Cost-based Optimization of Multistore Query Plans

2023 | Information Systems Frontiers | Citations: 0

Authors: Forresi, Chiara; Francia, Matteo; Gallinucci, Enrico; Golfarelli, Matteo

Abstract: Multistores are data management systems that enable query processing across diff ... Expand

Abstract: Multistores are data management systems that enable query processing across different and heterogeneous databases; besides the distribution of data, complexity factors like schema heterogeneity and data replication must be resolved through integration and data fusion activities. Our multistore solution relies on a dataspace to provide the user with an integrated view of the available data and enables the formulation and execution of GPSJ queries. In this paper, we propose a technique to optimize the execution of GPSJ queries by formulating and evaluating different execution plans on the multistore. In particular, we outline different strategies to carry out joins and data fusion by relying on different schema representations; then, a self-learning black-box cost model is used to estimate execution times and select the most efficient plan. The experiments assess the effectiveness of the cost model in choosing the best execution plan for the given queries and exploit multiple multistore benchmarks to investigate the factors that influence the performance of different plans. Collapse

Topics: database system MongoDB PostgreSQL document database relational database

Methods: computational algorithm experiment case study regression analysis method longitudinal research

Framework for the Classification of Imbalanced Structured Data Using Under-sampling and Convolutional Neural Network

2022 | Information Systems Frontiers | Citations: 0

Authors: Lee, Yoon Sang; Bang, Chulhwan Chris

Abstract: Among machine learning techniques, classification techniques are useful for vari ... Expand

Abstract: Among machine learning techniques, classification techniques are useful for various business applications, but classification algorithms perform poorly with imbalanced data. In this study, we propose a classification technique with improved binary classification performance on both the minority and majority classes of imbalanced structured data. The proposed framework is composed of three steps. In the first step, a balanced training set is created via under-sampling. Then, each example is converted into an image depicting a line graph. In the last step, a Convolutional Neural Network (CNN) is trained using the images. In the experiments, we selected six datasets from the UCI Repository and applied the proposed framework to them. The proposed model achieved the best receiver operating characteristic (ROC) curve and Balanced Accuracy (BA) on all the datasets and five datasets, respectively. This demonstrates that the combination of under-sampling and CNNs is a viable approach for imbalanced structure data classification. Collapse

Topics: marketing management Python systems implementation packaged software

Methods: machine learning decision tree classification AdaBoost experiment binary classification

Leveraging BI Systems to Overcome Infobesity: A Comparative Analysis of Incumbent and New Entrant firms

2022 | HICSS | Citations: 2

Authors: Malik, Ojaswi; Jaiswal, Ankur; Kathuria, Abhishek; Karhade, Prasanna

Abstract: Infobesity is a condition whereby firms collect more information than they need ... Expand

Abstract: Infobesity is a condition whereby firms collect more information than they need or more information than they can efficiently use. As both incumbent firms and new entrant firms face different information-rich technological and economic environments, they are at a greater risk of infobesity which can compromise their innovation outcomes. In this study we leverage a research design that integrates inductive analytics and abductive discovery to uncover how incumbent and new-entrant firms leverage Business Intelligence systems and digital collaboration activities to innovate in the face of infobesity. We find that new entrant firms encounter a threshold effect governed by the use of BI systems to filter information from their customer network. On the other hand, we found that while most incumbents are able to innovate, there are uninventive incumbents that are unable to develop new products when they deploy only moderate levels of BI systems to filter their supplier data. Collapse

Topics: innovation management business intelligence computer supported cooperative work customer relationship management system enterprise resource planning

Methods: decision tree classification survey computational algorithm theory development machine learning

Theories: theory of abduction

Unravelling the Origins of Infobesity: The Impact of Frequency on Intensity

2022 | HICSS | Citations: 0

Authors: Malik, Ojaswi; Karhade, Prasanna; Kathuria, Abhishek; Jaiswal, Ankur; Yen, Benjamin

Abstract: Infobesity is characterized by information overload whereby firms and decision m ... Expand

Abstract: Infobesity is characterized by information overload whereby firms and decision makers collect more information than they need, or they can efficiently use. While recent studies have begun to unravel the antecedents of infobesity in organizations, there is a need to examine the relationship between the frequency and the degree of experiencing infobesity originating from enterprise systems. We use a research design that integrates inductive analytics and abductive discovery to uncover the interaction of multi-level antecedents of infobesity and conclude that the rate at which firms encounter infobesity drives the perception of the intensity at which the overload will be experienced. Collapse

Topics: information overload innovation management pandemic enterprise resource planning information system use

Methods: decision tree classification theory development computational algorithm survey machine learning

Theories: theory of abduction

GarNLP: A Natural Language Processing Pipeline for Garnishment Documents

2021 | Information Systems Frontiers | Citations: 0

Authors: Bordino, Ilaria; Ferretti, Andrea; Gullo, Francesco; Pascolutti, Stefano

Abstract: Basic elements of the law, such as statuses and regulations, are embodied in nat ... Expand

Abstract: Basic elements of the law, such as statuses and regulations, are embodied in natural language, and strictly depend on linguistic expressions. Hence, analyzing legal contents is a challenging task, and the legal domain is increasingly looking for automatic-processing support. This paper focuses on a specific context in the legal domain, which has so far remained unexplored: automatic processing of garnishment documents. A garnishment is a legal procedure by which a creditor can collect what a debtor owes by requiring to confiscate a debtor’s property (e.g., a checking account) that is hold by a third party, dubbed garnishee. Our proposal, motivated by a real-world use case, is a versatile natural-language-processing pipeline to support a garnishee in the processing of a large-scale flow of garnishment documents. In particular, we mainly focus on two tasks: (i) categorize received garnishment notices onto a predefined taxonomy of categories; (ii) perform an information-extraction phase, which consists in automatically identifying from the text various information, such as identity of involved actors, amounts, and dates. The main contribution of this work is to describe challenges, design, implementation, and performance of the core modules and methods behind our solution. Our proposal is a noteworthy example of how data-science techniques can be successfully applied to a novel yet challenging real-world context. Collapse

Topics: wiki Java Python

Methods: logistic regression natural language processing information extraction experiment machine learning

Mining Social Networks to Detect Traffic Incidents

2021 | Information Systems Frontiers | Citations: 1

Authors: Vallejos, Sebastián; Alonso, Diego G.; Caimmi, Brian; Berdun, Luis; Armentano, Marcelo G.; Soria, Álvaro

Abstract: Social networks are usually used by citizens to report or complain about traffic ... Expand

Abstract: Social networks are usually used by citizens to report or complain about traffic incidents that affect their daily mobility. Automatically finding traffic-related reports and extracting useful information from them is not a trivial task, due to the informal language used in social networks, to the lack of geographic metadata, and to the large amount of non traffic-related publications. In this article, we address this problem by combining Machine Learning and Natural Language Processing techniques. Our approach (a) filters publications that report traffic incidents in social networks, (b) extracts geographic information from the textual content of the publications, and (c) provides a broadcasting service that clusters all the reports of the same incident. We compared the performance of our approach with state of the art approaches and with a popular traffic-specific social network, obtaining promising results. Collapse

Topics: Twitter social network application programming interface global navigation satellite system Wikipedia

Methods: experiment machine learning support vector machine natural language processing decision tree classification

Leveraging Multisource Heterogeneous Data for Financial Risk Prediction: A Novel Hybrid-Strategy-Based Self-Adaptive Method

2021 | Management Information Systems Quarterly | Citations: 0

Authors: Wang, Gang; Chen, Gang; Zhao, Huimin; Zhang, Feng; Yang, Shanli; Lu, Tian

Abstract: Emerging phenomena of ubiquitous multisource data offer promising avenues for ma ... Expand

Abstract: Emerging phenomena of ubiquitous multisource data offer promising avenues for making breakthroughs in financial risk prediction. While most existing methods for financial risk prediction are based on a single information source, which may not adequately capture various complex factors that jointly influence financial risks, we propose a hybrid-strategy-based self-adaptive method to effectively leverage heterogeneous soft information drawn from a variety of sources. The method uses a proposed new feature- sparsity learning method to adaptively integrate multisource heterogeneous soft features with hard features and a proposed improved evidential reasoning rule to adaptively aggregate base classifier predictions, thereby alleviating both the declarative bias and the procedural bias of the learning process. Evaluation in two cases at the individual level (concerning borrowers at a P2P lending platform) and the company level (concerning listed companies in the Chinese stock market) showed that, compared with relying solely on hard features, effectively incorporating multisource heterogeneous soft features using our proposed method enabled earlier prediction of financial risks with desirable performance. Collapse

Topics: peer-to-peer lending crowdsourcing social media electronic commerce communication service infrastructure

Methods: machine learning ensemble learning support vector machine sensitivity analysis XGBoost

Dynamic self-organizing feature map-based models applied to bankruptcy prediction

2021 | Decision Support Systems | Citations: 0

Authors: du Jardin, Philippe

Abstract: Most bankruptcy prediction models used by financial institutions rely on single- ... Expand

