BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical classifiers of RFQ acceptance rates in FX electronic m
 arket making - A. Abutaliev\, R. Tank and T. Brooks\, Barclays Bank
DTSTART:20240306T140000Z
DTEND:20240306T150000Z
UID:TALK212344@talks.cam.ac.uk
CONTACT:Stephanie North
DESCRIPTION:In foreign exchange (FX) markets\, participants can execute tr
 ansactions in a variety of different ways.  One particularly prominent pro
 tocol is referred to as an ‘RFQ’ or Request for Quote.\n\nIn this scen
 ario\, a customer asks for a price in a currency pair and notional\, and a
  dealer responds with a quote\, which is either accepted (a trade happens)
  or declined (no trade happens) by a customer. The empirical frequency of 
 acceptance is referred to as ‘RFQ hit ratio’\, and is widely recognise
 d as a key performance indicator of any electronic FX business operation. 
 It is therefore essential to understand what factors may influence RFQ acc
 eptance\, to what extent and how they do so. \nElectronic markets generate
  large volumes of high frequency data which can be used to help tackle thi
 s problem\, meaning that statistical leaning techniques naturally present 
 themselves as promising tools. The nature of RFQ workflow in particular\, 
 with its binary outcome for a given customer request and dealer response\,
  make it amenable for analysis in a classification setting. This setting h
 as been extensively studied over many decades by scholars and practitioner
 s alike.\nWe look at theoretical and practical aspects of building a stati
 stical classifier of FX RFQ acceptance\, with a particular emphasis on out
 -of-sample predictive ability by feature type and fitting method.\n
LOCATION:MR4\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR