BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132449Z
LOCATION:Jean-Jacques Rousseau
DTSTART;TZID=Europe/Stockholm:20210706T123000
DTEND;TZID=Europe/Stockholm:20210706T130000
UID:submissions.pasc-conference.org_PASC21_sess131_msa258@linklings.com
SUMMARY:Deep Structural Estimation: With an Application to Option Pricing
DESCRIPTION:Minisymposium\n\nDeep Structural Estimation: With an Applicati
 on to Option Pricing\n\nDidisheim, Chen, Scheidegger\n\nWe propose a novel
  structural estimation framework in which we train a surrogate of an econo
 mic model with deep neural networks. Our methodology alleviates the curse 
 of dimensionality and speeds up the evaluation and parameter estimation by
  orders of magnitudes, which significantly enhances one's ability to condu
 ct analyses that require frequent parameter re-estimation. As an empirical
  application, we compare two popular option pricing models (the Heston and
  the Bates model with double-exponential jumps) against a non-parametric r
 andom forest model. We document that: a) the Bates model produces better o
 ut-of-sample pricing on average, but both structural models fail to outper
 form random forest for large areas of the volatility surface; b) random fo
 rest is more competitive at short horizons (e.g., 1-day), for short-dated 
 options (with less than 7 days to maturity), and on days with poor liquidi
 ty; c) both structural models outperform random forest in out-of-sample de
 lta hedging; d) the Heston model's relative performance has deteriorated s
 ignificantly after the 2008 financial crisis.\n\nDomain: CS and Math, Emer
 ging Applications
END:VEVENT
END:VCALENDAR