Arturo Castellanos

Arturo Castellanos
College of William and Mary | WM · Mason School of Business

PhD - Information Systems

About

40
Publications
24,231
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
179
Citations
Introduction
Arturo Castellanos received his PhD degree in Business (Information Systems) from Florida International University. He is an Assistant Professor in the Mason School of Business at William & Mary. His research interests are in the areas of System Analysis and Design, Business Analytics, and Blockchain technology.
Additional affiliations
August 2014 - present
Florida International University
Position
  • Instructor
Description
  • Business Analytics (Fall 2015) Intro to IS (CGS3300) - Teaching Evaluation: 4.5/5.0 Special Topics: BI (QMB4930 - U02) - Teaching Evaluation: 4.83/5.0 Special Topics: BI (QMB4930 - U01) - Teaching Evaluation: 4.48/5.0
August 2012 - April 2016
Florida International University
Position
  • PhD Student
Description
  • Advisor: Dr. Monica Chiarini Tremblay Committee: Dr. Richard Klein Dr. Roman Lukyanenko

Publications

Publications (40)
Conference Paper
Full-text available
Many artificial intelligence (AI) applications involve the use of machine learning, which continues to evolve and address more and more complex tasks. At the same time, conceptual modeling is often applied to such real-world tasks so they can be abstracted at the right level of detail to capture and represent the requirements for the development of...
Conference Paper
Full-text available
Many organizations rely on machine learning techniques to extract useful information from large collections of data. Much research in this area has focused on developing and applying machine learning techniques. We propose that using conceptual models can improve machine learning by providing needed domain knowledge to augment training data with do...
Conference Paper
Full-text available
Artificial Intelligence is increasingly driven by powerful but often opaque machine learning algorithms. These black-box algorithms achieve high performance but are not explainable to humans in a systematic and interpretable manner, a challenge known as Explainable AI (XAI). Informed by a synthesis of two converging literature streams on informatio...
Conference Paper
Full-text available
In an increasingly digital world, conceptual modeling research is more relevant than ever to the information systems field, but it requires an update with current theory. In [Re21] we develop a new theoretical framework of conceptual modeling to change the assumptions that govern research in this area. Our framework draws attention to the role of c...
Article
Full-text available
Two Robots Explain our MISQ paper in a Youtube video: https://youtu.be/MfuCgSADeWA The paper: https://www.researchgate.net/publication/344123600_From_Representation_to_Mediation_A_New_Agenda_for_Conceptual_Modeling_Research_in_A_Digital_World
Article
Full-text available
The role of information systems (IS) as representations of real-world systems is changing in an increasingly digitalized world, suggesting that conceptual modeling is losing its relevance to the IS field. We argue the opposite: Conceptual modeling research is more relevant to the IS field than ever, but it requires an update with current theory. We...
Conference Paper
Full-text available
Advances in machine learning (ML) make it possible to extract useful information from large and diverse datasets. ML methods aim to identify patterns in a dataset based on the values of features and their combinations. Recent research has proposed combining conceptual modeling, specifically data models, with artificial intelligence. In this paper,...
Chapter
Full-text available
Machine learning has become almost synonymous with Artificial Intelligence (AI). However, it has many challenges with one of the most important being explainable AI; that is, providing human-understandable accounts of why a machine learning model produces specific outputs. To address this challenge, we propose superimposition as a concept which use...
Conference Paper
Full-text available
An important function of any information system is to represent an application domain. A general or foundational ontology provides a basis from which research on representational issues can be conducted. However, most efforts that develop general ontologies, have not taken a systems view. In this paper , we propose a General Systemist Ontology (GSO...
Conference Paper
Full-text available
Crowdsourcing is an efficient way to engage the general public in making contributions to the production of goods and services. Studies have shown that observational crowdsourcing, as a continuous activity, has many potential benefits to society. However, a major challenge is how to model a crowdsourced activity. In this research, we provide guidel...
Conference Paper
Full-text available
Machine learning has become almost synonymous with Artificial Intelligence (AI). However, it has many challenges with one of the most important being explainable AI; that is, providing human-understandable accounts of why a machine learning model produces specific outputs. To address this challenge, we propose superimposition as a concept which use...
Article
Full-text available
Since the 1970s, many approaches to representing domains have been suggested. Each approach maintains the assumption that the information about the objects represented in the information system (IS) is specified and verified by domain experts and potential users. Yet, as more IS are developed to support a larger diversity of users such as customers...
Article
Purpose Shortage of organs for transplantation and improvements in LVADs make the use of this technology common as bridge to transplant (BTT). Compared to traditional statistical methods, machine learning (ML) techniques provides improvement in predictive modeling, identifying dimensionality and non-linear relationships between variables. Thus, we...
Article
Purpose Several studies have evaluated the role of recipient hemodynamics on heart transplant (HTx) outcomes. Data on the role of donor hemodynamics and donor-related characteristics on outcomes is scarce. Methods We studied adult (≥18 years) Htx patients from 1997 and 2016 using the UNOS database that had donor right heart catheterization informa...
Article
Purpose Machine learning (ML) techniques can improve predictive modeling over more traditional methods by identifying higher dimensionality and non-linear relationships between variables. We hypothesized that an AutoML algorithm would be superior to a logistic regression (LR) model for prediction of outcomes in HT. Methods The UNOS database was qu...
Article
Full-text available
Since 1970s many approaches of representing domains have been suggested. Each approach maintains the assumption that the information about the objects represented in the Information System (IS) is specified and verified by domain experts and potential users. Yet, as more IS are developed to support a larger diversity of users such as customers, sup...
Chapter
Full-text available
With the transformation of our society into a “digital world,” machine learning has emerged as an essential approach to extracting useful information from large collections of data. However, challenges remain for using machine learning effectively. We propose that some of these can be overcome using conceptual modeling. We examine a popular cross-i...
Conference Paper
Full-text available
This research in progress discusses two country use cases of land record modernization by adopting blockchain technology. Through the cases in Honduras and Georgia, we examine how socio-political and technical issues influence the IS readiness of public organizations when adopting an emerging technology. While both countries partnered with private...
Presentation
Full-text available
I teach a MBA course on Business Analytics at Baruch College --the students come from a vast array of backgrounds/experience (e.g., finance, marketing, accounting, IS, etc.). Although most of the students see the value of ML in Business, not all of them have the technical expertise (or want to become 'data scientist'). AutoML and tools such as H2O'...
Conference Paper
Full-text available
With the growth of machine learning and other computationally intensive techniques for analyzing data, new opportunities emerge to repurpose organizational information sources. In this study, we explore the effectiveness of unstructured data entry formats in repurposing organizational data in solving new tasks and drawing novel business insights. U...
Article
Full-text available
This study demonstrates the use of text data mining (TDM) for exploring the content of a collection of corporate citizenship (CC) reports. The collection analysed comprises CC reports produced by seven Dow Jones companies (Citi, Coca-Cola, Exxon-Mobil, General Motors, Intel, McDonald's and Microsoft) in 2004, 2008 and 2012. Exploratory content anal...
Conference Paper
Full-text available
Design science research is becoming a major area in the IS discipline. Despite the growing popularity of DSR in IS, there is a lack of established guidance on how to conduct this type of research. Moreover, although DSR is considered a pluralistic area of research, few studies have proposed multi-paradigmatic methods for DSR. The current study sugg...
Conference Paper
Full-text available
In 2002 Wand and Weber proposed a framework and agenda for future conceptual modeling research, which identified twenty-two research opportunities. We assess the impact of the Framework on research. We explore whether research provided sufficient answers to the questions posed by Wand and Weber in 2002 15 years later.
Conference Paper
Full-text available
Data collected by organizations is typically used for tactical purposes-solving a business need. In this study we show the relationship between inferential utility and institutional practices in repurposing unstructured electronic documentation. Our aim is to (1) understand the underpinnings of unstructured-data-entry formats in the data collected...
Conference Paper
Full-text available
Much of conceptual modeling research over recent times has been guided by a seminal research agenda developed by Wand and Weber (2002), which identified twenty-two research opportunities. In this paper, we explore whether existing research has provided sufficient answers to these questions. Our findings from a review of the literature show a dialec...
Conference Paper
Full-text available
Conceptual modeling specifies the kinds of objects to be represented in an information system (IS). It involves documenting knowledge about a domain, defining its scope, and outlining constraints: making it a key element of IS. Conceptual models typically represent classes (categories, kinds) of objects rather than concrete specific individuals. Cl...
Conference Paper
Full-text available
Much of modern science and technology relies on the notion of a taxonomy. In a typical taxonomy, information is organized based on super/subset relationship from most specific to most generic. Informed by recent developments in psychology, to overcome limitations of taxonomies, we propose information gradient theory (IGT). According to IGT, domains...
Conference Paper
Full-text available
As more Information Systems (IS) are developed to support a larger diversity of users, analysts can no longer rely on a single group of individuals to complete domain specifications—especially in heterogeneous settings. This paper aims to bridge this gap by providing a theoretical ground for the existence and use of basic level classes. These class...
Poster
Full-text available
One of the challenges in dealing with gold standards in healthcare is the difficulty of getting subject matter experts to label the data sets based on the target of interest. Can we extend the gold-standard by understanding (via machine learning techniques) the thought process followed by subject matter experts when creating a gold standard?
Conference Paper
Full-text available
This study utilizes Text Data Mining (TDM) to analyze the contents of Corporate Social Responsibility (CSR) Reports. The goal is to find evidence that environmental sustainability has become embedded in corporate policy and the core business discourse of seven organizations over 2004-2012. Results from supervised modeling techniques suggest embedde...
Conference Paper
Full-text available
The literature shows that companies have matured on how they see and understand CSR—even to the extent of seeing it as an essential element of the firm’s strategy. As part of a comprehensive research agenda, we investigate CSR reports from seven Dow Jones companies to assess the embeddedness of Environmental Sustainability considerations into their...
Conference Paper
Every year more than 800,000 children in the U.S. spend time in foster care with 35% being on psychotropic medication. An increasing ratio of foster care children per case worker makes it challenging to balance their multiple roles during the lifecycle of a case. Although there are review boards for identifying cases that require special attention,...
Conference Paper
Full-text available
Collaborative filtering (CF) is a popular method for recommender systems. It clusters users based on similarities in their rating histories. Most rating schemes ask for a single-dimension rating score that reflects the user’s overall experience with a product or service. The dimensionality of a user’s rating, i.e., the pros and cons that led to the...
Conference Paper
Full-text available
Relief efforts for previous disasters such as the 9/11 attacks in New York, hurricane Katrina in New Orleans, and the earthquake in Haiti, illustrate the need for emergency management agencies to have a comprehensive emergency management plan in place. Miami-Dade County’s (MDC) Emergency Operating Center (EOC) is one of the leading centers in hurri...
Article
Relief efforts for previous disasters such as the 9/11 attacks in New York, hurricane Katrina in New Orleans, and the earthquake in Haiti, illustrate the need for emergency management agencies to have a comprehensive emergency management plan in place. Miami-Dade County's Emergency Operating Center (EOC) is one of the leading centers in hurricane e...

Projects

Projects (6)
Project
Process redesign and technological readiness needed for Blockchain-related projects --moving from paper to blockchain.
Project
Approaches to creation of citizen science and other crowdsourcing projects