This study performs a comparative analysis and evaluates the impact of different Relative Strenght Index (RSI) and stop loss configurations on a trading algorithm based on candlesticks patterns. It is tested on both the Swedish OMXS30 market and the UK FTSE100 market. By tweaking the configurations, RSI and stop loss was found to have a substantial impact on the performance of the algorithm. On both OMXS30 and FTSE100 markets the difference between configurations was shown to be significant / Denna studie gör en jämförelse och analyserar olika Relative Strenght Index (RSI) och stop loss-konfigurationers påverkan på en tradingalgoritm som är baserad på candlestick patterns. Algoritmen är testad på svenska OMXS30 och brittiska FTSE100. Genom att testa olika konfigurationer blev slutsatsen att RSI och stop loss hade en stor påverkar på algoritmens resultat. På både OMXS30 och FTSE100 var skillnaden mellan konfigurationerna signifikant.

This diploma thesis deals with the testing of the success of individual candlestick patterns of technical analysis. In the first part the theoretical basis of technical analysis and candlestick patterns will be presented. The second part will define basic candlestick patterns and their program definition. Backtesting on historical data will verify the success of individual candlestick patterns on EURUSD currency pair. In the third part, a trading system will be built based on the results of the testing of the candlestick patterns. An optimal setting of the trading system will be proposed. The aim of the thesis is to test success rate of candlestick patterns and find out if the candlestick pattern trading system is able to generate profits.

This thesis is dedicated to the application of machine learning methods to algorithmic trading. We take inspiration from intraday traders and implement a system that predicts future price based on candlestick patterns and technical indicators. Using forex and US stocks tick data we create multiple aggregated bar representations. From these bars we construct original features based on candlestick pattern clustering by K-Means and long-term features derived from standard technical indicators. We then setup regression and classification tasks for Extreme Gradient Boosting models. From their predictions we extract buy and sell trading signals. We perform experiments with eight different configurations over multiple assets and trading strategies using walk-forward validation. The results report Sharpe ratios and mean profits of all the combinations. We discuss the results and recommend suitable configurations. In overall our strategies outperform randomly selected strategies. Furthermore, we provide and discuss multiple opportunities for further research.