Mining semantic relations using NetFlow

Business-driven IT management (BDIM) aims at ensuring successful alignment of business and IT through thorough understanding of the impact of IT on business processes and business results, and vice versa. This thesis reviews the state of the art of BDIM research and advances it by contributing a comprehensive BDIM solution for the process of IT incident management. The solution can be used as a template for applying the BDIM methodology to other IT service management processes. The work presented in this dissertation resulted in three patent applications and is at the core of the HP IT Analytic™ product (formerly HP DecisionCenter™). This thesis was defended on March 2009.

2008 3rd IEEE/IFIP International Workshop on Business-driven IT Management

To summarize to business people the main challenges of business-driven information and communication technology (ICT) systems management, we suggest "the 5 C challenges of ICT systems management": 1) cost-benefit relationship, 2) complexity, 3) conformance to higher-level objectives, 4) circumstances and their diversity, and 5) change. We also advocate the slogan "To address the 5 C challenges you need at least the 5 A approaches and a compromise." Here, the "5 As" are the main approaches for addressing the "5 Cs": 1) analysis of benefits and costs, 2) automation of management activities, 3) aims (objectives, policy) modeling and processing, 4) accommodation of different circumstances through customization and context-sensitivity, and 5) adaptability. We also discuss how these 5 Cs and 5 As relate to self-management, policy-based management, and contract-based management and how they can be used for presenting a new project on modeling and using business value information.

IT Service Management and Business-Driven IT Management

For an IT service provider, incident management process in which particularly incident prioritization plays a pivotal role in the improvement of service quality and maximization of business profits. Traditional prioritization methods are concern impact and urgency exclusively but overlook financial losses and risks. In this work, an optimal method is proposed using Business Driven IT Management (BDIM) concepts and risk decision-making theory, whereby numbers of incidents can be prioritized to minimize the sum of business losses and risks. The method captures the linkage between IT decisions and business impacts through risk management and sensitivity analysis. A real network is discussed to demonstrate the value of the approach.

At the stage of urban distribution network resilience assessment, the assessment system is relatively low in perfection, resulting in a large difference between the assessment results and the actual situation. Therefore, a method for building a multi-dimensional resilience assessment system of urban distribution networks based on association rules is proposed. In the stage of selecting multi-dimensional resilience assessment indicators for urban distribution networks, association rules are introduced, and the relationship between distribution network operation data and distribution network resilience is analyzed by using support, confidence, and correlation coefficients. The positive and negative association rules of distribution network resilience are mined as the core, the sampling of global distribution network operation data is determined, and the constraint conditions of condition distribution are set. Based on the load effect of the distribution network and the state of distribution network components, the multi-dimensional toughness evaluation index of the urban distribution network can be selected. In the stage of setting the weight of the multi-dimensional toughness evaluation index of the urban distribution network, the influence of multi-dimensional toughness evaluation index parameters of the urban distribution network in an abnormal state solved by DFS in graph theory on the connection state of grid nodes is used, and the differential index weight of search results is combined. In this test result, under the design evaluation system, the analysis result of the overall load loss rate of the distribution network always keeps a high consistency with the actual value, the error is always stable within the 1.0% range, and the maximum error is only 0.88%.

The objective of this paper is Car Loan Prediction using Extreme Logistic Regression with Novel Association Rule and compared with Random Forest Algorithm. Machine learning is an emerging research field that can be used for predictions. Materials and Methods: A framework for car loan prediction is used by Extreme Logistic Regression with Novel Association Rule to predict the loans default from banks while customers are faced with critical problems compared with Random Forest Algorithm. This research study considers two groups such as an Extreme Logistic Regression Algorithm with Novel Association Rule and Random Forest Algorithm. The sample size considered for each of the algorithms is 20. Results: The accuracy, precision, and recall of Logistic Regression Algorithm with Novel Association Rule classifiers produce 73.99%, 18.49% and 24.66% respectively in predicting Car Loan on the dataset used whereas the Accuracy, Precision, and Recall of Random Forest algorithm produces 73.88%, 18.47%, and 24.62% respectively predicting the car loan default. This work shows the insignificance (p>0.001) between the classifiers based on an independent sample T-test. Conclusion: The performance of an Extreme Logistic Regression algorithm with a novel association classifier is significantly better than the Random Forest algorithm with a comparison of accuracy, precision and recall.

This paper advocates a non-intrusive and incremental approach to enabling existing Grid programming systems with new features. In particular, it presents a software component enabling NetSolve applications with direct communications between remote tasks. The software component is a supplementary one working on the top of the basic NetSolve system. Its design also allows remote tasks to be freely mixed in a single application, independent on whether each particular task is enabled for direct communications or not. Experiments with this software are also presented.

Association Rule Mining (ARM) with fuzzy logic perception smooth the progress of the easy process of mining of underlying frequent or recurrent patterns based on their own frequencies in the form of association rules from any transactional and relational datasets containing items to signify the most recent trends in the given dataset. These mined recurrent patterns or fuzzy association rules employ either for physical data analysis or also influenced to compel further mining tasks like categorization (classification) and collecting (clustering) which helps domain area experts to automate decision-making. In the concept of data mining, generally fuzzy Association Rule Mining (FARM) technique has been comprehensively adopted in transactional and relational datasets those datasets containing items who has a fewer to medium amount of attributes/dimensions. Few techniques have also adopted for high dimensional dataset also, but whether those techniques have also work for low dimensional datasets are yet to be proven out. Hence, in this paper we propose E-FAR-HD algorithm which is an enhanced version of FAR-HD algorithm that designed exclusively for large or high-dimensional datasets. We have designed this EFAR-HD algorithm that increases the accuracy of FAR-HD algorithm on the smaller datasets and remove the chances of misses when FAR-HD has tested on smaller datasets such as contact lens or patient dataset.

