This diploma thesis is focused on teoretical and practial aspects in the creation of trading strategie on FOREX market. The thesis include indicator and strategy that are build for tradning with EUR/USD currency. The designed strategy is developed in MetaTrader enviroment in MetaQuotes programming language. Indicator is optimalized on historical dates and choose settings for indicator to profit.

In den letzten Jahren gab es ein drastisches Wachstum in verfügbaren Finanzdaten. Finanzmärkte haben starke und oft nicht ganz vorhersagbare Änderungen ihrer Dynamik erlebt. Diese Tendenz hat dazu geführt, dass die Methoden der Risikomodellierung sowohl das Problem der hohen Dimensionalität als auch dynamische nicht Gaußsche Strukturen behandeln müssen. Das Ziel dieser Dissertation ist es, Methoden der Risikomodellierung vorzuschlagen, die gleichzeitig Reduzierung der Dimensionalität und dynamische Struktur in drei Anwendungen erlauben: 1) Asset Allocation und Hedging, 2) stochastische Modellierung von multivariaten Prozessen, 2) Messung der systemischen Risiken. Die vorgeschlagenen Methoden demonstrieren gute Ergebnisse im Vergleich mit den existierenden Methoden der Risikomodellierung und führen neue Verfahren zur Erkennung der extremen Risiken und Anomalien auf Finanzmärkten sowie zur deren Management. / Over the recent years, there have been a significant increase in financial data availability. On the other hand, financial markets have experienced sharp and often unforeseen changes in their dynamics. This tendency has caused the need for risk modeling approaches addressing both high dimensionality problem and accustoming for dynamic non Gaussian structure. The primary aim of this dissertation is to propose several risk modeling approaches which allow for simultaneous dimension reduction and dynamic structures in three setups: 1) asset allocation and hedging, 2) stochastic surface modeling and 3) systemic risk determination. Proposed models demonstrate good performance when compared to existing approaches for risk modeling and introduce new flexible ways to detect extreme risks and anomalies on financial markets as well as methods for their modeling and management.

因應電子化交易興起而進行的一系列人機互動研究顯示, 縱使人類會透過學習而改善其表現, 電腦化的交易程式獲利能力還是遠勝於真人交易者之表現。本研究遂以遺傳規劃演算法作為學習型交易者之代表, 與一系列電腦化交易策略相競爭, 以探討學習的功效及其限制。 本研究採用離散型雙方喊價機制, 摒除了計算能力所造成之決策時間差異所會帶來的影響, 亦排除掉人類情緒、預期、相關知識不足等可能因子, 在計算能力對等的情況下, 單純地來評估學習與理性設計策略的結果。並且首次嘗試將影響學習至鉅的智商因子帶入模型之中, 實驗結果顯示學習具有相當的能力, 即使是在對環境缺乏認識的情況下, 隨著時間的經過其表現最終可凌駕理性設計的策略之上, 然而學習所需的時間是學習型交易者的一大弱點。同時, 本研究也顯示對於以遺傳規劃建構的學習型交易者而言, 其虛擬智商的參數愈高, 學習的效果也愈佳。此研究因此可作為未來在代理人基經濟學模型中, 更深入地探討智商水準不同所造成之行為差異的基礎。 / The study of a series of human-agent interactions as well as computerized trading tournaments in double auction markets has exhibited a general superiority of computerized trading strategies over learning agents. The ineffectiveness of learning motivates the study of learning versus designed trading agents in this research. We therefore initiates a series of experiments to test the capability of learning GP agents and rationally-designed trading strategies. The results shows that with the cost of time, eventually learning agents can beat all other trading strategies. At the same time, the notion of intelligence is introduced into the model to investigate the influence of individual intelligence on learning ability. We utilize the population size of the GP trader as the proxy variable of IQ which is a measure of general intelligence. The results show that individuals with higher intelligence can perform better than those with lower intelligence, which manifests its importance discovered in Psychological research.

本研究中，我們計算OGA演化投資策略在五類時間數列模型上之表現，這五類模型分別是線性模型、雙線性模型、自迴歸條件異質變異數模型、門檻模型以及混沌模型。我們選擇獲勝機率、累積報酬率、夏普比例以及幸運係數做為評斷表現之準則，並分別推導出其漸近統計檢定。有別於一般計算智慧在財務工程上之應用，利用蒙地卡羅模擬法，研究中將對各表現準則提出嚴格之統計檢定結果。同時在實証研究中，我們考慮歐元兌美元及美元兌日圓的tick-by-tick匯率資料。故本研究主要的重點之一，乃是對於OGA演化投資策略，於這些模擬及實証資料上的有效性應用，作了深入且廣泛的探討。 / In this study, the performance of ordinary GA-based trading strategies are evaluated under five classes of time series model, namely, linear ARMA model, bilinear model, ARCH model, threshold model and chaotic model. The performance criteria employed are the winning probability, accumulated returns, Sharpe ratio and luck coefficient. We then provide the asymptotic statistical tests for these criteria. Unlike many existing applications of computational intelligence in financial engineering, for each performance criterion, we provide a rigorous statistical results based on Monte Carlo simulation. In the empirical study, two tick-by-tick foreign exchange rates are also considered, namely, EUR/USD and USD/JPY. As a result, this study provides us with a thorough understanding about the effectiveness of ordinary GA for evolving trading strategies under these artificial and natural time series data.