Estimating "Realized" Skewness using Convolutional Neural Network

arXiv:2611.04598 · math.ST, cs.LG, stat.TH · Submitted 2026-11-03 · Read on arXiv

math.ST, cs.LG, stat.TH

Submitted: 2026-11-03

Updated: 2026-11-03

Comments: This paper first proves that bias exist given a fixed-horizon of high-frequency data to estimate the low-frequency skewness by using the plug-in method. Then it provides an innovation machine learning method to approximate the optimal estimator by fixing a temporal aggregation architecture for neural network before learning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers