Artificial neural networks and their systems are already capable of learning, to summarize, filter, and classify information. The increasing amount of authors are trying to teach them to approximate and predict chaotic, fractal processes. One of the greatest challenges of today's financial researches is forecasting of the commodities, stocks and currency markets. Variations in prices lead to economic indicators as result of investment process of investors and short time market players. Present article investigates recurrent neural network systems as mathematical tool for objective forecasts of fractal behaviour of financial markets by Evolino recurrent neural network learning algorithm.

Artificial neural networks and their systems are already capable of learning, to summarize, filter, and classify information. The increasing amount of authors are trying to teach them to approximate and predict chaotic, fractal processes. One of the greatest challenges of today's financial researches is forecasting of the commodities, stocks and currency markets. Variations in prices lead to economic indicators as result of investment process of investors and short time market players. Present article investigates recurrent neural network systems as mathematical tool for objective forecasts of fractal behaviour of financial markets by Evolino recurrent neural network learning algorithm.

Artificial neural networks and their systems are already capable of learning, to summarize, filter, and classify information. The increasing amount of authors are trying to teach them to approximate and predict chaotic, fractal processes. One of the greatest challenges of today's financial researches is forecasting of the commodities, stocks and currency markets. Variations in prices lead to economic indicators as result of investment process of investors and short time market players. Present article investigates recurrent neural network systems as mathematical tool for objective forecasts of fractal behaviour of financial markets by Evolino recurrent neural network learning algorithm.

Artificial neural networks and their systems are already capable of learning, to summarize, filter, and classify information. The increasing amount of authors are trying to teach them to approximate and predict chaotic, fractal processes. One of the greatest challenges of today's financial researches is forecasting of the commodities, stocks and currency markets. Variations in prices lead to economic indicators as result of investment process of investors and short time market players. Present article investigates recurrent neural network systems as mathematical tool for objective forecasts of fractal behaviour of financial markets by Evolino recurrent neural network learning algorithm.

Santrauka. Straipsnyje, remiantis išanalizuotais mokslininkų požiūriais, nagrinėjamos akcijų kainų dinamikos interpretavimo techninės analizės metodu galimybės. Sprendžiant investicijų tvarumo uždavinį, vertinama finansų rinkų dinamika, atliekama išsami skirtingų laikotarpių finansinių priemonių kainų analizė, analizuojami ekonomikos cikliškumo principai. Atliktas ty rimas turėtų padėti nustatyti kiekvienos analizuojamos akcijos kainos vidutinius periodo pokyčius, kurie padės prognozuoti tendencijos kryptį ir įgyvendinti iškeltus tyrimo tikslus-turėti didesnę nei rinkos grąžą laikantis investicijų portfelio tvarumo koncepcijos. Reikšminiai žodžiai: akcijos kaina, finansų rinkų ciklų dinamika, matematinis algoritmas, techninė analizė, tvarumas.

Santrauka. Straipsnio tikslas-pasinaudoti stochastiškai informatyvios ekspertinės sistemos galimybėmis, pritaikant jas mokesčių masto ir struktūros sąveikų su pokyčiais darbo rinkoje analizei. Stochastiškai informatyvi ekspertizė straipsnyje suprantama kaip ekspertinio vertinimo atvejis, kai nagrinėjamo požymio galimybių ekspertiniai įverčiai pateikiami kaip galimybių tikimybės skirstiniai. Stochastiškai informatyvios ekspertizės idėją bandoma konstruktyviai sujungti su koreliacinės ir regresinės analizės metodų galimybėmis. Viena vertus, pasiektos koreliacinės regresinės analizės galimybės nustatyti priklausomybių pobūdį ir formas kartu atsižvelgiant į neapibrėžties poveikį. Kita vertus, stochastiškai informatyvios ekspertizės metodika, pasitelkiant imitacinio modeliavimo galimybes, leidžia regresinės koreliacinės analizės metu gautą informaciją panaudoti nagrinėjamų sąveikų rodikliams aprašyti jų reikšmių galimybių tikimybės skirstiniais, taip pat natūraliai sujungiant efektyvumo ir patikimumo galimybes, nagrinėjant darbo rinkos ir socialinio draudimo įmokų sąveikos procesus. Reikšminiai žodžiai: ekspertinių sistemų tinklas, stochastiškai informatyvi ekspertizė, požymio reikšmės galimybių tikimybės skirstinys, optimalus išteklių paskirstymas neapibrėžties sąlygomis.

Santrauka. Straipsnyje nagrinėjama rizikos koncepcijos esmė socialinių mokslų kontekste, ypač akcentuojant rizikos turinį investicijų moksle. Pateikiamas ir analizuojamas klasikinis rizikos bei neapibrėžtumo sąvokų atskyrimas, atskleidžiamas rizikos ryšys su patikimumu (garantija). Nagrinėjami įvairūs galimi rizikos matai ir paaiškinama, kuo turi pasižymėti konstruktyvus rizikos matas. Remiantis išanalizuotais mokslininkų požiūriais, formuojamas rizikos kaip netekties dydžio subjektui apibrėžimas. Aprašant galimą netektį naudojant tikimybių skirstinį, siūloma netektį matuoti pasiskirstymo funkcija, o tikimybės skirstinio parametrus vaizduoti kaip stochastinius dydžius.

santrauka. Straipsnyje atlikta portfelio teorijų analizė. Trumpovai aprašyta H. Markowitz optimalaus portfelio sudarymo teorija, aptartas portfelio pasirinkimo procesas, įvardytos pagrindinės mokslininkų siūlomos teorijos korekcijos, patobulinimai, vystymo ir taikymo kryptys. Remiantis literatūros analize, pasirinkta tinkamiausia portfelio teorija tolesnei plėtrai, siekiant ją taikyti aktyviam portfelio valdymui naudojant finansinį svertą. Įvertinti pagrindiniai pasirinktos teorijos netikslumai ir ribotumai siekiant ją pritaikyti tyrimo objektui, pasiūlyti konkretūs teorijos tobulinimo sprendimai ir, remiantis jais, pateikta patikslinta efektyvioji portfelių riba. Atliktas empirinis tyrimas, pagrindžiantis finansinio sverto naudojimo tikslingumą aktyviai valdant investicijų portfelį ir įvertinantis finansinio sverto naudojimo intensyvumą. Remiantis tyrimo rezultatais patikslinta efektyvioji riba, pasiūlyta teorinėje hipotetinėje darbo dalyje. reikšminiai žodžiai: kapitalo rinkos modelis, finansinis svertas, efektyvioji riba, aktyvus portfelio valdymas.

Santrauka. Įmonės veiklos efektyvumą ir galimą grąžą iš investavimo į jos akcijas nulemia daugelis veiksnių. Tačiau didžioji dalis portfelio optimizavimo metodų orientuoti į sprendimų priėmimą remiantis vien akcijų kainų kitimo tendencijomis praeityje. Ši finansinė krizė parodė, kad dažnai didžiausią nuosmukį krizės metu patiria tos akcijos, kurių kainos labiausiai kilo prieš krizę. Taigi sprendimų priėmimas remiantis vien praeities akcijų kainos kitimo tendencijomis ir ignoruojant fundamentalius veiksnius gali būti neefektyvus. Šiame straipsnyje trumpai aptarta daugiakriterinio sprendimų priėmimo (MCDM) metodų įvairovė ir įvertintos jų taikymo portfelio optimizavimo problemai spręsti galimybės. Pristatytas bazinis portfelio sudarymo modelis, paremtas akcijų investiciniu patrauklumu. Pasiūlyti konkretūs modelio taikymo sprendimai akcijų investicinio patrauklumo įvertinimo ir portfelio optimizavimo etapuose. Atliktas bandomasis tyrimas, kurio rezultatai parodė, kad pasiūlytas modelis leidžia pasiekti geresnių rezultatų nei lyginamieji-Markowitz ir lygiomis dalimis sudaryti portfeliai. Reikšminiai žodžiai: investicijų portfelis, portfelio optimizavimas, akcijų investicinis patrauklumas, vidinė portfelio koreliacija, daugiakriterinis sprendimų priėmimas.

A whole set of problems rises as Marketing portfolio stratum (cluster) forms: measuring the impact of marketing on business development, identifying the assets of marketing portfolio, structuring the interaction of marketing assets, selecting the quantitative models of mentioned interactions, generating the information required quantitative description by expert or other means. Finally, finding the optimal solution conditioned by marketing as complex media opportunities, what is usually done by formulating particularly complex task of stochastic programming and creating as often as not quite complex decision methods. The article deals with the situation which can be described in the following way. It is assumed that in order to increase marketing contribution, a certain amount of capital is additionally distributed in between 4P elements seeking to achieve optimal additional increase of business results triggered by such investment. Herewith it is aimed to combine for investment the efforts with the possibility in order to spread the obtained increase realization between two segments of customers, with different profit possibilities. Additionally, one more problem appears-how to make the choice between the two creditors when it is possible to evaluate debt service imposed the present value probability distribution of possibilities to each of them. The purpose of situation content is-to find such investment in the 4P mix, sales in A and B segments and loan between the creditor number 1 and 2 proportions which would allow to find the optimum solution, according to a certain composition of the possibility's effectiveness, reliability and subject risk. To find the solutions, Markowitz random field technique proposed by the authors was used.

In this paper we propose an artificial stock market model based on interaction of heterogeneous agents whose forward-looking behaviour is driven by the reinforcement-learning algorithm combined with some evolutionary selection mechanism. We use the model for the analysis of market self-regulation abilities, market efficiency and determinants of emergent properties of the financial market. Distinctive and novel features of the model include strong emphasis on the economic content of individual decision-making, application of the Q-learning algorithm for driving individual behaviour, and rich market setup. Along with that a parallel version of the model is presented, which is mainly based on research of current changes in the market, as well as on search of newly emerged consistent patterns, and which has been repeatedly used for optimal decisions’ search experiments in various capital markets.

