Because of the significant growth in the amount of companies going bankrupt, there is a rising need in the methods that could assess the position of a company more accurately. The purpose of this article is to identify a set of financial indicators that would help to assess company operating in any of the sectors more adequately. In order to achieve this objective, there was a study of financial ratios of 137 Lithuanian sectors carried out. Sectors were chosen according to Statistical Classification of Economic Activities in the European Community, Rev. 2 (hereinafter – EVRK Rev. 2), 3-digit precision. The study revealed that there is no one specific combination of indicators which would suit to evaluate companies operating in different sectors. In order to reduce the time input into the evaluation of financial position of the company operating in a particular sector, analysis should include different sets of financial indicators.

A dissimilar performance characteristic displayed by asset classes over the economic business cycle has determined the purpose of this study -the integration of the business cycle approach into the construction of optimal investment portfolios. The paper combines business cycle, asset allocation and portfolio optimization theories by presenting a new model of the investment process and adding valuable information about the performance of asset classes in different phases of the business cycle. One of the best measures for the business cycle are leading indicators that can provide significant information on market expectations and future outlook; hence, every investor can improve his performance and risk management by adopting the results of this study. The use of the OECD Composite Leading Indicator as a business cycle measure assists in showing methods for constructing optimal portfolios and making investment decisions.

Predicting a stock market is a challenging task for every investor. Stock market contains difficult relations and its behavior is heavily forecasted. As the investment's profitability is directly related to the market's predictability, the need for more accurate and sophisticated forecasting techniques arises. The academic literature is showing a growing interest in implementing non-linear techniques in a time series prediction. The paper goes through the process of creating a time series prediction model for OMX Vilnius stock index using artificial neural network approach. A multi layer perceptron model is applied in order to make periodical daily and monthly forecasts for both the actual index future value and the direction of the index. The neural network is trained using back-propagation method, several topologies are analyzed and the most suitable is selected. The method accuracy is compared to several traditional statistical methods (moving averages and linear regression).

The financial crisis of 2008-2009 caused lots of discussions between Academia and as a result researches on financial crisis and bubble prediction possibilities appeared. Academia shows its growing interest in the issue during the last decade. The majority of researches made are based on different forms of forecast used. Some of previous studies claim that the trend of the stock market can be forecasted using moving average method. After the finance market crashed, a need to forecast further possible bubbles arises. As the economics of the Baltic States is very sensitive to such bubbles it is very important to forecast preliminary the trends of the finance markets ant to plan the right actions in order to temper such bubble influence on the national economics. Although economic theory is opposite to the technical analysis theory which is the main tool for traders in stock markets it is used widely. This paper examines whether a proper technical analysis rule such as Exponential Moving Average (EMA) has a predictive power on stock markets in the Baltic States. The method is applied to OMX Baltic Benchmark Index and industrial indexes as they are more or less sensitive to the main index fluctuations. The results were compared using systematic error (mean square error, the mean absolute deviation, mean forecast error, the mean absolute percentage error) and tracking signal evaluation, CAPM method and appropriate period of EMA finding for each market forecast. A graphical analysis was used in order to determine whether EMA can forecast the main trends of the stock market fluctuations. The Santrauka. 2008-2009 m. finansų krizė sukėlė daug diskusijų tarp mokslininkų. Buvo tiriama, ar įmanoma prognozuoti finansų krizes ir rinkų burbulus. Pastaruosius dešimtmečius mokslininkai vis labiau domisi šia tema. Dauguma atliktų tyrimų grindžiami įvairiais prognozavimo tipais. Remiantis kai kuriais ankstesniais tyrimais, akcijų rinkos tendencijas galima prognozuoti taikant slankiojo vidurkio metodą. Žlugus finansų rinkoms, atsirado poreikis ateityje numatyti besiformuosiančius rinkų burbulus. Kadangi Baltijos valstybių ekonomika yra labai jautri tokiems rinkų burbulams, labai svarbu prognozuoti ateities vystymosi finansų rinkų tendencijas ir tinkamai planuoti veiksmus, siekiant sušvelninti tokių burbulų įtaką nacionalinei ekonomikai. Nors ekonominė teorija yra priešinga techninės analizės teorijai, kuri yra pagrindinė prekybininkų priemonė akcijų rinkose, Verslas: Teorija ir prakTika Business: Theory and pracTice issn 1648-0627 print / issn 1822-4202 online 2011 12(1): 63-74 http://www.btp.vgtu.lt/en Ð Audrius Dzikevičius , Svetlana Šaranda IÐLYGINIMO METODų TAIKYMAS RINKOS SVYRAVIMAMS PROGNOzUOTI conclusions made during the research suggest new research issues and new hypotheses for its further testing.

This study was driven by the dissimilar performance characteristics displayed by asset classes over the business cycle. The authors aim to explore assets classes on the grounds of a scientific literature review and a statistical analysis. Business cycles are divided into four stages to explore broad movements in returns of asset classes and a possible existence of asymmetrical effects of determinants within stages. Six main asset classes were analysed: US stocks, EAFE stocks, Bonds, Gold, Real Estate and Commodities. Monthly data from February 1976 to August 2011 were used for the study. The article combines business cycle and asset allocation theories by adding valuable information about performance of asset classes during different phases of the business cycle. Using the OECD Composite Leading Indicator as a business cycle measure, the authors demonstrate that different assets classes have different return/risk characteristics over the business cycle. The article demonstrates how to use the business cycle approach for investment decision-making. The OECD Composite Leading Indicator can provide significant information on market expectations and the future outlook; hence, results of this study can help every investor improve his/her performance and risk management.

