terms of true positive rate (TPR) and false positive rate (FPR) than the existing techniques for anomaly detection. For example, with FS, a supervised anomaly detection technique, multilayer perception increased the TPR by over 200% and decreased the FPR by about 97% for the KDD99 dataset. Similarly, with FS, an unsupervised anomaly detection technique, local outlier factor increased the TPR by more than 40% and decreased the FPR by 15% and 36% for Windows 7 and NSL-KDD datasets, respectively. In addition, all anomaly detection techniques require less computational time when using datasets with a suitable subset of features rather than entire datasets. Furthermore, the performance results have been compared with six other state-of-the-art techniques based on a decision tree (J48). Collapse

Topics: Microsoft Windows IT security intrusion detection system spreadsheet missing data

Methods: anomaly detection machine learning computational algorithm experiment simulation

Theories: co-evolution theory

Data engineering for fraud detection

2021 | Decision Support Systems | Citations: 1

Authors: Baesens, Bart; Höppner, Sebastiaan; Verdonck, Tim

Abstract: Financial institutions increasingly rely upon data-driven methods for developing ... Expand

Abstract: Financial institutions increasingly rely upon data-driven methods for developing fraud detection systems, which are able to automatically detect and block fraudulent transactions. From a machine learning perspective, the task of detecting suspicious transactions is a binary classification problem and therefore many techniques can be applied. Interpretability is however of utmost importance for the management to have confidence in the model and for designing fraud prevention strategies. Moreover, models that enable the fraud experts to understand the underlying reasons why a case is flagged as suspicious will greatly facilitate their job of investigating the sus­ picious transactions. Therefore, we propose several data engineering techniques to improve the performance of an analytical model while retaining the interpretability property. Our data engineering process is decomposed into several feature and instance engineering steps. We illustrate the improvement in performance of these data engineering steps for popular analytical models on a real payment transactions data set. Collapse

Topics: electronic authentication fraud detection electronic commerce online banking mobile application

Methods: machine learning descriptive statistic experiment feature engineering mathematical model

Autoencoders for strategic decision support

2021 | Decision Support Systems | Citations: 0

Authors: Verboven, Sam; Berrevoets, Jeroen; Wuytens, Chris; Baesens, Bart; Verbeke, Wouter

Abstract: In the majority of executive domains, a notion of normality is involved in most ... Expand

Abstract: In the majority of executive domains, a notion of normality is involved in most strategic decisions. However, few data-driven tools that support strategic decision-making are available. We introduce and extend the use of autoencoders to provide strategically relevant granular feedback. A first experiment indicates that experts are inconsistent in their decision making, highlighting the need for strategic decision support. Furthermore, using two large industry-provided human resources datasets, the proposed solution is evaluated in terms of ranking accuracy, synergy with human experts, and dimension-level feedback. This three-point scheme is validated using (a) synthetic data, (b) the perspective of data quality, (c) blind expert validation, and (d) transparent expert evaluation. Our study confirms several principal weaknesses of human decision-making and stresses the importance of synergy between a model and humans. Moreover, unsupervised learning and in particular the autoencoder are shown to be valuable tools for strategic decision-making. Collapse

Topics: decision making data quality decision support human resource management business intelligence

Methods: autoencoder data transformation experiment anomaly detection isolation forest

Design of electronic-commerce recommendation systems based on outlier mining

2021 | Electronic Markets | Citations: 0

Authors: Xia, Huosong; Wei, Xiang; An, Wuyue; Zhang, Zuopeng Justin; Sun, Zelin

Abstract: Prior studies mostly consider outliers as noise data and eliminate them, resulti ... Expand

Abstract: Prior studies mostly consider outliers as noise data and eliminate them, resulting in the loss of outlier knowledge. Based on the existing technology of recommendation systems and outlier detection, this research develops a new e-commerce recommended model from the perspective of outlier knowledge management. Specifically, we apply outlier data mining and integrate local outlier coefficients into the recommendation algorithm. The experimental results show that the proposed outlier extent recommendation model performs better than the traditional recommendation systems based on the collaborative filtering algorithm, which can effectively improve the quality of recommendation, enhance customer satisfaction and loyalty, and create potential benefits for the business. Our study contributes to the design of e-commerce recommending systems with some novel ideas and provides useful guidelines for developing the outlier extent. Collapse

Topics: recommender system electronic commerce collaborative filtering customer satisfaction knowledge management

Methods: computational algorithm experiment local outlier factor machine learning anomaly detection

Trajectory Outlier Detection: Algorithms, Taxonomies, Evaluation, and Open Challenges

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Belhadi, Asma; Djenouri, Youcef; Lin, Jerry Chun-Wei; Cano, Alberto

Abstract: Detecting abnormal trajectories is an important task in research and industrial ... Expand

Abstract: Detecting abnormal trajectories is an important task in research and industrial applications, which has attracted considerable attention in recent decades. This work studies the existing trajectory outlier detection algorithms in different industrial domains and applications, including maritime, smart urban transportation, video surveillance, and climate change domains. First, we review several algorithms for trajectory outlier detection. Second, different taxonomies are proposed regarding application-, output-, and algorithm-based levels. Third, evaluation of 10 trajectory outlier detection algorithms is performed on small, large, and big trajectory databases. Finally, future challenges and open issues with regard to trajectory outliers are derived and discussed. This survey offers a general overview of existing trajectory outlier detection algorithms in industrial informatics applications. As a result, mature solutions may be further developed by data mining and machine learning communities. Collapse

Topics: database system global navigation satellite system climate change big data mobile phone

Methods: computational algorithm anomaly detection machine learning experiment survey

Theories: Dempster-Shafer theory

An Automatic Ontology Generation Framework with An Organizational Perspective

2020 | HICSS | Citations: 0

Authors: Elnagar, Samaa; Yoon, Victoria; Thomas, Manoj A

Abstract: Ontologies have been known for their powerful semantic representation of knowled ... Expand

Abstract: Ontologies have been known for their powerful semantic representation of knowledge. However, ontologies cannot automatically evolve to reflect updates that occur in respective domains. To address this limitation, researchers have called for automatic ontology generation from unstructured text corpus. Unfortunately, systems that aim to generate ontologies from unstructured text corpus are domain-specific and require manual intervention. In addition, they suffer from uncertainty in creating concept linkages and difficulty in finding axioms for the same concept. Knowledge Graphs (KGs) has emerged as a powerful model for the dynamic representation of knowledge. However, KGs have many quality limitations and need extensive refinement. This research aims to develop a novel domain-independent automatic ontology generation framework that converts unstructured text corpus into domain consistent ontological form. The framework generates KGs from unstructured text corpus as well as refine and correct them to be consistent with domain ontologies. The power of the proposed automatically generated ontology is that it integrates the dynamic features of KGs and the quality features of ontologies. Collapse

Topics: knowledge representation web page predicate logic knowledge graph social media

Methods: ontological modelling computational algorithm domain ontology DOLCE ontology WordNet

Autoencoder Neural Networks versus External Auditors: Detecting Unusual Journal Entries in Financial Statement Audits

2020 | HICSS | Citations: 1

Authors: Schultz, Martin; Tropmann-Frick, Marina

Abstract: With the increasing complexity of business processes in today’s organizations an ... Expand

Abstract: With the increasing complexity of business processes in today’s organizations and the ever-growing amount of structured accounting data, identifying erroneous or fraudulent business transactions and corresponding journal entries poses a major challenge for public accountants at annual audits. In current audit practice, mainly static rules are applied which check only a few attributes of a journal entry for suspicious values. Encouraged by numerous successful adoptions of deep learning in various domains we suggest an approach for applying autoencoder neural networks to detect unusual journal entries within individual financial accounts. The identified journal entries are compared to a list of entries that were manually tagged by two experienced auditors. The comparison shows high f-scores and high recall for all analyzed financial accounts. Additionally, the autoencoder identifies anomalous journal entries that have been overlooked by the auditors. The results underpin the applicability and usefulness of deep learning techniques in financial statement audits. Collapse

Topics: accounting enterprise resource planning Python online learning system analytical information system

Methods: data transformation autoencoder machine learning deep learning anomaly detection

Prediction of Airline Delays based on Machine Learning Algorithms

2019 | Americas Conference on Information Systems | Citations: 0

Authors: Dand, Alok; Saeed, Khawaja; Yildirim, Bayram

Abstract: Every year around 20% of all flights are delayed or canceled. The costs of thes ... Expand

Abstract: Every year around 20% of all flights are delayed or canceled. The costs of these events to the airline companies and passengers are in billions of dollars each year. According to a report published in 2010 by Research (NEXTOR), around half of the total cost (direct and indirect) is paid by the passenger. The goal of this study is to predict airline delays using binary supervised and unsupervised machine learning classification algorithms using the US Domestic Flights data from 2015-2017. We use an expanded set of variables some of which are subject to decisional control of the airlines to help improve the predictions. Different performance measures such as prediction accuracy, recall rates, receiver operation characteristics -area under the curve scores were used to evaluate the efficacy of different algorithms. Collapse

Topics: database system fraud detection IT career

Methods: machine learning computational algorithm decision tree classification random forest classification naïve bayes

Detecting Anomalous Online Reviewers: An Unsupervised Approach Using Mixture Models

2019 | Journal of Management Information Systems | Citations: 48

Authors: Kumar, Naveen; Venugopal, Deepak; Qiu, Liangfei; Kumar, Subodha

Abstract: Online reviews play a significant role in influencing decisions made by users in ... Expand

Abstract: Online reviews play a significant role in influencing decisions made by users in day-to-day life. The presence of reviewers who deliberately post fake reviews for financial or other gains, however, negatively impacts both users and businesses. Unfortunately, automatically detecting such reviewers is a challenging problem since fake reviews do not seem out-of-place next to genuine reviews. In this paper, we present a fully unsupervised approach to detect anomalous behavior in online reviewers. We propose a novel hierarchical approach for this task in which we (1) derive distributions for key features that define reviewer behavior, and (2) combine these distributions into a finite mixture model. Our approach is highly generalizable and it allows us to seamlessly combine both univariate and multivariate distributions into a unified anomaly detection system. Most importantly, it requires no explicit labeling (spam/not spam) of the data. Our newly developed approach outperforms prior state-of-the-art unsupervised anomaly detection approaches. Collapse

Topics: social media email spam fake review deception detection online review

Methods: anomaly detection computational algorithm experiment machine learning unsupervised learning