Foreign exchange data crawling and analysis for knowledge discovery leading to informative decision making

作者:

Highlights:

摘要

Foreign exchange refers to the process of converting/changing money from one currency to another, e.g., from euro to US dollar. This kind of exchange is valuable and attractive because the value of various currencies may change over time, leading to gain or loss in terms of the overall value. Further, the foreign exchange market is growing rapidly and the development in technology has influenced all aspects of our daily life, including foreign currencies trading. Thus, there has been a major shift to electronic trading which has brought together the need for sophisticated techniques capable of monitoring the market in real time. To contribute to this domain, the research described in this paper covers the development of a framework which enables real time acquisition of data from a set of currency trading entities and fast data analysis. The framework also allows streaming and visualization of historical (previous) and current currency prices in close to real time. Finally, the framework benchmarks every monitored broker to decide whether he/she is trustworthy. The reported test results demonstrate the applicability and effectiveness of the developed framework. An additional value of the developed framework is attributed to its utilization by a domain expert who has guided the whole development process.

论文关键词:Foreign exchange,Data crawling,Knowledge discovery,Prediction,Clustering,Classification

论文评审过程:Received 27 May 2015, Revised 28 February 2016, Accepted 5 March 2016, Available online 30 March 2016, Version of Record 23 April 2016.

论文官网地址:https://doi.org/10.1016/j.knosys.2016.03.005