Abstract: Most bankruptcy prediction models used by financial institutions rely on single-period data, that is to say data that characterize firms at a given moment of their life. However, the financial literature devoted to bankruptcy considers this phenomenon to be a protracted process and time to be a fundamental explanatory variable of firm failure. The few studies that attempted to incorporate a temporal dimension into a forecasting model using multiperiod data often yielded results that did not really improve model accuracy. One may then suppose that the principles that ground the historical dimension of bankruptcy are less in question to explain the poor difference between the results estimated with these two types of data than the way time is modeled into prediction rules. This is why we propose a method that relies on a particular modeling of firm history using self-organizing neural networks and a segmentation of the data space, and which makes it possible to typify subsets of firms that share a common evolution of their financial situation over time. This method leads to models that are substantially more accurate than traditional ones, especially when it comes to forecasting the fate of firms the cost of misclassifi­ cation of which is the highest for any financial institution. Collapse

Topics: database system Java Python

Methods: XGBoost conceptual modelling random forest classification design science computational algorithm

Theories: theory of economic cycles

Missing Impact of Ratings on Platform Participation in India: A Call for Research in GREAT Domains

2020 | Communications of the Association for Information Systems | Citations: 33

Authors: Karhade, Prasanna; Kathuria, Abhishek

Abstract: In this study, we propose that research conducted in Western, educated, industri ... Expand

Abstract: In this study, we propose that research conducted in Western, educated, industrialized, rich, and democratic (WEIRD) domains does not necessarily generalize to the rest of the world. Growing, rural, eastern, aspirational, transitional (GREAT) domains now account for a significant proportion of world economic output and, thereby, warrant special attention. We submit that a tolerant stance under which scholars investigate GREAT domains with an open mind that allows for theoretical plurality will likely enrich IS theories. To exemplify this stance, we consider how online ratings affect ratee decisions to participate in financial transactions on a digital platform in a GREAT economy. The production and consumption of food affects every strata of society, and, thus, we choose to investigate our research question in the context of platform-enabled food delivery. We applied decision tree induction on a population-level dataset that included restaurants, their features, online ratings, and financial participation decisions from a major food discovery and delivery platform in India. Tree induction makes no distributional assumptions and makes no a priori assumptions on the combinations of factors, which allows one to put forth the most lenient test for uncovering any impact that online ratings have on the decisions that rates make tacitly. After conducting multiple computational experiments, we consistently found that online restaurant ratings did not have a significant bearing on their decision to participate on the food-delivery platform. Our counterintuitive finding serves as an example WEIRD domain logic that does not generalize to a GREAT domain and forms a credible basis for our call for additional research in GREAT domains. Collapse

Topics: digital platform decision making wireless LAN internet technology electronic market

Methods: decision tree classification machine learning computational algorithm experiment post analysis

Theories: information systems theory management theory

In the Realm of Hungry Ghosts: Multi-Level Theory for Supplier Participation on Digital Platforms

2020 | Journal of Management Information Systems | Citations: 0

Authors: Kathuria, Abhishek; Karhade, Prasanna P; Konsynski, Benn R.

Abstract: Digital platforms have transformed various industries, with profound changes wit ... Expand

Abstract: Digital platforms have transformed various industries, with profound changes witnessed in settings characterized by repeated, low value, and novel transactions, such as ride sharing, household services, and food delivery. Platform providers need to understand the factor(s) that suppliers consider before choosing to participate on their platforms. We argue that multi-level theorizing is necessary to explain the patterns of decision criteria that constitute the complex, yet boundedly-rational decision of platform participation. We draw on multiple theoretical perspectives which include predictors from firm-level strategic behavior, firm-level digital predictors, institutional predictors, and platform level, competition and contextual (environmental) predictors to model restaurant’s decision to participate on food delivery platforms, which are an exemplar of platforms that digitize transactions of ubiquitous and episodic nature. The population of 95,735 restaurants, serving a total of 135 different cuisines, located in the 37 largest cities of India, forms the dataset for developing our multi-level theory. Our decision tree induction methodology, which employs high levels of pruning, empowers us to discover context-specific rules that serve as credible approximations of the partial ordering of decision flows tacitly used by restaurants in deciding to participate on platforms. We identify six combinations of predictors, that is, decision rules, which are situated in at least four theoretical perspectives, to succinctly explain supplier participation on digital platforms. Finally, we abduct away from these specific decision rules to develop generalizable theoretical propositions. The decision trees, context-specific rules, general forms of the rules, and generalized propositions together form our multi-level theory for supplier participation on digital platforms. Our findings aid platform providers identify suppliers who can be the focus of efforts to increase platform participation, and help suppliers identify the participation status of competitors. For policymakers, our findings imply that incentives at the ends of the pricing spectrum can increase supplier participation on digital platforms. Collapse

Topics: digital platform decision making knowledge representation on-premises software Google+

Methods: theory development decision tree classification ontological modelling qualitative interview machine learning

Theories: institutional isomorphism theory institutional theory