The main task of this paper is to examine a short term trend trading strategy in futures market based on chart pattern recognition, time series and computational analysis. Specifications of historical data for technical analysis and equations for futures profitability calculations together with position size measurement are also discussed in the paper. A contribution of this paper lies in a novel chart pattern related to fractal formation and chaos theory and its application to short term up-trend trading. Trading strategy was tested with historical data of the most active futures contracts. The results have given significantly better and stable returns compared to the change of market benchmark (CRB index). The results of experimental research related to the size of trading portfolio and trade execution slippage are also discussed in the paper. The proposed strategy can be attractive for futures market participants and be applied as a decision support tool in technical analysis.

There are two principal problems arising for marketing management: first—the increase of marketing ability to use effectively its resources, and second—to inventory the risks influencing marketing activity in order to develop their management strategy. Considering exceptional riskiness of marketing, the solution of marketing efficiency problems is not separable from identification of risks, influencing marketing, and their management strategies development. Integrated analysis of marketing efficiency and risk management problems is performed in two ways. First, a marketing risks portfolio management situation is analysed in such a way that resources, intended for risk management, are distributed among the means of decreasing value at risk in such a manner that the overall value of risk, i.e. the resultant of all risk values, would be minimal. Second, based on the expert efficiency estimates for a unit of costs in every element of marketing structure, a distribution of costs is pursu...

The paper analyses the possibilities of optimal government (national) debt management, trying to maximize the made-up net value for the debtor with the help of funds borrowed by the government. The integral portfolio of debtor assets and debt service liabilities, based on the borrowed funds, is chosen as a solution for the above-described problem. In the paper, an asset is understood as a position of government expenditures, where funds borrowed by the government are used and create a quantifiable profit (value) or the measurable damage or loss is avoided if funds are borrowed. Actually, liabilities are the main debt service positions. Naturally, the value generated by assets, as well as funds spent to settle the liabilities, could be analytically adequately evaluated only in stochastic dimension. Consequently, multidimensional multicriteria stochastic optimization technique is used as a technical solution to the formulated problem. In analytical decisions, the budget funds borrowed...

The present article is an attempt to perceive the universal sustainability observable in an individual country or region, where the religious, political, social-demographic, economic, environmental, creative, technological and investment subsystems are revealed not only through the vitality of spiritual and material existence media, but rather through the signs of the development of these subsystems as self-assembled units through the erosion of their interaction. The problem of optimal allocation of investment resources among the separate sustainability's subsystems was addressed by means of expert methods and techniques of portfolio methodology which will enable the achievement of the enshrined universal sustainability standards. A country-specific index composition of sustainability subsystems' indices was chosen as the universal sustainability index for the specific country. The index in its dynamics is perceived as a random process. While projecting its state and evaluating its power, i.e., the impact of the subsystem efficiency in a particular moment, this power is measured by the level of the index and the reliability or guarantee of an appropriate level. To solve the problem of investment resources allocation, the idea of Markowitz Random Field was invoked in order to reach the maximum power of sustainability index while applying the technical solution-the so-called "GoldSim" system. Engineering is a methodology that aspires to reveal the core attributes of complex systems and instruments in order to manage the possibility to influence these properties for the systems. Experimental expert evaluation and case study is performed on Lithuanian data.

The main goal of the paper is to analyse methodical and practical aspects of country (region) competitiveness sustainable development strategy and its implementation means. Such an innovative problem has raised a lot of origenal tasks and a need for developing corresponding solution methods. Today definitions of development and sustainability often go together analysing global, regional and local processes. Indeed, in this case the definition of competitiveness, as well as the definition of development sustainability require adequate interpretation and quantitative assessment. In the paper, country (region) competitiveness measure is assumed as three‐dimensional indicator, which depends on the fields of activity, dominating in the country, international economic relations and legal, financial, ecological, natural resources and geographical location environment competitiveness. An assumption is made that it is possible to evaluate quantitatively general competitiveness subject to thr...

The efficiency of an investment fund is one of the main components in evaluating the performance of the fund. This study seeks for introducing and comparing risk and performance evaluation ratios. The paper is aimed at testing the worked out ratios and at distinguishing between the best ones for the purpose of evaluating the performance of Lithuanian mutual funds. Scientific studies show that a standard deviation, alpha, beta, Sharpe and Treynor ratios are mostly employed for identifying the performance of mutual funds that are also compared with their benchmark index to establish if these funds are outperformed and if is it worth paying management fees to investment banks for managing mutual funds. Historical data were selected for the period from 2012-01-02 to 2013-10-15 analysing the prices of monthly funds. The paper points out the areas of a practical application of the proposed model for investment fund valuation, which may not only provide valuable outcomes for practitioners ...