For factor/ML investors

I guess u guys will like this paper if u were building nonlinear factor models lol
FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-sectional Stock Returns
https://www.aaai.org/AAAI22Papers/AAAI-12027.DuanY.pdf

BTW we usually use PCA or (V)AE to deal with the data depending on the linearity.
It's stupid to be a fundamentalist in the factor investing field cuz there is no "perfect" algo.
PCA: principle content analysis
VAE: Variational autoencoder

#機器學習
#因子投資
#暴徒投資