The majority of studies in the field of AI guided financial trading focus on purely applying machine learning algorithms to continuous historical price and technical analysis data. However, due to non-stationary and high volatile nature of Forex market most algorithm fail when put into real practice. We developed novel event-driven features which indicate a change of trend in direction. We then build long deep learning models to predict a retracement point providing a perfect entry point to gain maximum profit. We use a simple recurrent neural network (RNN) as our baseline model and compared with shortterm memory (LSTM), bidirectional long short-term memory (BiLSTM) and gated recurrent unit (GRU). Our experiment results show that the proposed event-driven feature selection together with the proposed models can form a robust prediction system which supports accurate trading strategies with minimal risk. Our best model on 15-minutes interval data for the EUR/GBP currency achieved RME 0.006x 𝟏𝟏𝟏𝟏 −𝟑𝟑 , RMSE 2.407x𝟏𝟏𝟏𝟏 −𝟑𝟑 , MAE 1.708x𝟏𝟏𝟏𝟏 −𝟑𝟑 , MAPE 0.194% outperforming previous studies.

No abstract

No abstract

No abstract

We propose a new K-nearest neighbor (KNN) algorithm based on a nearest-neighbor self-contained criterion (NNscKNN) by utilizing the unlabeled data information. Our algorithm incorporates other discriminant information to train KNN classifier. This new KNN scheme is also applied in a community detection algorithm for mobile-aware service: First, as the edges of networks, the social relation between mobile nodes is quantified with social network theory; second, we would construct the mobile nodes optimal path tree and calculate the similarity index of adjacent nodes; finally, the community dispersion is defined to evaluate the clustering results and measure the quality of community structure. Promising experiments on benchmarks demonstrate the effectiveness of our approach for recognition and detection tasks.