Andrew and David hold two undergraduate degrees in mechanical engineering and mathematics, four masters degrees ranging from financial mathematics to computer science and are in the latter stages of their PhDs at University College London within the Computer Science department.
Andrew is currently developing advanced pattern recognition techniques using machine learning for prediction in noisy datasets. Recently he has been focusing on deep reinforcement learning algorithms.
Andrew has a strong research background working for numerous institutions in the front-office such as Brown Shipley, Morgan Stanley and Bank of England where he performed quantitative research with heavy use of machine learning, signal processing and advanced statistical analysis. He has also held a position as Research Scientist at the quantitative hedge fund matrix8J where he researched, designed and implemented intra-day algorithmic trading strategies.
More recently, he helped build Reinforcement Learning Execution Algorithms for ITG Brokerage and worked as a HFT quant at Virtu Financial.
David's research focus is directional forecasting and class imbalance problems, including applications of supervised and unsupervised learning models to cryptocurrency trading.
David's industry experience includes J.P. Morgan (Sales and Trading) and the Bank of England. He has also worked as a consultant for Schroders, helping to design distributed optimisation pipelines for systematic portfolio decision systems