Exploring the Relations Between Net Benefits of IT Projects and CIOs’ Perception of Quality of Software Development Disciplines

2020 | Business & Information Systems Engineering | Citations: 0

Authors: Vavpotič, Damjan; Robnik-Šikonja, Marko; Hovelja, Tomaž

Abstract: Software development enterprises are under consistent pressure to improve their ... Expand

Abstract: Software development enterprises are under consistent pressure to improve their management techniques and development processes. These are comprised of several software development methodology (SDM) disciplines such as requirements acquisition, design, coding, testing, etc. that must be continuously improved and individually tailored to suit specific software development projects. The paper proposes a methodology that enables the identification of SDM discipline quality categories and the evaluation of SDM disciplines’ net benefits. It advances the evaluation of software process quality from single quality category evaluation to multiple quality categories evaluation as proposed by the Kano model. An exploratory study was conducted to test the proposed methodology. The exploratory study results show that different types of Kano quality are present in individual SDM disciplines and that applications of individual SDM disciplines vary considerably in their relation to net benefits of IT projects. Consequently, software process quality evaluation models should start evaluating multiple categories of quality instead of just one and should not assume that the application of every individual SDM discipline has the same effect on the enterprise’s net benefits. Collapse

Topics: IS impact Chief Information Officer project management system development method new product development

Methods: computational algorithm survey machine learning literature study

Answering queries in hybrid Bayesian networks using importance sampling

2012 | Decision Support Systems | Citations: 0

Authors: Fernández, Antonio; Rumí, Rafael; Salmerón, Antonio

Abstract: In this paper we propose an algorithm for answering queries in hybrid Bayesian n ... Expand

Abstract: In this paper we propose an algorithm for answering queries in hybrid Bayesian networks where the underlying probability distribution is of class MTE (mixture of truncated exponentials). The algorithm is based on importance sampling simulation. We show how, like existing importance sampling algorithms for discrete networks, it is able to provide answers to multiple queries simultaneously using a single sample. The behaviour of the new algorithm is experimentally tested and compared with previous methods existing in the literature. Collapse

Topics: probabilistic reasoning

Methods: computational algorithm Bayesian network experiment chi squared test simulation

A Bayesian Network Model of Knowledge-Based Authentication

2007 | Americas Conference on Information Systems | Citations: 0

Authors: Chen, Ye

Abstract: In this paper, we adapt a statistical modeling approach to the problem of knowle ... Expand

Abstract: In this paper, we adapt a statistical modeling approach to the problem of knowledgebased authentication (KBA). The study consists of three parts, namely, model selection, feature selection, and empirical investigation. First, a nonparametric Bayesian network model of KBA is presented, which is grounded in probabilistic reasoning and information theory. Second, we propose an approach to feature selection in KBA that is based on the principle of maximum entropy with proper underlying probabilistic semantics in the security domain. Third, an empirical study extends the analytical modeling to the behavioral space of KBA involving both legitimate users and attackers. Our empirical investigation is comprised of a pilot study and a large-scale experiment with online social networking data. The pilot study validated that the proposed Bayesian model makes a sensible approximation to the human cognitive process. Our experiments with online social networking data showed that, with the cutting-edge statistical machine learning techniques and the abundant data available from the Internet, the guessability an attacker would achieve can be significantly improved. The results of the analytical modeling and the empirical study bear direct implications to the KBA implementation and establish a foundation for future research in the KBA area. Collapse

Topics: social network data breach internet technology electronic authentication information privacy concern

Methods: machine learning support vector machine mathematical model Bayesian network experiment

Theories: game theory information theory

Data mining of Bayesian networks using cooperative coevolution

2004 | Decision Support Systems | Citations: 2

Authors: Wong, Man Leung; Lee, Shing Yan; Leung, Kwong Sak

Abstract: This paper describes a novel data mining algorithm that employs cooperative coev ... Expand

Abstract: This paper describes a novel data mining algorithm that employs cooperative coevolution and a hybrid approach to discover Bayesian networks from data. A Bayesian network is a graphical knowledge representation tool. However, learning Bayesian networks from data is a difficult problem. There are two different approaches to the network learning problem. The first one uses dependency analysis, while the second approach searches good network structures according to a metric. Unfortunately, the two approaches both have their own drawbacks. Thus, we propose a novel algorithm that combines the characteristics of these approaches to improve learning effectiveness and efficiency. The new learning algorithm consists of the conditional independence (CI) test and the search phases. In the CI test phase, dependency analysis is conducted to reduce the size of the search space. In the search phase, good Bayesian networks are generated by a cooperative coevolution genetic algorithm (GA). We conduct a number of experiments and compare the new algorithm with our previous algorithm, Minimum Description Length and Evolutionary Programming (MDLEP), which uses evolutionary programming (EP) for network learning. The results illustrate that the new algorithm has better performance. We apply the algorithm to a large real-world data set and compare the performance of the discovered Bayesian networks with that of the back-propagation neural networks and the logistic regression models. This study illustrates that the algorithm is a promising alternative to other data mining algorithms. Collapse

Topics: logistics management marketing management missing data telephone workstation

Methods: computational algorithm Bayesian network artificial neural network experiment regression analysis method

Theories: co-evolution theory

A probabilistic reasoning model: Formulation and control strategy

1996 | Decision Support Systems | Citations: 0

Authors: Sarkar, Sumit; Ghosh, Deb

Abstract: It has been recognized that past experiences of a decision maker often plays a p ... Expand

Abstract: It has been recognized that past experiences of a decision maker often plays a pivotal role in solving new problem instances. Therefore, the ability to model human reasoning processes has become an important subject of research in recent years. In many applications, the reasoning process must deal with uncertainty inherent in the problem domain. This research addresses the issue of supporting the model formulation and data acquisition processes for situations that (i) operate under uncertain conditions, and (ii) utilize evidential information that is gathered in stages. A theoretical framework is presented for the probabilistic formulation of the reasoning process that incorporates past experiences. The model is validated by testing its performance on simulated data, and is shown to work well when a sufficiently large number of cases are available for estimating probabilities. The probabilistic reasoning system can revise beliefs in an intuitively appealing and theoretically sound manner when information is acquired in an incremental fashion. Two dynamic information gathering strategies are discussed for such a reasoning system, one using information theoretic techniques, and the other using decision theoretic techniques. Collapse

Topics: Unix decision making probabilistic reasoning

Methods: experiment simulation computational algorithm Monte Carlo simulation theory development

Intelligent inference systems based on influence diagrams

1995 | Decision Support Systems | Citations: 0

Authors: Gottinger, H. W.; Weimann, H. P.

Abstract: This paper explores various inference techniques for an intelligent decision sup ... Expand

Abstract: This paper explores various inference techniques for an intelligent decision support system based on influence diagrams. Rule-based expert systems for decision support have been successful for well-structured, well understood decision situations of a taxonomic classification type. As uncertainty is prevalent, information costly and payoff relevant, and the preferred solution depends on the specific beliefs and preferences of an individual or group decision maker the resolution methods of decision theory embodied in first-order predicate logic forms a natural basis for computerized intelligent decision support. Based on a unified characterization of knowledge inference procedures for logical probabilistic and decision theoretic reasoning are described in detail. Collapse

Topics: knowledge base probabilistic reasoning logic programming language decision making Prolog