Machine Learning and Tactical Asset Allocation – Part I: Integrating the Machine Learning Signals

In Kürze

Artificial Intelligence is transforming and redefining the way firms operate and make decisions. It offers a huge potential for the financial industry, including the effective management of portfolios. A particularly interesting area is the use of AI for the tactical adjustment of portfolios to current market conditions.


  • So far, we have been focussing on traditional econometric approaches for modelling economically sound relationships. In contrast, machine learning (ML) employs algorithms to learn patterns directly from data. It can handle large datasets and complex relationships. As such, ML is a promising and flexible supplement to our existing models.
  • In a traditional insurance asset management company, the specialists’ expertise is the central pillar of the allocation decisions. We here develop a concept to complement the existing human expertise with ML signals to improve the results of our processes.
  • We generate ML signals that forecast the upcoming market regime simply defined as equities outperforming government bonds or vice versa. The signals are generated by an algorithm that systematically searches a large macroeconomic database for comparable situations in the past. These signals amend our existing tactical asset allocation process as an additional input layer. They are used to adjust the overall depth of the initially recommended active positioning, applying simple rule-based overlay strategies.
  • In a true out of sample check since 06/2022 a tactical asset allocation (TAA) exclusively based on the machine learning signals would have clearly outperformed its benchmark and even naïve allocation strategies. For the intended use case i.e., complementing our more comprehensive TAA approach, we find in a long-term simulation study that the added value generated by particular combinations of machine learning overlays can be expected to range from 20 to 30 bps per year.


Download the full publication below

Machine Learning and Tactical Asset Allocation – Part I: Integrating the Machine Learning Signals

© Generali Investments, alle Rechte vorbehalten. Diese Website wird von der Generali Investments Holding S.p.A. als Holdinggesellschaft der wichtigsten Vermögensverwaltungsgesellschaften der Generali Gruppe zur Verfügung gestellt, die direkt oder indirekt die Mehrheitsbeteiligung an den unten aufgeführten Gesellschaften hält (im Folgenden gemeinsam "Generali Investments"). Diese Website kann Informationen über die Tätigkeit der folgenden Gesellschaften enthalten: Generali Asset Management S.p.A. Società di gestione del risparmio, Infranity, Sycomore Asset Management, Aperture Investors LLC (einschließlich Aperture Investors UK Ltd), Plenisfer Investments S.p.A. Società di gestione del risparmio, Lumyna Investments Limited, Sosteneo S. p.A. Società di gestione del risparmio, Generali Real Estate S.p.A. Società di gestione del risparmio, Conning* und unter deren Tochtergesellschaften Global Evolution Asset Management A/S - einschließlich Global Evolution USA, LLC und Global Evolution Fund Management Singapore Pte. Ltd - Octagon Credit Investors, LLC, Pearlmark Real Estate, LLC sowie Generali Investments CEE. *Einschließlich Conning, Inc, Conning Asset Management Limited, Conning Asia Pacific Limited, Conning Investment Products, Inc, Goodwin Capital Advisers, Inc. (zusammen "Conning").