Prediction with Expert Advice for Trading and Hedging on the Foreign Exchange Market

Najim Al-Baghdadi

Research output: ThesisDoctoral Thesis

66 Downloads (Pure)

Abstract

In this thesis, we explore the application of prediction with expert advice algorithms for investing in the Foreign Exchange (FX) market.

We introduce a data staging algorithm designed to reconstruct multiple time series databases into a partitioned and regularised database. The Data Aggregation Partition Reduction Algorithm, or DAPRA for short, was designed to solve the practical issue of effective and meaningful visualisation of irregularly sampled time series data.

We apply methods of prediction with expert advice to real-world foreign exchange trading data to find effective investment strategies. We build upon the framework of the long-short game, introduced by Vovk and Watkins (1998), and propose modifications aimed at improving the performance with respect to standard portfolio performance indicators.

We apply the Weak Aggregating Algorithm (WAA) to find optimal risk management strategies for financial Market Makers (MMs), using hedging strategies as experts. We combine their hedging decisions to reduce portfolio risk and maximise profitability. We develop a variation of the WAA using discounting and evaluate the results on commonly traded FX currency pairs.
Original languageEnglish
QualificationPh.D.
Awarding Institution
  • Royal Holloway, University of London
Supervisors/Advisors
  • Kalnishkan, Yuri, Supervisor
Award date1 Mar 2024
Publication statusUnpublished - 2 Feb 2024

Keywords

  • Prediction with Expert Advice
  • Machine learning
  • Hedging
  • Foreign Exchange
  • brokerage
  • Long-Short Game
  • Aggregating Algorithm
  • Wealth management
  • Artificial Intelligence
  • Weak Aggregating Algorithm

Cite this