Prekiaujant vertybiniais popieriais, svarbiausia yra priimti teisingą sprendimą: pirkti arba parduoti. Daugelis investuotojų prieš priimdami sprendimą atkreipia dėmesį į pasirinktos akcijos kainos kitimo grafiką ir vadovaujasi juo. Tačiau ne kiekvienas investuotojas galėtų tiksliai apibūdinti savo pasirinktą grafinį modelį. Problemos aktualumas - Prognozuoti rinkas yra pakankamai sudėtinga, pastebimas žymus akcijų kursų svyravimas. Ženklūs akcijų kursų pasikeitimai skaičiuojami ne per metus ar mėnesius, o dienomis ar net valandomis. Investitoriams, finansų analitikams finansinėse rinkose sunku dirbti. Spekuliavimas akcijomis aktyviose akcijų rinkose yra labai rizikingas, bet pelningas užsiėmimas. Pasiūlius sprendimo priėmimo metodą investavimo procesas techniniu požiūriu supaprastės ir nereikalaus didelių sąnaudų, bei gilių žinių, leis platesniam ratui žmonių įeiti į akcijų rinką. Problema – Sudėtingas akcijų rinkų prognozavimas, kadangi pastebimas žymus akcijų kursų svyravimas, todėl rizikinga spekuliuoti akcijomis aktyviose akcijų rinkose. Baigiamojo darbo objektas – sprendimo priėmimo metodas finansinių rinkų prognozėms atlikti, remiantis neuroniniais tinklais ir spiečiaus algoritmu. Baigiamojo darbo tikslas – Spiečiaus intelekto taikymo finansų rinkose analizė ir optimizavimas. / One of the central problems in financial markets is to make the profitable stocks trading decisions using historical stocks' market data. This paper presents the decision-making methodology which is based on the application of neural networks and swarm intelligence technologies and is used to generate one-step ahead investment decisions. In brief, the proposed methodology draws from the analysis of historical stock prices variations. The variations are passed to neural networks and the recommendations for the next day are calculated. The stocks with the highest recommendations are considered for further experimental investigations. The core idea of this algorithm is to select three best neural networks for the future investment decisions and to adapt the weights of other networks towards the weights of the best network. The experimental results presented in the paper show that the application of our proposed methodology lets to achieve better results than the average of the market. The theme of the Master’s degree paper is “Analysis and Optimization of Swarm Intelligent in Financial Markets”. The object of the Master’s degree paper is decision making method for financial markets, re neural network and swarm intelligence.

The need for solving nonlinear optimization problems is pervasive in many fields. Particle swarm optimization, advantageous with the simple underlying implementation logic, and simultaneous perturbation stochastic approximation, which is famous for its saving in the computational power with the gradient-free attribute, are two solutions that deserve attention. Many researchers have exploited their merits in widely challenging applications. However, there is a known fact that both of them suffer from a severe drawback, non- effectively converging to the global best solution, because of the local “traps” spreading on the searching space. In this article, we propose two approaches to remedy this issue by combined their advantages. In the first algorithm, the gradient information helps optimize half of the particles at the initialization stage and then further updates the global best position. If the global best position is located in one of the local optima, the searching surface’s additional gradient estimation can help it jump out. The second algorithm expands the implementation of the gradient information to all the particles in the swarm to obtain the optimized personal best position. Both have to obey the rule created for updating the particle(s); that is, the solution found after employing the gradient information to the particle(s) has to perform more optimally. In this work, the experiments include five cases. The three previous methods with a similar theoretical basis and the two basic algorithms take participants in all five. The experimental results prove that the proposed two algorithms effectively improved the basic algorithms and even outperformed the previously designed three algorithms in some scenarios.