Forex Trend Classification by Machine Learning

Foreign Currency Exchange market (Forex) is a highly volatile complex time series for which predicting the daily trend is a challenging problem. In this book, we investigate the prediction of the ' high ' exchange rate daily trend as classification problem (two classes), with uptrend and downtrend outcomes. Foreign Exchange (Forex) market trend was predicted using classification and machine learning techniques for the sake of gaining long-term profits. The trading strategy here is to take one action per day, where this action is either buy or sell based on the prediction we have. We view the prediction problem as a classification task, thus this work is not trying to predict the actual exchange rate value between two currencies, but rather, if that exchange rate is going to rise or fall. Forex daily exchange rate values can be seen as a time series data and all time series data forecasting and data mining techniques can be used to do the required classification task.

Autorentext

Areej A. Baasher is a Sudanese researcher studied in Egypt at Arab Academy for Science, Technology and Maritime Transport where she successfully completed two degrees: Bachelor in Computer Science 2007, Masters in Computer Science 2011. Her supervisor Prof. Mohamed W. Fakhr and she were authors of four papers related to this book's content.