Search

This paper proposes a new way to measure and deal with risk within the portfolio selection problem using a skewness/semivariance biobjective optimization framework. The solutions of this biobjective optimization problem allow the investor to analyse the efficient trade-off between skewness and semivariance. Due to the endogeneity of the cosemivariance matrix, the biobjective problem is solved using a derivative-free algorithm based on direct multisearch. For four datasets, collected from the Fama/French benchmark collection, the direct multisearch was able to determine the in-sample Pareto frontier. The out-of-sample performance of the skewness/semivariance model was assessed by choosing three portfolios (the portfolio that maximizes a skewness per semivariance ratio, the portfolio that maximizes the Sharpe ratio and the portfolio that maximizes the Sortino ratio) at each in-sample Pareto frontier and measuring their performance in terms of skewness per semivariance ratio, Sharpe ratio, Sortino ratio and turnover. The results show that the efficient skewness/semivariance portfolios are consistently competitive, and often superior, comparatively to the benchmark portfolios considered. Both in-sample and the out-of-sample performance analysis were conducted using three different benchmark returns for the semivariance computations.

In this paper we extend the study of the cardinality impact from the standard mean-variance scenario to higher moments, considering a utility maximization framework. For each scenario, we propose a bi-objective model that allows the investor to directly analyse the efficient trade-off between expected utility and cardinality. We study not only the effect of cardinality in each scenario but also the real gain of considering higher moments in portfolio management. This analysis is performed assuming that the investor has constant relative risk aversion (CRRA) preferences. For the data collected on the PSI20 index, the empirical results showed that there are no performance gains, in-sample, from the efficient mean-variance expected utility/cardinality portfolios to the efficient expected utility/cardinality portfolios when higher moments are considered. However, the out-of-sample performance of the efficient mean-variance-skewness expected utility/cardinality portfolios and of the efficient mean-variance-skewness-kurtosis expected utility/cardinality portfolios suggest the existence of real gains, especially when transaction costs are considered.

Forecasting Populations (FPOP) is a microsimulation model (MSM) that is the demographic core of an extensible modeling framework. The framework, with FPOP at its core, enables the geospatial projection of a population under purely demographic processes or under the additional influence of exogenous factors such as disease, policy changes and prevention programs, or environmental stressors. Empirically-derived transition probabilities of life events such as birth, death, marriage, divorce and migration, captured in lookup table format, drive the simulation. These transition probabilities can be modified dynamically by external user-defined functions or other external MSMs. The use of MSM structures and methodologies enables FPOP to portray the impact of heterogeneity in the geospatial dimension (e.g., distribution of environmental factors or distribution of intervention programs), as well as the social dimension (e.g., household or social network correlates), on the projections. POP is designed and structured to: enable linking with external MSMs of any kind; support inclusion or configuration of more detailed transition probabilities; be scalable to millions of agents; use either an existing baseline synthetic population or a custom synthetic population of the user’s design; and, run under computing environments that don’t require a high degree of specialized software or hardware. In this paper we describe the design and structure of FPOP and then apply FPOP first under purely demographic processes and, secondly, in conjunction with an external disease model of obesity.The objective of FPOP is to provide a demographically realistic projection of the size, structure, and movement of populations and households decades into the future.

Knowledge Analysis in Terms of Representation,Processing based Mobilisation and DistributionAbstract: Understanding, defining and using knowledge can be based on a number of many approaches, such as the synthesis of Knowledge Management Systems, Knowledge Agents, Knowledge Discovery and Data Mining, Organizational Semantic Webs. Knowledge is based on the accumulation of facts, procedural rules or heuristics. Knowledge is supported by both formal and informal processes and structures in their acquisition, sharing and applications. Workers and employees communicate and assimilate values, procedures, rules and data from the beginning of their activity in an organization, and hypothetically should begin to be increasingly willing to share what they know as their length of service increases. This paper presents a deep analysis of knowledge, as the basic pillar of the intelligent enterprise and of many other Intelligent Economic Systems. In this respect I emphasize that it is essential to realize that Knowledge Management is both a cultural and a technological provocation. We might say that the cultural aspect is a priority. Any system designed to support these challenges must extend far beyond the technological boundaries and take into account the people who will use it and contribute to its success. Our work demonstrates the main aspects and strategic advantages of knowledge representation, processing based mobilisation and distribution in the long process from integrating information and applications to automate knowledge worker functions. Developing systems that incorporate knowledge within organizations differs significantly from other systems, because it is absolutely necessary to associate operational interpretations with the information, in order to transform them into knowledge useful in various acts of decision.

Business intelligence is a business management term used to describe applications and technologies which are used to gather, provide access to, and analyse data and information about the organization, to help make better business decisions. The multi-agent approach provides a feasible solution for construction of the business intelligence system. This paper firstly briefly introduces the traditional business intelligence architecting principles and multi-agent approach. Secondly, a design of business intelligence system architecture is proposed, which is composed of the system framework, agent description and system workflow. This design allows to reduce effectively the construction costs of business intelligence systems and to extend the applied scope of business intelligence by minimizing the amount of data transfer and data storage. Using the predictive functionality of the system can bring a significant competitive advantage of business units. The paper presents a new approach for business intelligence architecture modelling, representing an extension over existing systems.

The increased globalization makes every country more and more responsible for its actions that are meant to support the price stability and the fiscal position sustainability in an unpredictable world. Decisions makers can provide the right solutions to overcome the latest global economic crisis by using methods of classifying the continuously growing amounts of digital economic data. The principles of neural networks are applied in order to classify a set of countries according to their statistical data for economic indicators provided by the European Committee. The results and performance of this classification technique is discussed in the final section of the paper.

The aim of the paper is to releve some aspects regarding a knowledge management system and a user model which will be implemented in the training process of the students.They are also presented some features and the personalization in a Knowledge Management Systems. The porpose is to develop an ontology for the user modelling in this context and later to use this in a multi agent system for the knowledge management.

Knowledge Management or knowledge-based management (noted and used throughout this paper as KM) is defined as a collaborative practice, by which organizations deliberately and intelligibly create, organize, distribute and analyze their own knowledge, in terms of resources, documents and people’s skills. It is widely regarded as an internal tool for increasing the operational efficiency of any organization, and has the potential to revolutionize the intelligent interaction between humans and agents (intelligent), based on more and more advanced technology. Semantic Technologies (STs) are distributed software technologies that make that meaning more explicit, principally so that it can be understood by computers. STs will dramatically impact enterprise architecture and the engineering of new system and infrastructure capabilities. They are tools that represent meanings, associations, theories, and know-how about the uses of things separately from data and knowledge, using reasoning algorithms. Time restrictions are not excessive in usual STs as distributed applications. Critical time reasoning problems may occur in case of faulty operations and overloading. At present, the reasoning depth developed for such system is still poor. This work represents research results for incorporating and considering appropriate semantic foundations in future technologies that can automate knowledge based work.

Data bases are one of the most important components in every large informatics system which stores and processes data and information. Because data bases contain all of the valuable information about a company, its clients, its financial activity, they represent one of the key elements in the structure of an organization, which determines imperatives such as confidentiality, integrity and ease of data access. The current paper discuses the integrity of data bases and it refers to the validity and the coherence of stored data. Usually, integrity is defined in connection with terms of constraint, that are rules regarding coherence which the data base cannot infringe. Data base that integrity refers to information correctness and assumes to detect, correct and prevent errors that might have an effect on the data comprised by the data bases.

We implement an agent-based financial market model simulation in which agents follow technical and fundamental trading rules to determine their speculative investment positions. We consider direct interactions between speculators due to which they may decide to change their trading behaviour. For instance, if a technical trader meets a fundamental trader and they realize that fundamental trading has been more profitable than technical trading in the recent past, the probability that the technical trader switches to fundamental trading rules is relatively high. In particular the influence of transaction costs is studied, which can be increased by the off-market regulation (for example in the form of taxes) on market stability, the overall volume of trade and other market characteristics.

A reduction of the algorithmic complexity of the fuzzy inference engine has the following property: the inputs (the fuzzy rules and the fuzzy facts) can be divided in two parts, one being relatively constant for a long a time (the fuzzy rule or the knowledge model) when it is compared to the second part (the fuzzy facts) for every inference cycle. The occurrence of certain transformations over the constant part makes sense, in order to decrease the solution procurement time, in the case that the second part varies, but it is known at certain moments in time. The transformations attained in advance are called pre-processing or knowledge compilation. The use of variables in a Business Rule Management System knowledge representation allows factorising knowledge, like in classical knowledge based systems. The language of the first-degree predicates facilitates the formulation of complex knowledge in a rigorous way, imposing appropriate reasoning techniques. It is, thus, necessary to define the description method of fuzzy knowledge, to justify the knowledge exploiting efficiency when the compiling technique is used, to present the inference engine and highlight the functional features of the pattern matching and the state space processes. This paper presents the main results of our project PR356 for designing a compiler for fuzzy knowledge, like Rete compiler, that comprises two main components: a static fuzzy discrimination structure (Fuzzy Unification Tree) and the Fuzzy Variables Linking Network. There are also presented the features of the elementary pattern matching process that is based on the compiled structure of fuzzy knowledge. We developed fuzzy discrimination algorithms for Distributed Knowledge Management Systems (DKMSs). The implementations have been elaborated in a prototype system FRCOM (Fuzzy Rule COMpiler).

As secure storage becomes more pervasive throughout the enterprise, the focus quickly moves from implementing encrypting storage devices to establishing effective and secure key management policies. Without the proper key generation, distribution, storage, and recovery, valuable data will be eventually compromised [9]. Although a considerable amount of research has been dedicated to encryption algorithms in the past decades, key management becomes an issue due to the quantity of data. For example, with millions of data you will need million set of keys. To manage and keep track of these keys, complexity and operational inefficiency becomes an issue. How to manage keys becomes a challenging task. Adequate understanding of these new challenges is essential to effectively devise new key management policies and mechanisms to guard against them. We discuss many of these methods in this new context to fill this gap.

This paper first applies the MODWT (Maximal Overlap Discrete Wavelet Transform) to Euro Area quarterly GDP data from 1995 – 2014 to obtain the underlying cyclical structure of the GDP components. We then design optimal fiscal and monetary policy within a large state-space LQ-tracking wavelet decomposition model. Our study builds a MATLAB program that simulates optimal policy thrusts at each frequency range where: (1) both fiscal and monetary policy are emphasized, (2) only fiscal policy is relatively active, and (3) when only monetary policy is relatively active. The results show that the monetary authorities should utilize a strategy that influences the short-term market interest rate to undulate based on the cyclical wavelet decomposition in order to compute the optimal timing and levels for the aggregate interest rate adjustments. We also find that modest emphasis on active interest rate movements can alleviate much of the volatility in optimal government spending, while rendering similarly favorable levels of aggregate consumption and investment. This research is the first to construct joint fiscal and monetary policies in an applied optimal control model based on the short and long cyclical lag structures obtained from wavelet analysis.

The aim of this paper is to investigate the impact of financial transaction tax (FTT) on the stability of financial market. The paper presents an agent-based financial market model and simulations, in which agents follow technical and fundamental trading rules to determine their speculative investment positions. The model developed by Westerhoff (2009) was chosen for the implementation and it was extended by FTT and arising transaction costs. As FTT may be defined variously, assets are understood as a tax object in this paper. The model includes direct interactions between speculators due to which they may decide to change their trading behaviour and deals with a technical and fundamental strategy of market participants. Results suggest that the modified model has a tendency to stabilize itself in a long-term if the fundamental trading rules overbear the technical trading method. This could be used, when the bubbles and the crashes occur in a financial market. Assets price would be stabilized, because its value targets near the fundamental value and the volatility would be also minimized. Substantial is setting the FTT at a low rate for market stabilization. If FTT and consequent transaction costs are too high, the financial system destabilizes and the price grows without limit.

In the article the questions of automation of the insurance company. Emphasized the use of information technology to the field of insurance. Described created using MS Access database

We introduce a topic in the intersection of symbolic mathematics and computation, concerning topics in multivariable Optimization and Dynamic Analysis. Our computational approach gives emphasis to mathematical methodology and aims at both symbolic and numerical results as implemented by a powerful digital mathematical tool, CAS software Xcas. This work could be used as guidance to develop course contents in advanced calculus curricula, to conduct individual or collaborative projects for programming related objectives, as Xcas is freely available to users and institutions. Furthermore, it could assist educators to reproduce calculus methodologies by generating automatically, in one entry, abstract calculus formulations.

Business simulations are useful tools due to the fact that it eases management decision making. No doubt there are many processes which must be considered and simulated. Therefore, such business simulator is often composed of many processes and contains many agents and interrelations as well. Since the business simulator based on multi-agent system is characterized by many interrelations within, this article deals with a specific part of the business simulator only – a demand function and its modeling. The aim of this partial research is to suggest demand function which would be most suitable for the business simulation. In this paper a new approach for customer decision function in business process simulation was presented. The decision of the customer is based on Marshallian demand function and customer utility function using Cobb-Douglas preferences. The results obtained by means of the MAREA simulation environment proved that this approach yields correct simulation results.

We present JAS 2, a new Java platform which aims at providing a unique simulation tool for discrete-event simulations, including agent-based and dynamic microsimulation models. JAS 2 is not released as a self-contained stand-alone application for model development. With the aim to develop large-scale, computationally resource-intensive models, the main architectural choice of JAS 2 is to use whenever possible standard, open-source tools aready available in the software development community. This decision entails a longer learning curve for the user than a dedicated, language-specific software package, but it allows for a more professional approach to simulation modeling compared to specific proprietary environments. There are two main advantages of using an open architecture where external libraries can be added and utilized: one is the possibility to easily integrate external functions that can be added as plug-ins; the other is the possibility to freely extend and modify the functions available on the platform, possibly within a cooperative effort of the community of users. Moreover, an open source application makes it easier to share and test the models. Building on the vast number of software solutions available, JAS 2 allows the user to separate data representation and management from the implementation of processes and behavioral algorithms. It also allows the user, within an object-oriented paradigm, to model the real-life system naturally and intuitively: each category of individuals or objects that populate the model is represented by a specific class, with its own variables and methods. The main value added of the platform lies in the potential for integration with RDBMS (relational database management) tools through ad-hoc microsimulation Java libraries. The management of input data persistence layers and simulation results is performed using standard database management tools, and the platform takes care of the automatic translation of the relational model (which is typical of a database) into the object-oriented simulation model.

Klein (2000) advocates the use of the Schur decomposition of a matrix pencil o solve linear rational expectations (RE) models. Meanwhile his algorithm has ecome a center piece in several computer codes that provide approximate olutions to (non-linear) dynamic stochastic general equilibrium (DSGE) models. A ubtlety not resolved by Klein is whether or not a certain Schur decompostion ould fail to solve the model while a second one would provide a solution. We how that this cannot happen.

Modern microeconomics and macroeconomics study dynamic phenomena. Dynamics could predict future states of an economy based on its structural characteristics. Economic dynamics are modeled in discrete and continuous time context, mainly via autonomous difference and differential equations. In this study, we use Xcas and Mathematica as software tools, in order to generate results concerning the dynamic properties of the solutions of the difference and differential equation(s) models and determine whether an economic equilibrium exists. Our computational approach does not require solving the difference or differential equation(s) and makes no assumptions for initial conditions. The results provide quantitative information based on the qualitative properties of the mathematical solutions. The computer codes are fully presented and can be reproduced as they are in computational-based research practice and education. The relevant output of CAS software is created in a way as to be interpreted without the knowledge of advanced mathematics.

Computational Statistics is an international journal that fosters the publication of applications and methodological research in the field of computational statistics. In this article, we will discuss the motivation, history, some specialties, and the future scope of this journal.

Our paper "Generalized Hukuhara Differentiability of Interval-valued Functions and Interval Differential Equations", appeared in Nonlinear Analysis 71 (2009), contains some imprecisions. In this note we correct them and give few new results on the topic.

Computations with large matrices work out faster with computer software, even faster creating automatically the matrix of the size and pattern needed. In this paper we propose free computer algebra system Xcas resources to display particular matrices that can be called up directly. Our computer codes provide shortcuts for entering random block diagonal matrices, random triangular matrices, random and specialized band matrices, elementary matrices Eij, Fourier matrices. As for matrices needed in the study of mathematical issues concerning the properties of the roots of a polynomial, we create features with polynomial coefficients. We also propose codes for immediate construction of functional matrices such as Jacobian, bordered Hessian and Wronskian. The computer codes proposed provide visual representation of the matrix pattern (which is traditionally explained using indices and numerals), infinite number of examples using random numbers and immediate construction of large matrices of various forms.

In the present paper, we use a new generalization of the Hukuhara di¤erence and derivative for fuzzy-valued functions, and we study several properties of the new concepts in the setting of the LU-parametric representation of fuzzy numbers, as- sessed both from theoretical and computational points of view.

Local (perturbation) methods compute solutions in one point and tend to deliver far lower accuracy levels than global solution methods. We develop a hybrid method that solves for some policy functions locally (using a perturbation method) and that solves for the other policy functions globally (using closed-form expressions and a numerical solver). We applied our hybrid method to solve large-scale RBC models used in the comparison analysis of Kollmann et al. (J Econ Dyn Control 35:186–202, 2011b). We obtain more accurate solutions than those produced by any other (either local or global) solution method participating in that comparison. Our running time is a few seconds. Lilia Maliar and Serguei Maliar acknowledge support from the Hoover Institution at Stanford University, the Ministerio de Ciencia e Innovación de España and FEDER funds under the project SEJ-2007-62656, the Ivie, and the Generalitat Valenciana under the grants BEST/2011/283 and BEST/2011/282, respectively.

This paper uses half-hourly electricity demand data in South Australia as an empirical study of nonparametric modeling and forecasting methods for prediction from half-hour ahead to one year ahead. A notable feature of the univariate time series of electricity demand is the presence of both intraweek and intraday seasonalities. An intraday seasonal cycle is apparent from the similarity of the demand from one day to the next, and an intraweek seasonal cycle is evident from comparing the demand on the corresponding day of adjacent weeks. There is a strong appeal in using forecasting methods that are able to capture both seasonalities. In this paper, the forecasting methods slice a seasonal univariate time series into a time series of curves. The forecasting methods reduce the dimensionality by applying functional principal component analysis to the observed data, and then utilize an univariate time series forecasting method and functional principal component regression techniques. When data points in the most recent curve are sequentially observed, updating methods can improve the point and interval forecast accuracy. We also revisit a nonparametric approach to construct prediction intervals of updated forecasts, and evaluate the interval forecast accuracy.

The knowledge management systems based on artificial reasoning (KMAR) tries to provide computers the capabilities of performing various intelligent tasks for which their human users resort to their knowledge and collective intelligence. There is a need for incorporating aspects of time and imprecision into knowledge management systems, considering appropriate semantic foundations. The aim of this paper is to present the FRTES, a real-time fuzzy expert system, embedded in a knowledge management system. Our expert system is a special possibilistic expert system, developed in order to focus on fuzzy knowledge.

For the Semantic Web point of view, computers must have access to structured collections of information and sets of inference rules that they can use to conduct automated reasoning. Adding logic to the Web, the means to use rules to make inferences, choose courses of action and answer questions, is the actual task for the distributed IT community. The real power of Intelligent Web will be realized when people create many programs that collect Web content from diverse sources, process the information and exchange the results with other programs. The first part of this paper is an introductory of Semantic Web properties, and summarises agent characteristics and their actual importance in digital economy. The second part presents the predictability of a multiagent system used in a learning process for a control problem.

This paper is the second part of The Semantic Web Paradigm for a Real-time Agent Control, and the goal is to present the predictability of a multiagent system used in a learning process for a control problem (MASLCP).

The aim of this paper is to develop a hedging methodology for making a portfolio of options delta, vega and gamma neutral by taking positions in other available options, and simultaneously minimizing the net premium to be paid for the hedging. A quadratic programming solution for the problem is formulated, and then it is approximated to a linear programming solution. A prototype for the linear programming solution has been developed in MS Excel using VBA.

Voting features based classifiers. shortly VFC. have been shown to perform well on most real-world data sets They are robust to irrelevant features and missing feature values. In this paper, we introduce an extension to VFC. called voting features based classifier with feature construction, VFCC for short, and show its application to the problem of predicting if a bank will encounter financial distress by analyzing, current financial statements. The previously developed VFC learn a set of rules that contain a single condition based on a single feature in their antecedent. The VFCC algorithm proposed in this work, oil the other hand, constructs rules whose antecedents may contain conjuncts based on several features. Experimental results on recent financial ratios of banks in Turkey show that the VFCC algorithm achieves better accuracy than other well-known rule learning classification algorithms (C) 2009 Elsevier Ltd. All rights reserved

This paper is a successor of [AK08]. Both papers describe the same suite of MATLAB R° routines devised to provide an approximately optimal solution to an infinite horizon stochastic optimal control problem. The difference is that this paper explains how to allow for state and control constraints. The suite routines implement a policy improvement algorithm to optimise a Markov decision chain approximating the original control problem, as described in [Kra01c] and [Kra01b].

The aim of this paper is to develop an algorithm for calculating and plotting payoff of option strategies for a portfolio of path independent vanilla and exotic options. A general algorithm for calculating the vector matrix for any arbitrary combination strategy is also developed for some of the commonly option trading strategies.

In this paper we have proposed a method to conduct the ordinal canonical correlation analysis (OCCA) that yields ordinal canonical variates and the coefficient of correlation between them, which is analogous to (and a generalization of) the rank correlation coefficient of Spearman. The ordinal canonical variates are themselves analogous to the canonical variates obtained by the conventional canonical correlation analysis (CCCA). Our proposed method is suitable to deal with the multivariable ordinal data arrays. Our examples have shown that in finding canonical rank scores and canonical correlation from an ordinal dataset, the CCCA is suboptimal. The OCCA suggested by us outperforms the conventional method. Moreover, our method can take care of any of the five different schemes of rank ordering. It uses the Particle Swarm Optimizer which is one of the recent and prized meta-heuristics for global optimization. The computer program developed by us is fast and accurate. It has worked very well to conduct the OCCA.

This paper illustrates the value of interoperability in the delivery of Government e-services: Governmentto- Government, business-to-Government and citizen-to-Government. It describes the many issues involved in achieving successful interoperability programs—together with the tools, technologies and standards that help make this possible.

In the present paper we introduce and study a generalization of the Hukuhara differ- ence and also generalizations of the Hukuhara differentiability to the case of interval valued functions. We consider several possible definitions for the derivative of an interval valued function and we study connections between them and their proper- ties. Using these concepts we study interval differential equations. Local existence and uniqueness of two solutions is obtained together with characterizations of the solutions of an interval differential equation by ODE systems and by differential algebraic equations. We also show some connection with differential inclusions. The thoretical results are turned into practical algorithms to solve interval differential equations.

We propose a generalization of the Hukuhara difference. First, the case of compact convex sets is examined; then, the results are applied to generalize the Hukuhara difference of fuzzy numbers, using their compact and convex level-cuts. Finally, a similar approach is seggested to attempt a generalization of division for real intervals and fuzzy numbers.

Correlation matrices have many applications, particularly in marketing and financial economics - such as in risk management, option pricing and to forecast demand for a group of products in order to realize savings by properly managing inventories, etc. Various methods have been proposed by different authors to solve the nearest correlation matrix problem by majorization, hypersphere decomposition, semi-definite programming, or geometric programming, etc. In this paper we propose to obtain the nearest valid correlation matrix by the differential evaluation method of global optimization. We may draw some conclusions from the exercise in this paper. First, the ‘nearest correlation matrix problem may be solved satisfactorily by the evolutionary algorithm like the differential evolution method/Particle Swarm Optimizer. Other methods such as the Particle Swarm method also may be used. Secondly, these methods are easily amenable to choice of the norm to minimize. Absolute, Frobenius or Chebyshev norm may easily be used. Thirdly, the ‘complete the correlation matrix problem’ can be solved (in a limited sense) by these methods. Fourthly, one may easily opt for weighted norm or un-weighted norm minimization. Fifthly, minimization of absolute norm to obtain nearest correlation matrices appears to give better results. In solving the nearest correlation matrix problem the resulting valid correlation matrices are often near-singular and thus they are on the borderline of non-semi-positive-definiteness. One finds difficulty in rounding off their elements even at 6th or 7th places after decimal, without running the risk of making the rounded off matrix non-positive definite. Such matrices are, therefore, difficult to handle. It is possible to obtain more robust positive definite valid correlation matrices by constraining the determinant (the product of eigenvalues) of the resulting correlation matrix to take on a value significantly larger than zero. But this can be done only at the cost of a compromise on the criterion of ‘nearness.’ The method proposed by us does it very well.

The LU-model for fuzzy numbers has been introduced in [4] and applied to fuzzy calculus in [9]; in this paper we build an LU-fuzzy calculator, in order to explain the use of the LU-fuzzy representation and to show the advantage of the parametrization. The calculator produces the basic fuzzy calculus: the arithmetic operations (scalar multiplication, addition, subtraction, multiplica- tion, division) and the fuzzy extension of many univariate functions (power with integer positive or negative exponent, exponential , logarithm, general power function with numeric or fuzzy exponent, sin, arcsin, cos, arccos, tan, arctan, square root, Gaussian and standard Gaussian functions, hyperbolic sinh, cosh, tanh and inverses, erf error function and complementary erfc error function, cu- mulative standard normal distribution). The use of the calculator is illustrated.

In this paper, we try to promote the building of a Quantitative Austrian Modelling (QAM). QAM must be viewed as a complementary quantitative prolongation of the Austrian methods and as a complementary approach to the already existing quantitative approaches - especially we would like here to answer to the appeal of Prof. N.J.Vriend [61]. As we explain it in the first part, our approach resulted from a critical view of the econometric procedures by Austrian methods and, from a theoretical instrumental study of the econometric models. We define the main properties to quantitative approaches and especially to the QAM. In the second part, we present QAM principles and equations (of the AUSTRIAN model), and justify it according to the classical Austrian point of view. The QAM could be viewed as an answer to Prof. M.J.Rizzo [49] about the relationship between the Praxeology and the Econometrics. Indeed, according to its properties, even if QAM won't be able to recreate any observable data, it could give a consistent pattern where the other quantitative approaches could fit. Especially, QAM could help, we hope so, to answer the question we asked about the quality of the econometric behavioral equations [8], in providing two levels of data, from where we could extract a relationship useful to correct observable econometric data. QAM is in building.

