Hierarchical clustering-based asset allocation
T Raffinot - The Journal of Portfolio Management, 2017 - pm-research.com
This article proposes a hierarchical clustering-based asset allocation method, which uses
graph theory and machine learning techniques. Hierarchical clustering refers to the formation …
graph theory and machine learning techniques. Hierarchical clustering refers to the formation …
The hierarchical equal risk contribution portfolio
T Raffinot - Available at SSRN 3237540, 2018 - papers.ssrn.com
… Exploiting the same basic idea in a different way, Raffinot [2017a] proposes a hierarchical …
The ”Hierarchical 1/N” proposed in Raffinot [2017a] finds a diversified weighting by distributing …
The ”Hierarchical 1/N” proposed in Raffinot [2017a] finds a diversified weighting by distributing …
Investing through economic cycles with ensemble machine learning algorithms
T Raffinot, S Benoît - Available at SSRN 2785583, 2018 - papers.ssrn.com
Ensemble machine learning algorithms (random forest and boosting) are applied to quickly
and accurately detect economic turning points in the United States and in the Eurozone over …
and accurately detect economic turning points in the United States and in the Eurozone over …
Supervised portfolios
G Chevalier, G Coqueret, T Raffinot - Quantitative Finance, 2022 - Taylor & Francis
We propose an asset allocation strategy that engineers optimal weights before feeding them
to a supervised learning algorithm. In contrast to the traditional approaches, the machine is …
to a supervised learning algorithm. In contrast to the traditional approaches, the machine is …
Interactions in asset pricing
G Chevalier, G Coqueret, T Raffinot - Available at SSRN, 2023 - papers.ssrn.com
We propose a linearization of rule-based algorithms that reveals the most important interactions
between characteristics and macroeconomic variables when explaining future stock …
between characteristics and macroeconomic variables when explaining future stock …
Interest-rates-free monetary policy rule
T Raffinot - 2017 - papers.ssrn.com
Interest rates are unreliable indicators of appropriate monetary policy; low nominal rates do
not indicate easy money. This paper attempts to assess the stance of monetary policy without …
not indicate easy money. This paper attempts to assess the stance of monetary policy without …
A monthly indicator of GDP for Euro-Area based on business surveys
T Raffinot - Applied Economics Letters, 2007 - Taylor & Francis
Policy-makers and analysts are continually assessing the state of the economy. But, gross
domestic product (GDP) is only available on quarterly basis with a time span of 1–3 months, …
domestic product (GDP) is only available on quarterly basis with a time span of 1–3 months, …
Time-varying risk premiums and economic cycles
T Raffinot - 2017 - papers.ssrn.com
Asset returns are not correlated with the business cycle but are primarily caused by the
economic cycles. To validate this claim, economic cycles are first rigorously defined, namely the …
economic cycles. To validate this claim, economic cycles are first rigorously defined, namely the …
Can macroeconomists get rich nowcasting output gap turning points with a simple machine-learning algorithm?
T Raffinot - Paris December 2015 Finance Meeting EUROFIDAI …, 2017 - papers.ssrn.com
To nowcast output gap turning points, probabilistic indicators are created from a simple and
transparent machine-learning algorithm known as Learning Vector Quantization. The real-…
transparent machine-learning algorithm known as Learning Vector Quantization. The real-…
Asset allocation, economic cycles and machine learning
T Raffinot - 2017 - theses.hal.science
A well-worked theory of macro-based investment decision is introduced. The theoretical
influence of economic cycles on time-varying risk premiums is explained and exhibited. The …
influence of economic cycles on time-varying risk premiums is explained and exhibited. The …