Stocks vs. Bonds - A Data-Driven Approach to Asset Allocation Using Machine Learning

Aug 3, 2026

Upload by Aria

This thesis explores the application of supervised machine learning algorithms to asset allocation strategies to strengthen investment decision-making. Conducted in collaboration with Nordea’s Asset & Wealth Management department, the work evaluates whether a machine learning model can improve portfolio performance and reduce risk in a dynamic, uncertain financial-market environment. It reviews the state of the field, theoretical foundations, and limitations of traditional methods, then examines quantitative-investing pitfalls and their consequences.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages75

Reading Time3 h 9 min

AccessFree to download

Abstract

Keywords

Acknowledgements

Glossary

Stocks vs. Bonds A Data-Driven Approach to Asset Allocation Using Machine Learning Master’s thesis in computer science and engineering Emil Hölvold Nermin Skenderovic Department of Mathematical Sciences CHALMERS UNIVERSITY OF TECHNOLOGY UNIVERSITY OF GOTHENBURG Gothenburg, Sweden 2023 Master’s thesis 2023 Stocks vs . Bonds A Data-Driven Approach to Asset Allocation Using Machine Learning Emil Hölvold Nermin Skenderovic Department of Mathematical Sciences Chalmers University of Technology University of Gothenburg Gothenburg, Sweden 2023 Stocks vs. Bonds A Data-Driven Approach to Asset Allocation Using Machine Learning Emil Hölvold Nermin Skenderovic © Emil Hölvold, Nermin Skenderovic, 2023 . Supervisor: Sebastianus Cornelis Jacobus Bruinsma, Department of Data Science and AI Advisor: Karl Larsson, Nordea Bank Abp Advisor: Fredrik Lundström, Nordea Bank Abp Examiner: Stefan Lemurell, Department of Mathematical Sciences Master’s Thesis 2023 Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg SE-412 96 Gothenburg Telephone +46 31 772 1000 Cover: The cumulative return of the stock index MSCI World and the bond index Bloomberg Global Aggregate between 2001 and 2023 . Typeset in LATEX Gothenburg, Sweden 2023 Stocks vs. Bonds A Data-Driven Approach to Asset Allocation Using Machine Learning Emil Hölvold Nermin Skenderovic Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg Abstract This thesis explores the application of supervised machine learning algorithms to asset allocation strategies with the aim of enhancing investment decision-making processes. Collaborating with Nordea, one of the leading ﬁnancial institutions in the Nordics, the study was conducted at their Asset & Wealth Management department to investigate the potential of developing a machine learning model, with the goal of improving portfolio performance and reducing risk in the context of a dynamic and uncertain ﬁnancial market environment. The research begins by analysing the current status of the ﬁeld, examining the theoretical foundations of asset allocation, and identifying the shortcomings of traditional approaches. Additionally, the thesis raises a nuanced view of quantitative investing, with an in-depth exposition of the most common pitfalls and their consequences. Building on this foundation and previous work, regression and classiﬁcation algorithms are investigated together with premium ﬁnancial data as potential solutions to overcome these limitations. Speciﬁcally, the Random Forest and XGBoost models are used to forecast movements for the upcoming month in a global stock and bond index. The signals generated by the models are then incorporated into a rule-based allocation model. The ﬁndings of this research suggest that machine learning techniques can oﬀer valuable insights and improved performance in asset allocation. The results highlight the potential of these models to identify leading indicators and exploit market inefﬁciencies, resulting in improved risk-adjusted returns. The best-performing model achieved an alpha of 2.05% during the backtest between 2020 and 2023, accompanied by an increase in Sharpe ratio and a decrease in volatility. However, it is important to note that the eﬀectiveness of machine learning algorithms is heavily dependent on the quality and availability of data, as well as the appropriate selection and calibration of model parameters. Financial markets are dynamic and subject to various factors, so ongoing adjustments are necessary to adapt to changing market conditions and mitigate risks. Keywords: asset allocation, machine learning, quantitative investing, regression, classiﬁcation, algorithms, Random Forest, XGBoost, leading indicators, risk-adjusted returns. Acknowledgements We would like to express our sincere gratitude and appreciation to the following

FAQs

What is the main objective of the thesis?

To apply supervised machine learning to asset allocation with the goal of improving investment decision-making by enhancing performance and reducing risk in uncertain markets.

How is machine learning used in the proposed approach?

Regression and classification methods are investigated, and Random Forest and XGBoost are used to forecast movements for the upcoming month in global stock and bond indexes. Their signals feed into a rule-based allocation model.

What do the results indicate about machine learning for asset allocation?

The findings suggest machine learning can provide valuable insights and improved risk-adjusted returns by identifying leading indicators and exploiting market inefficiencies. The best model achieved an alpha of 2.05% in the 2020–2023 backtest, with higher Sharpe ratio and lower volatility.

Aug 3, 2026

Upload by Aria