Interpretable Machine Learning for Diversified Portfolio Construction

Jaeger, Markus; Krügel, Stephan; Marinelli, Dimitri; Papenbrock, Jochen; Schwendner, Peter

doi:10.3905/jfds.2021.1.066

Cited by 22 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…663,664 On the other hand, the automation of small stock transactions avoiding cognitive biases, or the creation of optimised portfolios given an investor's profile, count as ML-based daily-life operations. [665][666][667] The common pattern in both fields lies behind the assignation and optimisation of the variables, typically numerous and with intricate data structures. For EM, this expertise might help in experiment planning and decision-making refinement in autonomous EM, through a set of predefined goals and sample features constituting the variables space.…”

Section: Other Fields Of Researchmentioning

confidence: 99%

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

2022

View full text Add to dashboard Cite

show abstract

Section: Other Fields Of Researchmentioning

confidence: 99%

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

2022

View full text Add to dashboard Cite

show abstract

“…An example for using interpretable machine learning techniques is a use case developed by Munich Re Markets, published in Jaeger et al ( 2021 ). It is a robust, fast, and interpretable machine learning approach to diversified portfolio construction.…”

Section: Addressing Trustworthy Ai With Technologymentioning

confidence: 99%

Financial Risk Management and Explainable, Trustworthy, Responsible AI

Fritz-Morgenthal¹,

Hein²,

Papenbrock³

2022

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

This perspective paper is based on several sessions by the members of the Round Table AI at FIRM1, with input from a number of external and international speakers. Its particular focus lies on the management of the model risk of productive models in banks and other financial institutions. The models in view range from simple rules-based approaches to Artificial Intelligence (AI) or Machine learning (ML) models with a high level of sophistication. The typical applications of those models are related to predictions and decision making around the value chain of credit risk (including accounting side under IFRS9 or related national GAAP approaches), insurance risk or other financial risk types. We expect more models of higher complexity in the space of anti-money laundering, fraud detection and transaction monitoring as well as a rise of AI/ML models as alternatives to current methods in solving some of the more intricate stochastic differential equations needed for the pricing and/or valuation of derivatives. The same type of model is also successful in areas unrelated to risk management, such as sales optimization, customer lifetime value considerations, robo-advisory, and other fields of applications. The paper refers to recent related publications from central banks, financial supervisors and regulators as well as other relevant sources and working groups. It aims to give practical advice for establishing a risk-based governance and testing framework for the mentioned model types and discusses the use of recent technologies, approaches, and platforms to support the establishment of responsible, trustworthy, explainable, auditable, and manageable AI/ML in production. In view of the recent EU publication on AI, also referred to as the EU Artificial Intelligence Act (AIA), we also see a certain added value for this paper as an instigator of further thinking outside of the financial services sector, in particular where “High Risk” models according to the mentioned EU consultation are concerned.

show abstract

“…Emphasizing on portfolio risk management, some new portfolio construction frameworks rely on clustering techniques. Providing less risky portfolios out of sample compared to traditional risk parity methods, the hierarchical risk parity approach (de Prado, 2016 ) also presents a better risk-adjusted performance than the equal risk contribution strategy (Jaeger et al, 2021 ). More recently, Ferretti ( 2022 ) introduces the naive network modularity-based allocation showing a generally good performance.…”

Section: Literature Reviewmentioning

confidence: 99%

On ESG Portfolio Construction: A Multi-Objective Optimization Approach

Xidonas

Essner

2022

Comput Econ

View full text Add to dashboard Cite

Ahead of the new asset management era that calls for sustainable investments, the limitations of the traditional bi-objective mean–variance framework need to be resolved, to accommodate responsible investment objectives. In this paper, we propose a multi-objective minimax-based portfolio optimization model, attempting to simultaneously maximize the risk performance of the three typical ESG investment objectives. Also, apart from the systematic risk, the underlying formulation incorporates the controversy dimension, associated with each company participating in the optimal ESG portfolio. The validity of the proposed model is assessed through an extensive empirical testing on the EURO STOXX 50, the DAX, the CAC 40 and the DJIA, for a 5-year period. The results are considered as highly satisfactory, since the optimal ESG portfolios produced by the model provide consistently higher risk-adjusted returns, in comparison to their respective market benchmarks.

show abstract

Interpretable Machine Learning for Diversified Portfolio Construction

Cited by 22 publications

References 41 publications

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

Financial Risk Management and Explainable, Trustworthy, Responsible AI

On ESG Portfolio Construction: A Multi-Objective Optimization Approach

Contact Info

Product

Resources

About