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

Data Quality in Data Ecosystems: Towards a Design Theory

2022 | Americas Conference on Information Systems | Citations: 5

Authors: Altendeitering, Marcel; Dübler, Stephan; Guggenberger, Tobias

Abstract: Data quality is an important aspect for the success of data ecosystems. Sharing ... Expand

Abstract: Data quality is an important aspect for the success of data ecosystems. Sharing low-quality data causes large data preparation efforts, can disrupt the chain for value co-creation, and can damage the mutual trust among partners in the ecosystem. While there are many data quality tools available in literature and practice, there is limited knowledge on the peculiarities of assessing and managing data quality in data ecosystems. In this study, we present the results of a design science research project that was concerned with the development of design principles for ensuring data quality in data ecosystems. The proposed concept extends an existing ecosystem with an artifact that technically enforces data quality checks on shared data in the manufacturing domain. Our work aims to provide the prescriptive design knowledge needed for such systems. For practitioners, we offer generalized design principles that can inform custom implementations of data quality tools in data ecosystems. Collapse

Topics: digital ecosystem mobile application data quality Python Apache Spark

Methods: design principle design artifact design science design requirement qualitative interview

Enhancing Cubes with Models to Describe Multidimensional Data

2022 | Information Systems Frontiers | Citations: 0

Authors: Francia, Matteo; Marcel, Patrick; Peralta, Verónika; Rizzi, Stefano

Abstract: The Intentional Analytics Model (IAM) has been recently envisioned as a new para ... Expand

Abstract: The Intentional Analytics Model (IAM) has been recently envisioned as a new paradigm to couple OLAP and analytics. It relies on two basic ideas: (i) letting the user explore data by expressing her analysis intentions rather than the data she needs, and (ii) returning enhanced cubes, i.e., multidimensional data annotated with knowledge insights in the form of interesting model components (e.g., clusters). In this paper we contribute to give a proof-of-concept for the IAM vision by delivering an end-to-end implementation of describe, one of the five intention operators introduced by IAM. Among the research challenges left open in IAM, those we address are (i) automatically tuning the size of models (e.g., the number of clusters), (ii) devising a measure to estimate the interestingness of model components, (iii) selecting the most effective chart or graph for visualizing each enhanced cube depending on its features, and (iv) devising a visual metaphor to display enhanced cubes and interact with them. We assess the validity of our approach in terms of user effort for formulating intentions, effectiveness, efficiency, and scalability. Collapse

Topics: Python online analytical processing structured query language covid 19 JavaScript

Methods: cluster analysis design artifact experiment multidimensional modeling design science

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

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

Insurance Fraud and Isolation Forests

2021 | International Conference on Information Systems | Citations: 4

Authors: Debener, Jörn; Heinke, Volker; Kriebel, Johannes

Abstract: Fraud is a significant issue for insurers. Previous literature has mainly used ... Expand

Abstract: Fraud is a significant issue for insurers. Previous literature has mainly used supervised learning to detect insurance fraud. However, supervised learning must deal with significant difficulties in fraud detection, such as very few cases being labeled as fraud and overfitting to the outcomes of pre-existing fraud detection systems, which can lead to overlooking new fraud patterns. Unsupervised learning methods producing anomaly scores could be a remedy to improve insurance fraud detection systems. However, unsupervised learning must identify anomalies that are conceptionally meaningful for fraud. In this paper, we suggest a theoretical framework for choosing features to include in fraud detection models. We evaluate this framework using isolation forests for anomaly detection based on more than 32,000 automobile insurance claims. We further evaluate textual information based on concepts from deception detection in computational linguistics using straightforward cluster methods and state-of-the-art transformers. Collapse

Topics: fraud detection shapley additive explanation deception detection electronic mail expert system

Methods: isolation forest anomaly detection unsupervised learning BERT autoencoder

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

LogGAN: a Log-level Generative Adversarial Network for Anomaly Detection using Permutation Event Modeling

2021 | Information Systems Frontiers | Citations: 0

Authors: Xia, Bin; Bai, Yuxuan; Yin, Junjie; Li, Yun; Xu, Jian

Abstract: System logs that trace system states and record valuable events comprise a signi ... Expand

Abstract: System logs that trace system states and record valuable events comprise a significant component of any computer system in our daily life. Each log contains sufficient information (i.e., normal and abnormal instances) that assist administrators in diagnosing and maintaining the operation of systems. If administrators cannot detect and eliminate diverse and complex anomalies (i.e., bugs and failures) efficiently, running workflows and transactions, even systems, would break down. Therefore, the technique of anomaly detection has become increasingly significant and attracted a lot of research attention. However, current approaches concentrate on the anomaly detection analyzing a high-level granularity of logs (i.e., session) instead of detecting log-level anomalies which weakens the efficiency of responding anomalies and the diagnosis of system failures. To overcome the limitation, we propose an LSTM-based generative adversarial network for anomaly detection based on system logs using permutation event modeling named LogGAN, which detects log-level anomalies based on patterns (i.e., combinations of latest logs). On the one hand, the permutation event modeling mitigates the strong sequential characteristics of LSTM for solving the out-of-order problem caused by the arrival delays of logs. On the other hand, the generative adversarial network-based model mitigates the impact of imbalance between normal and abnormal instances to improve the performance of detecting anomalies. To evaluate LogGAN, we conduct extensive experiments on two real-world datasets, and the experimental results show the effectiveness of our proposed approach on the task of log-level anomaly detection. Collapse

Topics: Hadoop Distributed File System high-performance computing source code

Methods: anomaly detection experiment generative adversarial network isolation forest computational algorithm

Making the Newsvendor Smart – Order Quantity Optimization with ANNs for a Bakery Chain

2020 | Americas Conference on Information Systems | Citations: 0

Authors: Seubert, Franz; Stein, Nikolai; Taigel, Fabian; Winkelmann, Axel

Abstract: Accurate demand forecasting is particularly crucial for products with short she ... Expand

Abstract: Accurate demand forecasting is particularly crucial for products with short shelf life like bakery products. Over-and underestimation of customer demand affects not only profit margins of bakeries but is also responsible for 600,000 metric tons of food waste every year in Germany. To solve this problem, we develop an IT artifact based on artificial neural networks, which is automating the manual order process and capable of reducing costs as well as food waste. To test and evaluate our artifact, we cooperated with an SME bakery chain from Germany. The bakery chain runs 40 points of sale (POS) in southern Germany. After algorithm based reconstructing and cleaning of the censored sales data, we compare two different data-driven newsvendor approaches for this inventory problem. We show that both models are able to significantly improve the forecast quality (cost savings up to 30%) compared to human planners. Collapse

Topics: decision making point of sale system customer satisfaction application programming interface

Methods: design artifact isolation forest computational algorithm artificial neural network design science