---
title: "Estimating \"Realized\" Skewness using Convolutional Neural Network"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04598v1"
permalink: "https://feed.astralor.com/items/itm_bc22876a5aa23fbbd61c4c9c"
published: "2026-11-03T09:53:48.000Z"
score: 55
channel: "ai"
tags: ["Estimating","Realized","Skewness","Convolutional Neural Network","Convolutional Neural Networks","Multi Layer","Multi Layer Perceptrons"]
---

# Estimating "Realized" Skewness using Convolutional Neural Network

## At a glance

We propose a new estimator of low-frequency skewness (monthly) that exploits high-frequency data (5 min) through a direct functional mapping consisting of layers of Convolutional Neural Networks followed by Multi Layer …

## Key points

- We propose a new estimator of low-frequency skewness (monthly) that exploits high-frequency data (5 min) through a direct functional mapping consisting of layers of Convolutional Neural Networks followed by Multi Layer …
- Monte Carlo experiments involving stochastic volatility models, with and without jumps, show that the estimator reduces finite-sample bias relative to existing realized-skewness estimators and remains accurate under mod…
- Empirically, our estimator exhibits temporal stability and delivers cross-sectional performance in actual skewness-sorted portfolios.

## Full text

We propose a new estimator of low-frequency skewness (monthly) that exploits high-frequency data (5 min) through a direct functional mapping consisting of layers of Convolutional Neural Networks followed by Multi Layer Perceptrons. Monte Carlo experiments involving stochastic volatility models, with and without jumps, show that the estimator reduces finite-sample bias relative to existing realized-skewness estimators and remains accurate under model misspecification. Empirically, our estimator exhibits temporal stability and delivers cross-sectional performance in actual skewness-sorted portfolios. We characterize the finite-sample bias of conventional plug-in skewness estimators and establish risk consistency properties of the proposed NN estimator under standard regularity conditions.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_bc22876a5aa23fbbd61c4c9c