C
Christian Schittenkopf
Researcher at Austrian Research Institute for Artificial Intelligence
Publications - 31
Citations - 717
Christian Schittenkopf is an academic researcher from Austrian Research Institute for Artificial Intelligence. The author has contributed to research in topics: Volatility (finance) & Autoregressive conditional heteroskedasticity. The author has an hindex of 13, co-authored 31 publications receiving 689 citations. Previous affiliations of Christian Schittenkopf include Siemens & Technische Universität München.
Papers
More filters
Journal ArticleDOI
GARCH vs. stochastic volatility: Option pricing and risk management
TL;DR: In this article, the authors examined the out-of-sample performance of two common extensions of the Black-Scholes framework, namely a GARCH and a stochastic volatility option pricing model, calibrated to intraday FTSE 100 option prices.
Journal ArticleDOI
Two strategies to avoid overfitting in feedforward networks
TL;DR: A new network topology is presented to avoid overfitting in two-layered feedforward networks by using two additional linear layers and principal component analysis to reduce the dimension of both inputs and internal representations and to transmit the essential information.
Journal ArticleDOI
Financial volatility trading using recurrent neural networks
TL;DR: It is argued that any report containing RNN results on financial tasks should be accompanied by results achieved by simple finite-memory sources combined with simple techniques to fight nonstationarity in the data.
Journal ArticleDOI
Forecasting Time-dependent Conditional Densities: A Semi-non- parametric Neural Network Approach
TL;DR: In this paper, the authors propose to estimate conditional densities semi-non-parametrically in a neural network framework and demonstrate the importance of distributional assumptions in volatility prediction and show that the out!of!sample fore! casting performance of neural networks slightly dominates those of GARCH models.
Journal ArticleDOI
Risk-neutral density extraction from option prices: improved pricing with mixture density networks
TL;DR: A new semi-nonparametric approach to risk-neutral density extraction from option prices is presented, based on an extension of the concept of mixture density networks, which is shown to yield significantly better results in terms of out-of-sample pricing accuracy in comparison to the basic and an extended Black-Scholes model.