Robust generalized eigenvalue classifier with ellipsoidal uncertainty
Uncertainty is a concept associated with data acquisition and analysis, usually appearing in the form of noise or measure error, often due to some technological constraint. In supervised learning, uncertainty affects classification accuracy and yields low quality solutions. For this reason, it is essential to develop machine learning algorithms able to handle efficiently data with imprecision. In this paper we study this problem from a robust optimization perspective. We consider a supervised learning algorithm based on generalized eigenvalues and we provide a robust counterpart formulation and solution in case of ellipsoidal uncertainty sets. We demonstrate the performance of the proposed robust scheme on artificial and benchmark datasets from University of California Irvine (UCI) machine learning repository and we compare results against a robust implementation of Support Vector Machines.
Implementation of IT and program projects seems to be very complicated and taught process, associated with many uncertainties and risks. Sure, this does not mean the rejection of such projects, supposed the more responsibility for the decision making process of new information technologies implementation. To manage various problems which face project managers, it makes sense to use special risk management software. The functionality of modern risk management systems allows identifying risk occurrence, conducting scenario modeling, take the more appropriate managing decisions based on scenario analysis and mathematical calculations. All these functionality will support project manager to optimize his business activities in accordance to risk management practices and ensure better coordination and balance inside the project team. Currently there available a wide range of project management software, but it is reasonable to conduct some analysis in terms of applicability to specific IT projects. The author will review the most appropriate software solutions for the risk management in IT area, conduct competitive analysis and provide some recommendations on software selection.
Into the Red explores the emergence of a credit card market in post-Soviet Russia during the formative period from 1988 to 2007. In her analysis, Alya Guseva locates the dynamics of market building in the social structure, specifically the creative use of social networks. Until now, network scholars have overlooked the role that networks play in facilitating exchange in mass markets because they have exclusively focused on firm-to-firm or person-to-person ties. Into the Reddemonstrates how networks that combine individuals and organizations help to build markets for mass consumption. The book is situated on the cutting edge of emerging interdisciplinary research, linking multiple layers of analysis with institutional evolution. Using an intricate framework, Guseva chronicles both the creation of a credit card market and the making of a mass consumer. These processes are placed in the context of the ongoing restructuring in postcommunist Russia and the expansion of Western markets and ideologies through the rest of the world.
Supply chain management is rather new scientific field that reflects the concept of integrated business planning. This concept should be experts and practitioners in logistics and strategic management. Today, integrated planning to become a reality thanks to the development of information technology and computer technology. At the same time to achieve a competitive advantage is not enough high-speed, low-cost data transfer process. In order to effectively apply information technology tools necessary to develop a quantitative analysis of the effectiveness of supply chain management. The mam element of this tool are optimization models that reveal the complex interactions, the wave and the synergies that arise in supply chain management. In this article we consider one of the classes of such models - the so-called dynamic models of conveyor systems, processing of applications.
In this paper, we use robust optimization models to formulate the support vector machines (SVMs) with polyhedral uncertainties of the input data points. The formulations in our models are nonlinear and we use Lagrange multipliers to give the first-order optimality conditions and reformulation methods to solve these problems. In addition, we have proposed the models for transductive SVMs with input uncertainties.
The paper focuses on the concept of ‘financial strategies’ and addresses two problems: first, how to define the concepts of financial strategy and strategizing, and second, how to operationalize them into indicators for empirical research. The introduction to this new concept is based on the conviction that strategizing (which is understood as a specific attitude to life held by people who do not live for the moment, think about their future even if it is rather uncertain, set long-term financial goals and act towards achieving them), is an intrinsic factor in the financial behavior of people. It is argued that it is not possible to define financial strategy or to operationalize it objectively and universally since people operate in very different circumstances; i.e. in different institutional environments or at different stages of life, etc. The solution must be found in the interactionist sociological perspective with the emphasis on the construction of the interpretation of a situation: how individuals themselves make sense of financial strategizing in their own environment, the options they perceive and the constraints they feel.
Summarizes the latest applications of robust optimization in data mining.
An essential accompaniment for theoreticians and data miners Data uncertainty is a concept closely related with most real life applications that involve data collection and interpretation. Examples can be found in data acquired with biomedical instruments or other experimental techniques. Integration of robust optimization in the existing data mining techniques aims to create new algorithms resilient to error and noise.
The manual is intended for students of Department of computer engineering MIEM HSE. In the textbook based on the courses "Economics of firm" and "the development strategy of the organization." Discusses the key conceptual and methodological issues of the theory and practice of Economics and development planning of the organization. The use of textbooks will enable students: to analyze key performance indicators, and use the tools of strategic analysis with reference to concrete situations in contemporary Russian and international business. Special attention is paid to the methods and systems of information support of the life support functions of business organizations and management methodology of innovation and investment. An Appendix contains source data for analysis of competition in a particular industry.
The paper provides a number of proposed draft operational guidelines for technology measurement and includes a number of tentative technology definitions to be used for statistical purposes, principles for identification and classification of potentially growing technology areas, suggestions on the survey strategies and indicators. These are the key components of an internationally harmonized framework for collecting and interpreting technology data that would need to be further developed through a broader consultation process. A summary of definitions of technology already available in OECD manuals and the stocktaking results are provided in the Annex section.
Over the last two decades national policy makers drew special attention to the implementation of policy tools which foster international cooperation in the fields of science, technology, and innovation. In this paper, we look at cases of Russian-German collaboration to examine the initiatives of the Russian government aimed at stimulating the innovation activity of domestic corporations and small and medium enterprises. The data derived from the interviews with companies’ leaders show positive effects of bilateral innovative projects on the overall business performance alongside with major barriers hindering international cooperation. To overcome these barriers we provide specific suggestions relevant to the recently developed Russian Innovation Strategy 2020.