This thesis deals with the Forex and trading on it. The aim of this work is to evaluate the possibility of trading primarily for retail investors, for which this financial market is becoming increasingly popular. In the first two chapters, Forex, its characteristic and information about trading are presented. In the next chapter, analysis of exchange rate development is described , both fundamental and technical. More attention is paid to technical analysis. The demonstration of application of technical analysis is presented. The last chapter deals with comparing the selected trading platforms in terms of availability, technical analysis and trading opportunities.

This diploma thesis is committed to examination of validity of Harmonic Patterns in Forex trading. Scott Carney described existing and introduced new Harmonic Patterns in 1999 in his book Harmonic Trader. These patterns use the Fibonacci principle to analyze price action and to provide both bullish and bearish trading signals. The goal of this thesis is to find out whether harmonic trading strategy on selected pairs is profitable in FX market, which patterns are the most profitable and what is the success rate for the signals they provide.

Reinforcement Learning has applications in various domains, but the typical assumption is of a stationary process. Hence, when this hypothesis does not hold, performance may be sub-optimal. Tackling non-stationarity is not a trivial task because it requires adaptation to changing environments and predictability in various conditions, as dynamics and rewards might change over time. Meta Reinforcement Learning has been used to handle the non-stationary evolution of the environment while knowing the potential source of noise in the system. However, our research presents a novel method to manage such complexity by learning a suitable latent representation that captures relevant patterns for decision-making, improving the policy optimization procedure. We present a two-step framework that combines the unsupervised training of Deep Variational Auto-encoders to extract latent variables and a state-of-the-art model-free and off-policy Batch Reinforcement Learning algorithm called Fitted Q-Iteration, without relying on any assumptions about the environment dynamics. This framework is named Latent-Variable Fitted Q-Iteration (LV-FQI). Furthermore, to validate the generalization and robustness capabilities for exploiting the structure of the temporal sequence of time-series data and extracting near-optimal policies, we evaluated the performance with empirical experiments on synthetic data generated from classical financial models. We also tested it on Foreign Exchange trading scenarios with various degrees of non-stationarity and low signal-to-noise ratios. The results showed performance improvements compared to existing algorithms, indicating great promise for addressing the long-standing challenges of Continual Reinforcement Learning. / Reinforcement Learning har tillämpningar inom olika områden, men den typiska antagningen är att det rör sig om en stationär process. När detta antagande inte stämmer kan prestationen bli suboptimal. Att hantera icke-stationaritet är ingen enkel uppgift eftersom det kräver anpassning till föränderliga miljöer och förutsägbarhet under olika förhållanden, då dynamiken och belöningarna kan förändras över tiden. Meta Reinforcement Learning har använts för att hantera den icke-stationära utvecklingen av miljön genom att känna till potentiella källor till brus i systemet. Vår forskning presenterar emellertid en ny metod för att hantera en sådan komplexitet genom att lära en lämplig latent representation som fångar relevanta mönster för beslutsfattande och förbättrar optimeringsprocessen för policyn. Vi presenterar en tvåstegsramverk som kombinerar osuperviserad träning av Deep Variational Auto-encoders för att extrahera latenta variabler och en state-of-the-art model-free och off-policy Batch Reinforcement Learning-algoritm, Fitted Q-Iteration, utan att förlita sig på några antaganden om miljöns dynamik. Detta ramverk kallas Latent-Variable Fitted Q-Iteration (LV-FQI). För att validera generaliserings- och robusthetsförmågan att utnyttja strukturen hos den tidsmässiga sekvensen av tidsseriedata och extrahera nära-optimala policys utvärderade vi prestandan med empiriska experiment på syntetiska data genererade från klassiska finansiella modeller. Vi testade också det på handelsscenario för Foreign Exchange med olika grader av icke-stationaritet och låg signal-till-brus-förhållande. Resultaten visade prestandaförbättringar jämfört med befintliga algoritmer och indikerar stor potential för att tackla de långvariga utmaningarna inom kontinuerlig Reinforcement Learning.

本研究主要是以「外匯報酬三因子模型」為基礎，故先檢視在本樣本期間內(1985/2至2016/10) ，以雙分類法將37國主流貨幣分為9個投組後，外匯超額報酬解釋力，是否會因加入動能策略因子形成之三因子模型，而較原本兩因子模型(市場因子、利差策略因子)來的強？最終測得三因子模型在判斷係數及殘差等適切度表現較佳。 接著利用逐步迴歸分析法(限制所有自變數均須於90%信心水準內顯著)嘗試尋找獲利成因，主要挑選出不同面向之11種經濟成因因子(股價指數波動、投機活動、流動性、貨幣波動、落後短期利率、落後股利率、落後期限利差、落後違約利差、)落後避險基金套利資本、工業生產量及通膨率因子)來檢測可否解釋三因子模型中獲取報酬之利差、動能策略因子，並利用Fama-MacBeth兩步驟橫斷面迴歸法評估模型市場定價能力。結果發現定價能力均顯著，而利差交易策略之成因為股價指數波動因子(△EVOL)，因其可能連動匯率波動而呈現負相關；動能交易策略成因則為股價指數波動因子(△EVOL)及落後期限利差因子(△LTS)，主要因動能交易主要來自於市場資訊反應不完全，前者成因因子提供更大的動量執行交易策略、後者則因投資人在不同景氣循環下而有不同的投資反應，如景氣擴張的過度自信與樂觀、景氣衰退下產生行為財務領域中的處置效果，使兩成因與動能策略因子呈現正相關。 / This paper is based on the model of three-factors foreign exchange returns. So we test whether three-factors FX model which adds the factor of momentum can have stronger ability to explain currency excess return than two-factors FX model in the sampling period of February 1985 to October 2016. And the 37 kinds of currency are sorted by double sort method and become 9 portfolios. Finally, no matter coefficient of determination or residual error, three-factors FX model performs well. Further, we use stepwise LS regression (independent variable should have statistical significance in 90% confidence interval) to find which factor we choose can cause carry and momentum strategy profit in three-factors FX model. Next, using Fama-MacBeth two-step regression to estimate the asset pricing ability. The results represent that all contribution factors which get from stepwise LS method are significant. Carry trade strategy and △EVOL are negative correlation, because volatility of stock index will influence volatility of FX. And there have the positive correlation between momentum trade strategy and two factors(△EVOL and △LTS). Just because the profit from momentum strategy comes from the incomplete reaction of market information and △EVOL give more motive force. Besides, there have different investment reactions in diverse business cycle. Investors are over confident and optimistic during the period of recession and have disposition effect during the period of boom.