Practical investment with the long-short game

Najim Al-Baghdadi, David Lindsay, Yuri Kalnishkan, Sian Lindsay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we apply the aggregating algorithm, an on-line prediction with expert advice algorithm, to real-world foreign exchange trading data with the aim of finding investment strategies with optimal returns. We consider the Long-Short game first introduced in Vovk and Watkins (1998) and it’s implementation, including the derivation of expert predictions from model trading data. Furthermore, we propose modifications to improve the practical performance of the game with respect to well-known portfolio performance indicators.
Original languageEnglish
Title of host publicationConformal and Probabilistic Prediction and Applications
Subtitle of host publicationCOPA 2020
PublisherProceedings of Machine Learning Research
Pages209-228
Number of pages20
Volume128
Publication statusPublished - Sept 2020
EventThe 9th Symposium on Conformal and Probabilistic Prediction with Applications: COPA 2020 - Online
Duration: 9 Sept 202011 Sept 2020
https://cml.rhul.ac.uk/copa2020/

Publication series

NameProceedings of Machine Learning Research

Conference

ConferenceThe 9th Symposium on Conformal and Probabilistic Prediction with Applications: COPA 2020
Abbreviated titleCOPA 2020
Period9/09/2011/09/20
Internet address

Keywords

  • Prediction with Expert Advice
  • Online Learning
  • Aggregating Algorithm
  • Portfolio Optimisation
  • Long-Short Game
  • Foreign Exchange
  • Currency Trading

Cite this