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.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v11-fletcher10a, title = {Multiple Kernel Learning on the Limit Order Book}, author = {Fletcher, Tristan and Hussain, Zakria and Shawe-Taylor, John}, booktitle = {Proceedings of the First Workshop on Applications of Pattern Analysis}, pages = {167--174}, year = {2010}, editor = {Diethe, Tom and Cristianini, Nello and Shawe-Taylor, John}, volume = {11}, series = {Proceedings of Machine Learning Research}, address = {Cumberland Lodge, Windsor, UK}, month = {01--03 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v11/fletcher10a/fletcher10a.pdf}, url = {https://proceedings.mlr.press/v11/fletcher10a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Multiple Kernel Learning on the Limit Order Book %A Tristan Fletcher %A Zakria Hussain %A John Shawe-Taylor %B Proceedings of the First Workshop on Applications of Pattern Analysis %C Proceedings of Machine Learning Research %D 2010 %E Tom Diethe %E Nello Cristianini %E John Shawe-Taylor %F pmlr-v11-fletcher10a %I PMLR %P 167--174 %U https://proceedings.mlr.press/v11/fletcher10a.html %V 11 %X 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.
RIS
TY - CPAPER TI - Multiple Kernel Learning on the Limit Order Book AU - Tristan Fletcher AU - Zakria Hussain AU - John Shawe-Taylor BT - Proceedings of the First Workshop on Applications of Pattern Analysis DA - 2010/09/30 ED - Tom Diethe ED - Nello Cristianini ED - John Shawe-Taylor ID - pmlr-v11-fletcher10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 11 SP - 167 EP - 174 L1 - http://proceedings.mlr.press/v11/fletcher10a/fletcher10a.pdf UR - https://proceedings.mlr.press/v11/fletcher10a.html AB - 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. ER -
APA
Fletcher, T., Hussain, Z. & Shawe-Taylor, J.. (2010). Multiple Kernel Learning on the Limit Order Book. Proceedings of the First Workshop on Applications of Pattern Analysis, in Proceedings of Machine Learning Research 11:167-174 Available from https://proceedings.mlr.press/v11/fletcher10a.html.

Related Material