AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Gated Neural Networks for Option Pricing: Rationality by Design

Yongxin Yang, Yu Zheng, Timothy Hospedales

AAAI 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 37 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use gated multi-model (9 pricing nets with softmax gate) instead of single model (ablation)rational gated NN · S&P 500 options testMAPE (%): 34.99 -> 6.84Improved
Use Multi instead of MNN (manual option grouping)option pricing NN · S&P 500 options testMAPE (%): 18.22 -> 6.84Improved
Use Multi instead of PSSFoption pricing NN · S&P 500 options testMAPE (%): 26.25 -> 6.84Improved
Use Multi instead of Kou Jump econometric modeloption pricing · S&P 500 options testMAPE (%): 9.90 -> 6.84Improved
Use Multi instead of Black-Scholesoption pricing · S&P 500 options testMSE: 64.71 -> 12.11Improved
Use Single rational network instead of Black-Scholesoption pricing · S&P 500 options testMSE: 64.71 -> 580.47Hurt
Add virtual options for conditions C5 and C6 (ablation)Multi model · risk neutral density 15 May 2008density validityImproved
Add second derivative hint loss (Eq. 7) for condition C2 (ablation)Multi model · risk neutral density 15 May 2008density validityImproved
Increase number of training daysneural network pricing models · S&P 500 optionstest errorHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy