Welcome to My Homepage!

Fools ignore complexity. Pragmatists suffer it. Some can avoid it. Geniuses remove it.

Alan J. Perlis


Photo credit: Amir Holakoo

I am the Senior Lecturer of Quantitative Finance at the School of Mathematics at the Monash University and a member of Monash Centre for Quantitative Finance. Before, I was a Post-Doctoral researcher at the Swiss Finance Institute at EPFL, EPFL and the European Center for Advanced Research in Economics and Statistics (ECARES), Free University of Brussels, Belgium. My CV. LinkedIn.

Working Papers (Latest First: date written):

  1. 1.Towards Explaining The ReLU Feed-Forward Network: Asymptotic Properties (joint with Vincentius Franstianto and Gregoire Loeper), 2019.                                 [*New Draft*] . [*Replication Python Code*]

  2. Abstract: A multi-layer, multi-node ReLU network is a powerful, efficient, and popular tool in statistical prediction tasks. However, in contrast to the great emphasis on its empirical applications, its statistical properties are rarely investigated which is mainly due to its severe nonlinearity and heavy parametrization. To help to close this gap by taking advantage of existing results on a sieve estimator, we first show that there exists such a sieve estimator for a ReLU feed-forward network. Next, we establish three asymptotic properties of the ReLU network: consistency, sieve-based convergence rate, and asymptotic normality. Finally, to validate the theoretical results, a Monte Carlo analysis is provided.

  1. 2.Correlated Time-Changed Lévy Processes (joint with Kihun Nam), 2020. [Submitted]

  2. Abstract: Carr and Wu (2004), henceforth CW, developed a framework that encompasses almost all of the continuous-time models proposed in the option pricing literature. Their main result hinges on the stopping time property of the time changes, but all of the models CW proposed for the time changes do not satisfy this assumption. In this paper, when the time changes are adapted, but not necessarily stopping times, we provide analogous results to CW. We show that our approach can be applied to all models in CW. 

  1. 3.Model Risk and Disappointment Aversion (joint with Loriano Mancini and Stoyan Stoyanov), 2019.

       [under major revision: new draft coming soon]

  1. Abstract: Extensions of expected utility theory are sensitive to the tail behavior of the portfolio return distribution and may not be approximated reliably through higher-order moment expansions. We develop a novel approach for model risk assessment based on a projection method and apply it to portfolio construction. We provide an extensive out-of-sample analysis to explore the economic gains of incorporating non-normality about financial asset returns into utility maximization with the generalized disappointment aversion (GDA) preferences. We find that the marginal utility gains of the optimal portfolio of a GDA investor are remarkably robust to misspecifications in the marginal distributions but are very sensitive to the structural assumption of stock returns implemented through a factor model.

  1. 4.Risk Premia and Lévy Jumps: Theory and Evidence (joint with Julien Hugonnier and Loriano Mancini), 2019.

  2. Abstract: To study jump and volatility risk premia in asset returns, we develop a novel class of time-changed Lévy models. The models are characterized by flexible Lévy measures, and allow consistent estimation under physical and risk neutral measures. To operationalize the models, we introduce a simple and rigorous filtering procedure to recover the unobservable time changes. An extensive time series and option pricing analysis of 16 time-changed Lévy models shows that infinite activity processes carry significant jump risk premia, and largely outperform many finite activity processes.

Papers in Progress:

  1. 5.Assessing Pricing Errors in Asset Pricing Models: A Novel Econometric Evaluation Framework (Joint with Stoyan Stoyanov)

        [*First draft coming soon*]   

  1. Objectives: We develop a novel econometric test, with the higher statistical power than extant tests, for the hypothesis that addresses the misspecification -- goodness-of-fit -- for a general class of asset pricing models.

  1. 6.Taming the Factor Zoo: A Neural Networks Approach (joint with Vincentius Franstianto)

        [*First draft coming soon*]

  1. Objectives: In this paper, we ask these questions: how to explain the output of neural networks respect to its input variables? In a non-linear and nonparametric time series formulation, what are the most significant/important risk factors? Is there a need for many factors to explain why the average rate of returns varies across securities? 

  1. 7.Smoothed Generalized Disappointment Aversion (Joint with Stoyan Stoyanov and Roméo Tédongap)

  2. Objectives: We extend the standard disappointment aversion model of Gul (Econometrica, 1991) and Routledge and Zin (JF, 2010) such that one is able to apply the traditional Taylor series expansion to an asset allocation problem. In addition, the model is more flexible to address some anomalies in the asset pricing such equity risk premium and Allais paradox.

  1. 8.Hedging Climate Change in Real Time

  2. Objectives: We introduce a dynamic hedging strategy for the climate change risk based on messages of large number of investors on the stock market. Thanks to the availability of the data, our hedging strategy can be implemented at the HF level.

Latest Publications:


  1. Fractional Calculus and Fractional Processes with Applications in Financial Economics (joint with Frank J. Fabozzi and Sergio Focardi), Elsevier (2017).


  1. Modeling Tail Risk with Tempered Stable Distributions: An Overview (joint with Gregoire Loeper),  Annals of Operations Research, (2019).

  2. Abstract: In this study, we investigate the performance of different parametric models with stable and tempered stable distributions for capturing the tail behaviour of log-returns (financial asset returns). First, we define and discuss the properties of stable and tempered stable random variables. We then show how to estimate their parameters and simulate them based on their characteristic functions. Finally, as an illustration, we conduct an empirical analysis to explore the performance of different models representing the distributions of log-returns for the S&P500 and DAX indexes.

  3. Quanto Option Pricing with Lévy Models (joint with Frank J. Fabozzi, Young S. Kim and Jiho Park), Computational Economics, (2018).

  4. Abstract: We develop a multivariate Lévy model and apply the bivariate model for the pricing of quanto options that captures three characteristics observed in real-world markets for stock prices and currencies: jumps, heavy tails and skewness. The model is developed by using a bottom-up approach from a subordinator. We do so by replacing the time of a Brownian motion with a Lévy process, exponential tilting subordinator. We refer to this model as a multivariate exponential tilting process. We then compare using a time series of daily log-returns and market prices of European-style quanto options the relative performance of the exponential tilting process to that of the Black-Scholes and the normal tempered stable process. We find that, due to more flexibility on capturing the information of tails and skewness, the proposed modeling process is superior to the other two processes for fitting market distribution and pricing quanto options.

  5. Quantile-based Inference for Univariate Tempered Stable Distributions, (joint with David Veredas and Frank J. Fabozzi) Computational Economics, (2017).

  6. Abstract: We introduce a simple, fast, and accurate way for the estimation of numerous distributions that belong to the class of tempered stable probability distributions. Estimation is based on the Method of Simulated Quantiles (Dominicy and Veredas, 2013) and it consists of matching empirical and theoretical functions of quantiles that are informative about the parameters of interest. In the Monte Carlo study we show that MSQ is significantly faster than Maximum Likelihood and the estimates are almost as precise as MLE. A Value at Risk study using 13 years of daily returns from 21 world-wide market indexes shows that MSQ estimates provide as good risk assessments as with MLE.

  7. Elliptical Tempered Stable Distribution, (joint with Y. S. Kim and Frank J. Fabozzi)  Quantitative Finance, (2016).

  8. Abstract: Elliptical distributions are useful for modeling multivariate data, multivariate normal and Student t distributions being two special classes. In this paper, we provide a definition for the elliptical tempered stable distribution based on its characteristic function, which involves a unique spectral measure. This definition provides a framework for creating a connection between the infinite divisible distribution (in particular the elliptical tempered stable distribution) with fractional calculus. In addition, a definition for the elliptical tempered stable copula is discussed. A simulation study shows the accuracy of this definition, in comparison to the normal copula, for measuring the dependency of data. An empirical study of stock market index returns for 20 countries shows the usefulness of the theoretical results.



Research Interests:

Theoretical and Empirical Asset pricing Financial Econometrics

Machine Learning

Contact Details:

Email: hasan.fallahgoul@monash.edu,


Phone: +61 (0) 3 990 59894


School of Mathematics, Level 4

9 Rainforest Walk

Monash University

3800, Victoria