This paper aims to enhance the classical mean-variance portfolio selection by using machine learning techniques and accounting for systemic risk. The optimal portfolio is solved through a three-step supervised learning model. Firstly, the Smooth Pinball Neural Network is employed to predict...

We examine machine learning and factor-based portfolio optimization. We find that factors based on autoencoder neural networks exhibit a weaker relationship with commonly used characteristic-sorted portfolios than popular dimensionality reduction techniques. Machine learning methods also lead to...

We directly optimize portfolio weights as a function of firm characteristics via deep neural networks by generalizing the parametric portfolio policy framework. Our results show that network-based portfolio policies result in an increase of investor utility of between 30 and 100 percent over a...

We provide a methodology for credit risk analysis that can be embedded into a risk appetite framework. We analyze the information content in CDS spreads to estimate the systematic and idiosyncratic components of credit risk for CDS issuers in the industrial sector of Europe. Such decomposition...

Since 2009, stock markets have resided in a long bull market regime. Passive investment strategies have succeeded during this low-volatility growth period. From 2018 on, however, there was a transition into a more volatile market environment interspersed by corrections increasing in amplitude...

One of the most important factors to control for the achievements of investment portfolio returns is risk. If we only think that a 100% positive return is needed to recover a portfolio loss of 50%, we can understand why. With the advent of the exponential growth of technology usage in markets,...

The change subsequent to the sub-prime crisis pushed pressure on decreased financial products complexity, going from exotics to vanilla options but increase in pricing efficiency. We introduce in this paper a more efficient methodology for vanilla option pricing using a scenario based particle...

Despite a rich academic literature dedicated to mutual fund performance, the question of the portfolio manager added value remains subject to discussion. The debate between active and passive investing is expected to last while there is no consensus on the appropriate measure for evaluating a...

This paper addresses the open debate about the usefulness of high-frequency (HF) data in large-scale portfolio allocation. We consider the problem of constructing global minimum variance portfolios based on the constituents of the S&P 500 over a four-year period covering the 2008 financial...

This paper describes a methodology extension for decomposing non-linear portfolio risk by fund manager which we refer to as "Manager Component Value-at-Risk." The approach is well suited to funds holding any asset class or instrument type including derivatives. This decomposition approach is...