Correlation matrices have many applications, particularly in marketing and financial economics. The need to forecast demand for a group of products in order to realize savings by properly managing inventories requires the use of correlation matrices. In many cases, due to paucity of data/information or dynamic nature of the problem at hand, it is not possible to obtain a complete correlation matrix. Some elements of the matrix are unknown. Several methods exist that obtain valid complete correlation matrices from incomplete correlation matrices. In view of non-unique solutions admissible to the problem of completing the correlation matrix, some authors have suggested numerical methods that provide ranges to different unknown elements. However, they are limited to very small matrices up to order 4. Our objective in this paper is to suggest a method (and provide a Fortran program) that completes a given incomplete correlation matrix of an arbitrary order. The method proposed here has an advantage over other algorithms due to its ability to present a scenario of valid correlation matrices that might be obtained from a given incomplete matrix of an arbitrary order. The analyst may choose some particular matrices, most suitable to his purpose, from among those output matrices. Further, unlike other methods, it has no restriction on the distribution of holes over the entire matrix, nor the analyst has to interactively feed elements of the matrix sequentially, which might be quite inconvenient for larger matrices. It is flexible and by merely choosing larger population size one might obtain a more exhaustive scenario of valid matrices. Moreover, the Differential Evolution algorithm is amenable to parallelization.

In this paper we illustrate the LU representation of fuzzy numbers and present an LU-fuzzy calculator, in order to explain the use of the LU-fuzzy model and to show the advantage of the parametrization. The model can be applied either in the level-cut or in generalized LR frames. The hand-like fuzzy calculator has been developed for the MSWindows platform and produces the basic fuzzy calculus: the arithmetic operations (scalar multiplication, addition, subtraction, multiplication, division) and the fuzzy extension of many univariate functions (exponential, logarithm, power with numeric or fuzzy exponent, sin, arcsin, cos, arccos, tan, arctan, square root, Gaussian, hyperbolic sinh, cosh, tanh and inverses, erf and erfc error functions, cumulative standard normal distribution).

In this paper we introduce some new test functions to assess the performance of global optimization methods. These functions have been selected partly because several of them are aesthetically appealing and partly because a few of them are really difficult to optimize, while all the functions are multi-modal. Each function has been graphically presented to appreciate its geometrical appearance. To optimize these functions we have used the Repulsive Particle Swarm (RPS) method. We have also appended a computer program of the RPS method. Except two functions, namely the 'crowned cross' and the 'cross-legged table' functions all other new test functions are optimized by the RPS program.The program has also been tested with success on a number of well-established benchmark functions. However, the program fails miserably in optimizing the Bukin and a couple of other functions. Note: Readers should beware of the plagiarism by one Mr. Sanjeev K Singh, Tezpur University, Assam, who, in his article "A Comparative Study of Genetic Algorithm, Improved-Repulsive Particle Swarm Optimization and Simulated Annealing" published in the proceedings of Advances in Computational Optimization and Analysis of Systems (COSA 2007), 6-9 February, 2007 Outreach Centre, IIT, Kanpur, attributes introduction of some new functions (Bird function, Penholder function, Cross function, etc) and the improved Particle Swarm method to himself.

The Prisoner Dilemma is a typical structure of interaction in human societies. In spite of a long tradition dealing with the matter from different perspectives, the emergence of cooperation or defection still remains a controversial argument from both empirical and theoretical point of views. In this paper an innovative model is presented and analyzed in the attempt to provide a reasonable framing of the issue. A population of boundedly rational agents repeatedly chooses to cooperate or defect. Each agent’s action affects only her interacting mates, according to a network of relationships which is endogenously modifiable since agents are given the possibility to substitute undesired mates with unknown ones. Full cooperation, full defection and coexistence of both cooperation and defection in homogeneous clusters are possible outcomes of the model. A computer program is developed with the purpose of understanding the impact of parameters values on the type of outcome. Numerous simulations are run and the resulting evidence is analyzed and interpreted

Recent financial crises and especially large corporate bankruptcies, have led bank managements and financial authorities to follow and monitor both financial and real sector risks, and to focus on firm failures. Bank of International Settlements, has therefore, taken the decision to include the necessity for banks to employ internal rating systems among BASEL II criteria. Thus, risk assessment and internal rating systems criteria would be made operational by the individual European Union banking systems, by the end of 2007, and January 2008 in Turkey, at the latest. Financial and operational information of the firms, makes up the input to the risk analysis. This information can be aggregated to portray the sectoral trends, and/or focused upon on a firm basis to understand firms’ financial behaviours. Finance theory summarizes firms’ risks under financial distress and firm failure. There have been a myriad of works under these two headings, particularly in the United States, after the Great Depression. While early studies have focused upon the differences in the financial ratios of financially sound and failed firms, especially with the advances in computing capacity, the last two decades have witnessed an increasing use of machine learning methods in the failure prediction. Therefore, machine learning methods can be considered as having great potential in failure prediction and being good candidates as decision aids for policy-making. This study considers financial distress and firm failure on theoretical grounds, gives a compact but elaborate explanation of machine learning schemes, and analyzes the results of these schemes run with data obtained from the database of Real Sector Data Division of the Central Bank. Cost sensitive learning was given special attention in the analysis.

