BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:7ef43eb0bf61f1c25627cd5a698accae
DTSTAMP:20260421T195644Z
SUMMARY:Mikko Pakkanen: Learning to Remove the Drift
DESCRIPTION:When data-driven trading algorithms are trained\, statistical a
 rbitrage opportunities present in the training data may “skew” the beh
 aviour of the trading algorithm. For example\, if a utility-maximising hed
 ging algorithm is trained with price paths that possess an upward trend\, 
 the algorithm will over-hedge\, as it aims to capture alpha in addition to
  hedging. Such behaviour is undesirable in practice as it may violate the 
 mandate of the trading desk and also lead to poor performance if the trend
  has evaporated by the time the algorithm is deployed. In this talk I will
  present a deep learning-based approach to mitigate the problem. Concretel
 y\, the approach seeks to learn re-weighting of the training data\, akin t
 o constructing an equivalent martingale measure in theory. Joint work with
  Hans Bühler\, Phillip Murray and Ben Wood.
URL:https://www.imperial.ac.uk/events/162944/mikko-pakkanen-learning-to-rem
 ove-the-drift/
DTSTART;TZID=Europe/London:20230531T143000
DTEND;TZID=Europe/London:20230531T153000
LOCATION:Room 410\, Huxley Building\, South Kensington Campus\, Imperial Co
 llege London\, London\, SW7 2AZ\, United Kingdom
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
DTSTART:20230531T143000
TZNAME:BST
TZOFFSETTO:+0100
TZOFFSETFROM:+0100
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR