Narrow your search
Listing 1 - 4 of 4
Sort by

Dissertation
Quantitative analyses on portfolios simulations : how complex should the quality stocks definition be ?
Authors: --- --- ---
Year: 2017 Publisher: Liège Université de Liège (ULiège)

Loading...
Export citation

Choose an application

Bookmark

Abstract

This thesis aims at investigating the market anomaly quality as defined by Asness,
Frazzini and Pedersen (2017) in their “Quality Minus Junk” factor. The undertaken study
refines the quality stocks definition and its complexity. The concept of the quality anomaly has
been for years arduous to portray, as its meaning is highly subjective and differs from one
academician to another. Quality is occasionally not seen as a “pure anomaly” since it consists
of an aggregation of numerous factors and ratios. This memoir is willing to enlighten this
interpretation puzzle.
The basic concepts of market theories and portfolio management are introduced and
discussed, just like the evolution of pricing models. The most distinguished anomalies, other
than quality, are acquainted as a preface for the quality concept debate. Hence, the QMJ factor
(Asness, Frazzini, & Pedersen, 2017) is analyzed in its three components; profitability, growth
and safety. A replica of its ratios is built using SAS software with the goal to simulate
Fama/French styled long-short portfolios based on a CRSP/Compustat dataset. The computed
portfolios are regressed on QMJ and analyzed using SAS Miner software, along with
descriptive statistics, correlations, cumulated returns and Sharpe ratios.
The results show that the growth component may be entirely dismissed without
damaging the model. The safety factors greatly matter in the regressions and strengthen their
roles into quality. Return on equity, return on assets and cash flows are profitability ratios that
are significant in the definition as well. While the signals of gross profits are remarkably
persistent and drove the quality performance in all empirical analyses. Hence, the source of
quality is identified by these late six final ratios, cutting the complexity of the definition by
more than two.


Dissertation
Quality investing : design of a quality definition from a practitioners' perspective
Authors: --- --- ---
Year: 2018 Publisher: Liège Université de Liège (ULiège)

Loading...
Export citation

Choose an application

Bookmark

Abstract

This thesis highlights the complexity of Quality investing and the underlying large dispersion in Quality definitions. Indeed, there exists a fundamental difference in the perceptions of Quality between practitioners and academicians. Moreover, since academic studies appear to focus on Quality measures that have significant predictive power for stock returns, their Quality definitions tend to constantly outperform Quality definitions emanating from the industry.
In an attempt to first reconcile practitioners and then impulse a convergence towards academic definitions, a survey has been carried out on a sample of practitioners with the aim of designing a generally accepted Quality definition made out of Quality measures supported by academic studies. Globally this Quality definition encompasses four dimensions – i.e. Profitability (captured by ROIC), Quality Earnings (captured by low accruals), Growth (captured by 3-year growth in cash flow over assets and 3-year growth in gross margin) and Safety (captured by low leverage).The Quality Minus Junk factor constructed on this new definition experiences, in fact, poor return performance in comparison to purely academic measures over a time period spanning from 2005 to 2015. This suggests that even when confronted to what exists in the academic side, practitioners stick to their comprehensive and pragmatic vision of Quality and do not improve the predictive power of their definition.
In the light of these findings, one can expect the convergence towards a unique and effective Quality definition to be extremely complex so that funds which offer exposure to the quality factor should be cautious about their returns expectations and the way they market their strategy.


Dissertation
La pertinence des modèles de Machine Learning dans la prévsion de la rémunération des facteurs de risque de type Smart Beta
Authors: --- --- --- ---
Year: 2019 Publisher: Liège Université de Liège (ULiège)

Loading...
Export citation

Choose an application

Bookmark

Abstract

Le rapport suivant a été écrit dans le cadre de mon stage dans l'entreprise « Behave! ». Son principal objectif est d’identifier et de défendre le modèle de Machine Learning le plus pertinent dans la cadre de prévisions portant sur 7 styles d’investissement différents : « Growth », « Momentum », « Quality », « Size », « Value », « Volatility » et « Yield ».

Étant donné que ce mémoire est rédigé selon une orientation "rapport d’entreprise", une part importante de ce document est consacrée à la construction de modèles et à l’analyse de résultats.

De nombreuses recherches académiques ont néanmoins dû être effectuées et viendront, aussi souvent que possible, appuyer les conclusions établies au fur et à mesure des chapitres.

Ma tâche au sein de l’entreprise peut être divisée en trois étapes majeures, il en va de même pour la construction de ce rapport.
Premièrement, les facteurs de risque sont définis et systématiquement liés à leurs styles d’investissement. C’est l’occasion d’étudier les techniques utilisées par l’entreprise pour les calculer.

Dans un deuxième temps, ce sont les modèles de Machine Learning qui sont définis et appliqués à un exemple simple en utilisant les logiciels « RStudio » et « Microsoft Azure Cortana Intelligence ». Dans ce mémoire, l’approche se limite aux modèles suivants : « Hidden Markov », « Random Forest », « Support Vector Machine » et « Neural Network ».

Il s’agira enfin d’appliquer ces modèles aux styles d’investissement proposés par l’entreprise afin de pouvoir faire des comparaisons qui serviront ensuite de base à mes recommandations finales.


Book
Risk Analysis and Portfolio Modelling
Authors: ---
ISBN: 3039216252 3039216244 Year: 2019 Publisher: MDPI - Multidisciplinary Digital Publishing Institute

Loading...
Export citation

Choose an application

Bookmark

Abstract

Financial Risk Measurement is a challenging task, because both the types of risk and the techniques evolve very quickly. This book collects a number of novel contributions to the measurement of financial risk, which address either non-fully explored risks or risk takers, and does so in a wide variety of empirical contexts.

Listing 1 - 4 of 4
Sort by