Factors that Affect Consumer-to-Consumer Sales: An Inductive Predictive Analytics Approach

2023 | Americas Conference on Information Systems | Citations: 0

Authors: El Arabaty, Ashraf; Okoli, Chitu

Abstract: This study investigates factors affecting consumer-to-consumer (C2C) sales perf ... Expand

Abstract: This study investigates factors affecting consumer-to-consumer (C2C) sales performance, specifically in the context of second-hand luxury goods. Using a large dataset of users from a French C2C luxury fashion website, the research identifies factors influencing C2C sales beyond current knowledge. Findings show that the number of followers a seller has, as well as the number of products a seller wishes for and likes, are associated with increased sales. Additionally, the study uncovers unexpected results: sellers listing many products also buy many products, and the number of users a seller follows is associated with increased sales. These findings contribute to a better understanding of the unique characteristics of C2C e-commerce. The article provides practical implications for sellers and C2C platforms to improve their sales performance, catering to the dual-role nature of users in C2C transactions. Collapse

Topics: electronic commerce website explainable artificial intelligence social capital

Methods: machine learning linear regression analysis literature study random forest classification decision tree classification

Peer-to-Peer (P2P) Lending Risk Management: Assessing Credit Risk on Social Lending Platforms Using Textual Factors

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

Authors: Siering, Michael

Abstract: Peer-to-peer (P2P) lending platforms offer Internet users the possibility to bor ... Expand

Abstract: Peer-to-peer (P2P) lending platforms offer Internet users the possibility to borrow money from peers without the intervention of traditional financial institutions. Due to the anonymity on such social lending platforms, determining the creditworthiness of borrowers is of high importance. Beyond the disclosure of traditional financial variables that enable risk assessment, peer-to-peer lending platforms offer the opportunity to reveal additional information on the loan purpose. We investigate whether this self-disclosed information is used to show reliability and to outline creditworthiness of platform participants. We analyze more than 70,000 loans funded at a leading social lending platform. We show that linguistic and content-based factors help to explain a loan's probability of default and that content-based factors are more important than linguistic variables. Surprisingly, not every information provided by borrowers underlines creditworthiness. Instead, certain aspects rather indicate a higher probability of default. Our study provides important insights on information disclosure in the context of peer-to-peer lending, shows how to increase performance in credit scoring and is highly relevant for the stakeholders on social lending platforms. Collapse

Topics: crowdsourcing peer-to-peer lending LendingClub risk management logistics management

Methods: qualitative content analysis machine learning regression analysis method descriptive statistic logistic regression

Theories: signaling theory

FACTORS INFLUENCING THE ACCEPTANCE OF SELF-SERVICE BIG DATA PREPARATION AND ANALYTICS TOOLS

2023 | European Conference On Information Systems | Citations: 0

Authors: Zaki, Mohamed; Fischer, Svenja; Woodall, Philip; Leischnig, Alexander

Abstract: Although self-service data preparation and analytics tools (SSPATs) have become ... Expand

Abstract: Although self-service data preparation and analytics tools (SSPATs) have become increasingly popular and can provide major benefits to users, barriers associated with the technology and its usage may prevent adoption. Based on prior work on technology acceptance and related theories, this study develops a net effects model and a configurational effects model to further the understanding of SSPAT acceptance. Using a configurational lens, this study shows how a fresh methodological approach from a different epistemological stance applied to a well-established theoretical basis can offer novel insights into effects and patterns that may complement exisiting findings. The results of our empirical study based on a sample of 339 firms confirm insights from previous studies and advance them by providing vision for compound antecedents of SSPAT acceptance and complementarity effects among antecedent conditions. Collapse

Topics: ease of use fuzzy logic technology adoption perceived usefulness user experience

Methods: survey partial least squares path modeling theoretical contribution meta analysis exploratory data analysis

Theories: fuzzy set theory technology acceptance model unified theory of acceptance and use of technology

