High frequency FOREX market transaction data handling
Masry, Shaimaa . 2010
The foreign exchange market generates millions of daily tick data, often referred to as high frequency data (HFD), as a result of market participants decisions. By analyzing these data, one could reveal many of the market properties. However, HFD may possibly contain observations that are not reliable in terms of actual market activity. We manipulate a real dataset storing the full transaction history of more than 40,000 traders on an account level for 2.25 years. Prior to exploring the data to discover basic mechanisms of the market dynamics, we perform a cleaning procedure to remove erroneous or misleading observations from the set that would affect the validity of any forthcoming results. Validating the adopted cleaning methodology, we can confirm a clean transaction dataset allowing for a better understanding of the financial market.
مدينة النشر
London, United Kingdom
موقع المؤتمر
London
اسم المؤتمر
4th CSDA International Conference on Computational and Financial Econometrics
This paper presents an autonomous effective trading system devoted to the support of decision-making processes in the financial market domain. Genetic programming (GP) has been used effectively as…