Multiple Kernel Learning on the Limit Order Book


Tristan Fletcher, Zakria Hussain, John Shawe-Taylor ;
Proceedings of the First Workshop on Applications of Pattern Analysis, PMLR 11:167-174, 2010.


Simple features constructed from order book data for the EURUSD currency pair were used to construct a set of kernels. These kernels were used both individually and simultaneously through the Multiple Kernel Learning (MKL) methods of SimpleMKL and the more novel LPBoostMKL to train multiclass Support Vector Machines to predict the direction of future price movements. The kernel methods outperformed a trend following benchmark both in their predictive ability and when used in a simple trading rule. Furthermore, the kernel weightings selected by the MKL techniques highlight which features of the EURUSD order book are the most informative for predictive tasks.

Related Material