A Literature Review of Data Governance and Its Applicability to Smart Cities

2022 | HICSS | Citations: 0

Authors: Bozkurt, Yusuf; Rossmann, Alexander; Pervez, Zeeshan

Abstract: Data governance have been relevant for companies for a long time. Yet, in the br ... Expand

Abstract: Data governance have been relevant for companies for a long time. Yet, in the broad discussion on smart cities, research on data governance in particular is scant, even though data governance plays an essential role in an environment with multiple stakeholders, complex IT structures and heterogeneous processes. Indeed, not only can a city benefit from the existing body of knowledge on data governance, but it can also make the appropriate adjustments for its digital transformation. Therefore, this literature review aims to spark research on urban data governance by providing an initial perspective for future studies. It provides a comprehensive overview of data governance and the relevant facets embedded in this strand of research. Furthermore, it provides a fundamental basis for future research on the development of an urban data governance framework. Collapse

Topics: data governance smart city database system spreadsheet privacy

Methods: natural language processing literature study literature sample cluster analysis qualitative content analysis

Pattern Labelling of Business Communication Data

2022 | Group Decision and Negotiation | Citations: 0

Authors: Kaya, Muhammed-Fatih

Abstract: Systematic pattern recognition as well as the corresponding description of deter ... Expand

Abstract: Systematic pattern recognition as well as the corresponding description of determined patterns entail numerous challenges in the application context of high-dimensional communication data. These can cause increased effort, especially with regard to machine-based processing concerning the determination of regularities in underlying datasets. Due to the increased expansion of dimensions in multidimensional data spaces, determined patterns are no longer interpretable by humans. Taking these challenges into account, this paper investigates to what extent pre-defined communication patterns can be interpreted for the application area of high-dimensional business communication data. An analytical perspective is considered by taking into account a holistic research approach and by subsequently applying selected Machine Learning methods from Association Rule Discovery, Topic Modelling and Decision Trees with regard to the overall goal of semi-automated pattern labelling. The results show that meaningful descriptions can be derived for the interpretation of pre-defined patterns. Collapse

Topics: cloud computing database system negotiation support system business-to-business

Methods: data transformation principal component analysis DBSCAN decision tree classification computational algorithm

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

What constitutes a machine-learning-driven business model? A taxonomy of B2B start-ups with machine learning at their core

2022 | European Conference On Information Systems | Citations: 0

Authors: Vetter, Oliver; Hoffmann, Felix; Pumplun, Luisa; Buxmann, Peter

Abstract: Artificial intelligence, specifically machine learning (ML), technologies are p ... Expand

Abstract: Artificial intelligence, specifically machine learning (ML), technologies are powerfully driving business model innovation in organizations against the backdrop of increasing digitalization. The resulting novel business models are profoundly shaped by ML, a technology that brings about unique opportunities and challenges. However, to date, little research examines what exactly constitutes these business models that use ML at their core and how they can be distinguished. Therefore, this study aims to contribute to an increased understanding of the anatomy of ML-driven business models in the business-to-business segment. To this end, we develop a taxonomy that allows researchers and practitioners to differentiate these ML-driven business models according to their characteristics along ten dimensions. Additionally, we derive archetypes of ML-driven business models through a cluster analysis based on the characteristics of 102 start-ups from the database Crunchbase. Our results are cross-industry, providing fertile soil for expansion through future investigations. Collapse

Topics: business-to-business business model artificial intelligence database system value creation

Methods: cluster analysis machine learning theoretical contribution triangulation k-means clustering

A Framework for Informal Learning Analytics - Evidence from the Literacy Domain

2021 | HICSS | Citations: 0

Authors: Rizk, Aya; Rodriguez, Adrian

Abstract: Multidisciplinary approaches to learning analytics (LA) have the potential to pr ... Expand

Abstract: Multidisciplinary approaches to learning analytics (LA) have the potential to provide important insights into student learning beyond interactions within learning management systems (LMS). In this paper we demonstrate the benefits of such an approach by proposing a framework that adds the contextual elements of task design, tools and technologies and datasets to established LA processes. Our framework was developed as a design science research (DSR) artifact, working with teachers of English at two Swedish secondary schools. The results highlight the importance of valid task design for generating relevant, useful insights and provide a basis for simplifying and automating in-situ LA that can be used by teachers in their everyday work. The study also provided important insights for the field of online research and comprehension (ORC) both in relation to methodology and how students engage with a task that requires locating and synthesizing information on the open Internet in a second language. Collapse

Topics: internet technology task productivity brainstorming systems development

Methods: design science data transformation principal component analysis design artifact k-means clustering

Theories: educational theory

Closed-form evaluations and open-ended comment options: How do they affect customer online review behavior and reflect satisfaction with hotels?

2021 | Decision Support Systems | Citations: 0

Authors: Xu, Xun

Abstract: The online review systems of digital platforms feature a variety of designs. Thi ... Expand

Abstract: The online review systems of digital platforms feature a variety of designs. This study examines how closed-form evaluations and open-ended textual comment options affect customers’ online review writing behaviors and reflect satisfaction with hotels. We find that direct and spillover effects exist. These refer to the effects of cus­ tomers’ closed-form evaluations of a product or service attribute on their reviews of the same attribute and other attributes in their open-ended comments, respectively. Regarding the direct effect, positive closed-form evalu­ ations of attributes reduce customers’ behaviors of writing details about the same attributes in open-ended comments, but negative closed-form evaluations of attributes increase that behavior. The increasing effect is greater than the reducing effect. Regarding the spillover effect, closed-form evaluations of certain attributes increase customers’ behaviors of writing details about other attributes in open-ended comments. Additionally, we find that the heterogeneity effect lies in the different roles of closed-form evaluations and open-ended textual comments in reflecting customers’ overall satisfaction. Open-ended comments about the advantages of the at­ tributes have a more significant effect than the closed-form evaluations of the same attributes in reflecting overall customer satisfaction, but closed-form evaluations better reflect customers’ low overall satisfaction with the disadvantages of the attributes. The direct, spillover, and heterogeneity effects on customers’ evaluations and comments regarding independent hotels are higher than those effects on evaluations and comments regarding chain hotels. The findings provide insights for companies to design review systems, understand customer per­ ceptions, and use the positive electronic word-of-mouth effect. Collapse

Topics: online review user-generated content customer satisfaction systems design data breach

Methods: computational algorithm natural language processing Wald test descriptive statistic sentiment analysis

Theories: theory of information

What are customers commenting on, and how is their satisfaction affected? Examining online reviews in the on-demand food service context

2021 | Decision Support Systems | Citations: 0

Authors: Xu, Xun

Abstract: The on-demand economy has prospered with the rapid development of digital platfo ... Expand

Abstract: The on-demand economy has prospered with the rapid development of digital platforms. Many customers use ondemand service platforms to order services and then post online reviews. Using text-mining approaches, this study examines customers’ online review-writing behavior and their overall satisfaction with restaurants in the context of on-demand food service. We use customers’ overall ratings in their reviews to measure their overall satisfaction. We find that customers comment on the main service provider, the restaurants, and the auxiliary service providers, which include the drivers and on-demand service platform; in their online customer reviews, which are posted on the restaurants’ web pages on the on-demand service platform. From text regressions, we found the determinants of customer satisfaction with the restaurants through their online reviews. There is a spillover effect from the performance of auxiliary providers on customer satisfaction with the main provider. That is, the performance of the drivers and the platform affects customers’ overall satisfaction with the res­ taurants. In addition, we find that a higher cost of the order makes customers comment more on the attributes offered by the restaurants to show their overall satisfaction. Further, we find the type of listed merchants categorized by their properties (i.e., chain or independent) and participation in the platform programs affect the influence of the various attributes, offered by different providers, on customer satisfaction with the main pro­ vider. The findings shed light on the determinants of customers’ overall satisfaction and urge improvement in collaboration and coordination between various participants in the on-demand service context. Collapse

Topics: customer satisfaction online review web page user-generated content service quality

Methods: sentiment analysis natural language processing descriptive statistic latent semantic analysis computational algorithm