The parameterized expectations algorithm (PEA) involves a long simulationand a nonlinear least squares (NLS) fit, both embedded in a loop. Both steps are natural candidates for parallelization.This note shows that parallelization can lead to important speedups forthe PEA.I provide example code for a simple model that can serve as a templatefor parallelization of more interesting models, as well as a download linkfor an image of a bootable CD that allows creation of a cluster and executionof the example code in minutes, with no need to install any software.

This paper solves an incomplete market model with infinite number of agents and exogenous borrowing constraints described in den Haan, Judd and Juillard (2004). We apply the idea of “barrier methods” to convert optimization problem with borrowing constraints as inequalities into a problem with equality constraints, and the converted model is solved by a second-order perturbation method. The simulation results of impulse responses and second moments match the standardized features of incomplete market models. Accuracy of the solution is in a reasonable range but significantly decreases when the economy is near the borrowing limit or moves away from the steady state.

A welfare analysis of policies for risk averse preferences is handicapped within linear or linearized models and their certainty equivalence property. I calculate the optimal policy in a nonlinear stochastic dynamic general equilibrium model. Then I estimate the posterior density of structural parameters and the marginal likelihood within a nonlinear state space model. The computational challenges are considerable and I concentrate on the numerics and statistics for a simple model of dynamic consumption and labor choice. It is estimated on simulated data in order to test the routines with known true parameters. The code is written for a general model class. The policy function is approximated by Smolyak Chebyshev polynomials and the rational expectation integral by Smolyak Gaussian quadrature. The Smolyak operator is used to extend univariate approximation and integration operators to many dimensions. It is also called boolean method, hyperbolic cross points, discrete or sparse grids, fully symmetrical integration rules or complete polynomials. It reduces the curse of dimensionality from exponential to polynomial growth. The likelihood integrals are evaluated by a Gaussian quadrature and Gaussian quadrature particle filter. The bootstrap or sequential importance resampling particle filter, based on a Monte Carlo integration, is used as an accuracy benchmark. The posterior is estimated by the Gaussian filter and a Metropolis-Hastings algorithm. I propose a genetic extension of the standard Metropolis-Hastings algorithm by parallel random walk sequences. The candidate parameter vectors are constructed by innovation from the parallel sequences in addition to the usual random walk shocks. This improves the robustness of start values and the global maximization properties. Moreover it simplifies a cluster implementation and the random walk variances decision is reduced to only two parameters so that almost no trial sequences are needed. Finally the marginal likelihood is calculated as a criterion for nonnested and quasi-true models in order to select between the nonlinear estimates and a first order perturbation solution combined with the Kalman filter.

This note describes ParallelKnoppix, a bootable CD that allows creationof a Linux cluster in very little time.An experienced user can create a cluster ready to execute MPI programsin less than 10 minutes.The computers used may be heterogeneous machines, of the IA-32 architecture.When the cluster is shut down, all machines except one are in their originalstate, and the last can be returned to its original state by deleting adirectory.The system thus provides a means of using non-dedicated computers to createa cluster.An example session is documented.

In simulation we often have to generate correlated random variables by giving a reference intercorrelation matrix, R or Q. The matrix R is positive definite and a valid correlation matrix. The matrix Q may appear to be a correlation matrix but it may be invalid (negative definite). With R(m,m) it is easy to generate X(n,m), but Q(m,m) cannot give real X(n,m). So, Q has to be converted into the near-most R matrix by some procedure. NJ Higham (2002) provides a method to generate R from Q that satisfies the minimum Frobenius norm condition for (Q-R). Ali Al-Subaihi (2004) gives another method, but his method does not produce an optimal R from Q. In this paper we propose an algorithm to produce an optimal R from Q by minimizing the maximum norm of (Q-R). A Computer program (in FORTRAN) also has been provided. Having obtained R from Q, the paper gives an algorithm to obtain X(n,m) from R(m,m). The proposed algorithm is based on factorization of R, yet it is different from the Kaiser Dichman (1962) procedure. A computer program also has been given.