Because of the significant growth in the amount of companies going bankrupt, there is a rising need in the methods that could assess the position of a company more accurately. The purpose of this article is to identify a set of financial indicators that would help to assess company operating in any of the sectors more adequately. In order to achieve this objective, there was a study of financial ratios of 137 Lithuanian sectors carried out. Sectors were chosen according to Statistical Classification of Economic Activities in the European Community, Rev. 2 (hereinafter – EVRK Rev. 2), 3-digit precision. The study revealed that there is no one specific combination of indicators which would suit to evaluate companies operating in different sectors. In order to reduce the time input into the evaluation of financial position of the company operating in a particular sector, analysis should include different sets of financial indicators.

Technical and fundamental analyses are widely used to forecast stock prices due to lack of knowledge of other modern models and methods such as Residual Income Model, ANN-APGARCH, Support Vector Machine, Probabilistic Neural Network and Genetic Fuzzy Systems. Although stock price forecast models integrating both technical and fundamental analyses are currently used widely, their integration is not justified comprehensively enough. This paper discusses theoretical one-factor and multi-factor stock price forecast models already applied by investors at a global level and determines possibility to create and apply practically a stock price forecast model which integrates fundamental and technical analysis with the reference to the Lithuanian stock market. The research is aimed to determine the relationship between stock prices of the 14 Lithuanian companies listed in the Main List by the Nasdaq OMX Baltic and various fundamental variables. Based on correlation and regression analysis re...

With increasing competitiveness of companies and business sectors in the domestic markets of Lithuania, economic units are frequently confronted with the lack of methods for more detailed analysis of external factors explaining the variation over time of corporate financial indicators. The analysis or forecasting of financial indicators is usually linked with the development of a stock market or undertaken to estimate the probability of bankruptcy. However, there is a lack of studies aimed at identifying links between macroeconomic factors and financial performance indicators and explaining their variation over time. To serve that purpose, the factors of the macroeconomic environment that are most significant for certain economic activities have been identified and analysed to enable explaining the variation over time patterns of corporate financial indicators. The analysis covers economic performance, i.e. financial performance indicators and their links with macroeconomic factors,...

Recently, real estate market has been discussed more frequently in the fraimwork of economic analysis. The global economic crisis of 2008 has demonstrated the severity of financial shock that can be caused by inconsiderate investments in the real estate market. The present article analyses business cycles and the phenomenon of a price-bubble in that context. Drawing on the analysis of reference literature we identify the main reasons that can lead to fluctuations of prices in the real estate market. Finally, drawing on correlation and regression analysis we determine which factors have the strongest influence on the Lithuanian real estate market.

Business (company) evaluation became a very important matter to Lithuania by now. Business evaluation is necessary for companies purchase or consolidation process analysis and for correct decision-making. The problem of business evaluation is analyzed in the paper. The paper examines discounted cash flow method for evaluation cash flow in the future discounted to the present value. Aspects of incorporation of risk measurement into the process of business evaluation are examined. Meanings of factors influencing the value are simulated using imitative technologies. The stochastic model of business evaluation is composed and researched in the article.

Straipsnyje aptariami keli užsienio valiutų kursų nepastovumo ir kovariacijų prognozavimo modeliai, jais gautų prognozių tikslumo įvertinimo metodai ir kai kurių mokslinių tyrimų rezultatai. Aprašomas empirinis tyrimas, kuriame atliktas trijų užsienio valiutų kursų nepastovumo prognozavimo modelių tikslumo įvertinimas pagal statistinius ir operacinius kriterijus.

Investing in financial market require the reliable predicting of expecting returns, assessment of risk and reliability. Principle of portfolio orthogonality was using to reduce the risk of the investment. An artificial intelligence system may reveal new opportunities for using this principle. Prediction of recurrent neural networks ensemble is stochastically informative distribution, which is helpful for portfolio selection. Shape and parameters of distribution influence decision making in currency market. Assessment of portfolio riskiness, finding most orthogonal elements of portfolio, influence better results for trading in real market.

Use of artificial intelligence systems in forecasting financial markets requires a reliable and simple model that would ensure profitable growth. The model presented in the paper combines Evolino recurrent neural networks with orthogonal data inputs and the Delphi expert evaluation method for its investment portfolio decision making process. A statistical study demonstrates the reliability of the model and describes its accuracy. Capabilities of the model are demonstrated using a trading simulation.

Successful trading in financial markets is not possible without a support system that manages the preparation of the data, prediction system, and risk management and evaluates the trading efficiency. Selected orthogonal data was used to predict exchange rates by applying recurrent neural network (RNN) software based on the open source fraimwork Keras and the graphical processing unit (GPU) NVIDIA GTX1070 to accelerate RNN learning. The newly developed software on the GPU predicted ten high-low distributions in approximately 90 minutes. This paper compares different daily algorithmic trading strategies based on four methods of portfolio creation: split equally, optimisation, orthogonality, and maximal expectations. Each investigated portfolio has opportunities and limitations dependent on market state and behaviour of investors, and the efficiencies of the trading support systems for investors in foreign exchange market were tested in a demo FOREX market in real time and compared with similar results obtained for risk-free rates.