BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine Learning\, Asset Pricing and FinTech
DTSTART:20181116T103000
DTEND:20181116T120000
DTSTAMP:20260407T003014Z
UID:723caccd20a4df418fcc37073446f4f621988cd58b06ddf141f32b25
CATEGORIES:Conferences - Seminars
DESCRIPTION:Alberto ROSSI\, University of Maryland\nCombination of 2 paper
 s:\nPaper 1. Predicting Stock Returns with Machine Learning\nAbstract\nWe 
 employ a semi-parametric method known as Boosted Regression Trees (BRT) to
  forecast stock returns and volatility at the monthly frequency. BRT is a 
 statistical method that generates forecasts on the basis of large sets of 
 conditioning information without imposing strong parametric assumptions su
 ch as linearity or monotonicity. It applies soft weighting functions to th
 e predictor variables and performs a type of model averaging that increase
 s the stability of the forecasts and therefore protects it against overfit
 ting. Our results indicate that expanding the conditioning information set
  results in greater out-of-sample predictive accuracy compared to the stan
 dard models proposed in the literature and that the forecasts generate pro
 fitable portfolio allocations even when market frictions are considered. B
 y working directly with the mean-variance investor’s conditional Euler e
 quation we also characterize semi-parametrically the relation between the 
 various covariates constituting the conditioning information set and the i
 nvestor’s optimal portfolio weights. Our results suggest that the relati
 on between predictor variables and the optimal portfolio allocation to ris
 ky assets is highly non-linear. \n \nPaper 2. Who Benefits from Robo-adv
 ising? Evidence from Machine Learning\nAbstract\nWe study the effects of a
  large US robo-adviser on investor performance. Across all clients\, the r
 obo-adviser reduces investors holdings in money market mutual funds and in
 creases bond holdings. It reduces the holdings of individual stocks and US
  active mutual funds\, and moves investors towards low-cost indexed mutual
  funds. Finally\, it increases investors’ international diversification 
 and investors’ overall risk-adjusted performance. From sign-up\, it take
 s approximately six months for the robo-adviser to adjust investors’ por
 tfolios to the new allocations. We use a machine learning algorithm\, know
 n as Boosted Regression Trees (BRT)\, to explain the cross- sectional vari
 ation in the effects of PAS on investors’ portfolio allocation and perfo
 rmance. The investors that benefit the most from robo-advising are the cli
 ents with little investment experience\, as well as the ones that have hig
 h cash-holdings and high trading volume pre-adoption. Clients with little 
 mutual fund holdings and clients invested in high-fee active mutual funds 
 also display significant performance gains. \n 
LOCATION:UNIL\, Extranef\, room 126 https://planete.unil.ch/plan/?local=EX
 T-126
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR