BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:No-Arbitrage Factor Geometry: Identification in High-Dimensional I
 nstrumented Asset Pricing
DTSTART:20260616T121500
DTEND:20260616T131500
DTSTAMP:20261028T123837Z
UID:523e48e7d8ad658763979167a70143bfcc1d2d385f72c0c70b422879
CATEGORIES:Conferences - Seminars
DESCRIPTION:Mingyang Liu - PhD student\, Imperial College London\nInstrume
 nted asset pricing models use large sets of firm characteristics to identi
 fy latent sources of systematic risk. As the number of available character
 istics continues to grow\, a natural question is whether additional instru
 ments provide genuinely new information or instead repackage existing info
 rmation in higher-dimensional form. This thesis-based work studies that qu
 estion from a geometric perspective\, building on Instrumented Principal C
 omponent Analysis and the characteristic-based asset pricing literature.\n
 \nUsing a broad panel of equity characteristics\, I document that the effe
 ctive dimensionality of the characteristic space is substantially lower th
 an the raw instrument count suggests\, and that the resulting long-run geo
 metry is highly anisotropic. In such a space\, conventional Euclidean noti
 ons of orthogonality can be misleading\, allowing latent and observable fa
 ctor directions to overlap. Motivated by this observation\, I develop a no
 -arbitrage geometric extension of IPCA that incorporates empirical charact
 eristic geometry through a QZ-based metric and an economically disciplined
  identification structure. Preliminary evidence suggests that accounting f
 or this geometry is important for factor identification and is associated 
 with improved cross-sectional pricing relative to standard Euclidean IPCA 
 specifications.\n 
LOCATION:UNIL\, Extranef\, room 126
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR