Manuel Morales, PhD

Thanks to funding from the Montreal Institute of Structured Finance and Derivatives (IFSID), I am currently setting up a new research project in collaboration with the National Bank of Canada and the Canada Research Chair in Risk Management at HEC Montreal. This compon...

In partnership with CWP Energy, we explore different machine learning algorithms in order to first identify reliable signals and factors that in turn can be incorporated into a forecasting model for day-ahead electricity prices in Canadian markets.

In this paper we introduce a new coherent cumulative risk measure on a subclass in
the space of càdlàg processes. This new coherent risk measure turns out to be tractable enough within a class of models where the aggregate claims is driven by a spectrally positive Lévy...

In partnership with National Bank of Canada, we look at "zero-intelligence" simulator models in order to reproduce high-frequency signatures and limit-order-book features of assets of interest. This project involves event-driven simulation model developing as well as t...

The field of risk theory has traditionally focused on ruin-related quantities. In particular, the so-called expected discounted penalty function (Gerber and Shiu. N Am Actuar J, 2(1):48–78, 1998) has been the object of a thorough study over the years. Although interest...

In partnership with a private broker, we explored various machine learning methods in order to produce a trend-detecting algorithm that would ultimate optimize trading orders. An algorithmic trading algorithm was implemented.  

In partnership with CIBC Asset Management, we explored the applications of Self-organizing maps in detecting macro-economical regime changes in financial data series.

Regime-switching models (RSM) have been recently used in the literature as alternatives to the Black-Scholes model. Several authors favor RSM as being more realistic since, by construction, they model those exogenous macroeconomic cycles against which asset prices evol...