A5016612974- Financial Risk and Volatility Modeling
- Stochastic processes and financial applications
- Complex Systems and Time Series Analysis
- Financial Markets and Investment Strategies
- Risk and Portfolio Optimization
- Market Dynamics and Volatility
- Insurance and Financial Risk Management
- Probability and Risk Models
- Credit Risk and Financial Regulations
- Monetary Policy and Economic Impact
- Economic theories and models
- Statistical Distribution Estimation and Applications
- Stock Market Forecasting Methods
- Insurance, Mortality, Demography, Risk Management
- Stochastic processes and statistical mechanics
- Capital Investment and Risk Analysis
- Statistical Methods and Inference
- Banking stability, regulation, efficiency
- Advanced Statistical Methods and Models
- Housing Market and Economics
- Bayesian Methods and Mixture Models
- Forecasting Techniques and Applications
- Mathematical Dynamics and Fractals
- Advanced Data Processing Techniques
- Mathematical Biology Tumor Growth
Texas Tech University
2014-2025
University of California, Santa Barbara
2003-2017
Stony Brook University
2005-2014
Karlsruhe Institute of Technology
2004-2013
Karlsruhe University of Education
1999-2013
University of Duisburg-Essen
2013
Pranalytica (United States)
2008-2012
State University of New York
2005-2012
University of California System
1994-2008
Institute of Mathematical Statistics
2001-2003
In the 1960's Benoit Mandelbrot and Eugene Fama argued strongly in favor of stable Paretian distribution as a model for unconditional asset returns. Although substantial body subsequent empirical studies supported this position, plays minor role current work. While economics finance literature distributions are virtually exclusively associated with distributions, paper we adopt more fundamental view extend concept stability to variety probabilistic schemes. These schemes give rise...
Some new performance measures may be regarded as alternatives to the most popular criterion for portfolio optimization, Sharpe ratio. Analysis of some allocation problems here takes into consideration selection models based on different risk perceptions and sample paths final wealth process each problem. One ratio seems suitable optimization problems, but we need a thorough classification set that would ideal large classes financial problems.
Because of the theoretical challenges posed by Efficient Market Hypothesis with respect to technical analysis, effectiveness indicators in high-frequency trading remains inadequately explored, particularly at minute-level frequency, where effects microstructure market dominate. This study evaluates integration traditional Random Forest regression models using SPY data, analyzing 13 distinct model configurations. Our empirical results reveal a stark contrast between in-sample and...
Quantitative stability of optimal values and solution sets to stochastic programming problems is studied when the underlying probability distribution varies in some metric space measures. We give conditions that imply a program behaves stable with respect minimal information (m.i.) naturally associated data program. Canonical metrics bounding m.i. are derived for specific models, namely linear two-stage, mixed-integer two-stage chance-constrained models. The corresponding quantitative...
It is shown by means of several examples that probability metrics are a useful tool to study the asymptotic behaviour (stochastic) recursive algorithms. The basic idea this approach find ‘suitable' metric which yields contraction properties transformations describing limits algorithm. In order demonstrate wide range applicability method we investigate from various fields, some have already been analysed in literature.
Regime switching models, especially Markov Switching (MS) are regarded as a promising way to capture nonlinearities in time series. Combining the elements of MS models with full Autoregressive Moving Average–Generalized Conditional Heteroskedasticity (ARMA–GARCH) poses severe difficulties for computation parameter estimators. Existing methods can become completely unfeasible due path dependence such models. In this article, we demonstrate how overcome problem. We formulate MS–ARMA–GARCH...