When assessing the impact of technology, we should focus on how technology is applied and how it works in different contexts. And it also works with the assistance of the top management and company-scale financial support. China's state-owned enterprises (SOEs) are also facing the severe problem of how to transform and upgrade their internal management. From the single-module operation of the material management system, office automation system, customer service system, and property charging system, to the establishment of an ERP team to implement a comprehensive information technology track, thanks to the top-level management support and guidance of technology’s painful implementations. The case of S Company provides comprehensive services including property management, leasing, and business support to over 1,200 tenants. The scene shows the company facing the challenge of managing diverse operations and information silos. The solution is to implement an ERP system that will streamline processes, enhance efficiency, and facilitate data-driven decision-making. Adopting the Gartner Plan perspective as a concluding note in this article, we examine the implementation of technology from the viewpoint of executive management. This offers inspiration and serves as a point of reference for peers.

The purpose of the article is to consider the information and analytical support of the cash flows management at the enterprises. It is necessary to investigate the theoretical aspects of the information and analytical support of the cash flows management, taking into account the current conditions of the enterprises. The object of the research is the information and analytical support of the cash flows management at the enterprises. The methods of cognition, synthesis, generalization, systematization, visual methods are used. The concept of "information flow" is considered, which can be considered in three aspects: syntactic, semantic, and pragmatic. The term "information and analytical support" is disclosed from the point of view of scientific concepts of various researchers. It is determined the components of the information and analytical support of the cash flow management. These components include: information, analytical, software and technological support. The sources of the information component of the information and analytical support of the enterprise's cash flow management are determined. It has been proven that the quantity and quality of information determines the effectiveness of the entire management system of the enterprise as a whole and cash flow management, in particular. A systematization of stakeholders interested in receiving data on the company's cash flows is provided. Thus, a component of the cash flow management system is information and analytical support, the main components of which are informational, analytical, software and technological components. To carry out an effective analysis of cash flows, it is necessary to create an information base that includes external and internal information. When studying internal information, it is divided into accounting and non-accounting. The results of the study showed that the need of stakeholders for information about the state of cash flows of financial statements is growing every year, therefore it is important to provide stakeholders with reliable information. The expediency of distinguishing two groups of information users: external and internal has been established. The practical value of the conducted research lies in the further use of information and analytical support in the company's activities.

This study investigates the impact of e-commerce on the performance of SMEs in Taiwan, focusing on key factors that drive successful adoption. The analysis considers management support, IT infrastructure, organizational readiness, and external environment factors. Multiple regression analysis was conducted to test the hypotheses. Findings indicate that management support is the primary driver of e-commerce adoption, followed by IT infrastructure and organizational readiness, while the external environment has a smaller effect. Positive managerial attitudes, technological improvements, and organizational resource readiness are essential for e-commerce adoption. Government policies, socio-cultural alignment, and an effective legal framework also play significant roles. These findings provide insights for business managers and recommendations for policymakers to support SME growth in the digital economy.

The IT Service Management (ITSM) industry has defined processes as best practices in the widely-accepted IT Infrastructure Library (ITIL®) framework. However, there are few tools available to provide decision support to IT Service Managers who wish to improve service management processes. It is essential to assess the current capability of processes before process improvements are planned. Our research addressed the problems of the lack of transparency and the need for efficiency in ITSM process assessment. Using the Design Science Research methodology, we developed an innovative Software-mediated Process Assessment (SMPA) approach that automates assessment of ITSM processes and supports the decision-making of IT Service Managers. The SMPA approach includes process selection, an online survey to collect assessment data, measurement of process capability and specific recommendations for managers to commence process improvement. We implemented a decision support system (DSS) to automate the SMPA approach and evaluated it at two IT service providers. The evaluations indicated that the SMPA approach supports decision-making on process improvements. In the future, data analytics performed on the assessment data can help IT managers to analyse and visualise the ‘big data’ of process knowledge.

The Impact of Business Intelligence on the Quality of Decision Making – A Mediation Model

Cloud adoption has gained momentum recently, however cloud adoption is still a maturing concept. Cloud maturity frameworks are therefore required by organizations to assess their cloud maturity. This study focuses on the business impact and management of cloud adoption rather than on the technical aspects of server virtualization, optimization and integration. The aim of this study to propose a framework, which enterprises could use to evolve their cloud maturity to a higher level, improving business efficiency and effectiveness. Higher levels of maturity allow organizations to leverage the benefits of cloud by aligning technology adoption to business requirements, whilst managing the risks. This theoretical model could aid IT managers and decision makers use evidence-based management principles determine their maturity of cloud adoption i.e. support managers of large enterprises close the 'research-practice gap' by basing business management practices on research evidence. The method of this study is to use an in-depth, qualitative approach. We are studying South African large enterprise cases by interacting with respondents associated with the cloud adoption journey (i.e. CIOs, CTOs, technology heads, and IT managers). A semi-structured questionnaire has been prepared and is being administered through in-depth interviews. The researcher has completed 12 in-depth interviews and it is still necessary to shortly address the testing and evaluation of the model. The test results phase is still being conducted and is not being presented in this contribution. This paper presents the conceptual model of the study.