Machine Learning Engineer | PhD in Trustworthy AI

Location: Leuven, Belgium
Email: alexander.stevens@telenet.be
Phone: +32 471 55 07 73
LinkedIn: AlexanderPaulStevens
GitHub: AlexanderPaulStevens
Google Scholar: Profile

Summary

• Data scientist passionate about building trustworthy AI solutions that deliver measurable business impact.
• Over 5 years of experience translating cutting-edge research into applied AI solutions across finance and healthcare.
• Proven track record of delivering impactful projects within diverse, international settings.
• Eager to contribute to data-driven transformation for global clients through innovative AI solutions.

Work Experience

Machine Learning Engineer

ML6, Belgium | 31 March 2025 - Present

• Scoped and implemented end-to-end agentic AI workflows into real-world financial data pipelines.
• Automated financial calculations using generative AI, reducing manual processing time from months to minutes.

Researcher

KU Leuven, Belgium | 12 October 2020 - 28 February 2025

• Designed explainable ML methods increasing the trust and adoption of AI-based decision systems in business settings.
• Led 17 MSc data science projects (2-3 students, two award-winning teams), both academic and industry collaborations.
• Published 11 peer-reviewed papers including top-tier venues (IEEE TSC, EJOR, ESWA, ICPM).
• Presented at invited talks and lectures on ethical and explainable AI to academic and corporate audiences.

Visiting Researcher

Queensland University of Technology, Australia | 21 August 2023 - 22 December 2023

• Developed counterfactual models for ICU admission prediction, enabling clinicians to identify patient risk factors.
• Collaboration with Prof. Chun Ouyang and Prof. Catarina Moreira

Research Assistant

KU Leuven, Belgium | 1 June 2020 - 9 October 2020

• Developed a Python data science tutorial on descriptive analytics and advanced multivariate statistics.

Master Thesis Intern

Brainjar, Belgium | 23 September 2019 - 27 March 2020

• Publication: Explainability and Fairness in Machine Learning: Improve Fair End-to-end lending for Kiva
• Mitigated gender bias in Kiva’s lending recommendations, increasing overall fairness by 39.97% across six key metrics.

Data Analyst Intern

TVH, Belgium | 6 January 2020 - 27 March 2020

• Built customer segmentation models to identify the top 10% of high-value clients, enabling targeted sales strategies.

Education

Doctor of Philosophy (PhD)

KU Leuven | 12 October 2020 - 23 December 2024

• Grade: 78.33%
• PhD booklet: Trustworthy Artificial Intelligence for Business Process Analytics

Master of Business Engineering

KU Leuven | 3 September 2018 - 26 June 2020

• Grade: 74.46%
• Majored in Data Analytics and Business Applications
• Exchange semester at the Sophia Antipolis campus (Nice, France)

Bachelor of Business Engineering

KU Leuven | 26 September 2015 - 28 September 2018

• Grade: 64.03%
• Exchange course at IÉSEG School of Management (Lille, France)

Skills & Expertise

• Machine Learning: Predictive modelling, deep learning, XAI, fairness, robustness, NLP, process mining.
• Data Engineering: Deploying scalable solutions on major Cloud platforms (Python, SQL, Docker, Git, Azure/GCP).
• Consulting & Communication: Problem scoping, stakeholder alignment, translating AI insights to strategic value.
• Languages:
  • Dutch (Native): ⬤⬤⬤⬤⬤
  • English (Fluent/Professional): ⬤⬤⬤⬤
  • French (Proficient): ⬤⬤⬤

Projects & Certifications

Hobby Projects

• Horizon: Developed a self-hosted investment analytics platform integrating live market data.
• West-Flemish HPT: Built a large language model trained from scratch with self-scraped West-Flemish data.

Certifications

• Fundamentals of Accelerated Data Science (NVIDIA)
• 6 Introductory Data Science Courses (DataCamp)
• Post-graduate course: Trustworthy and Explainable Artificial Intelligence

Publications (Selection of 12)

Journal Publications

[1] He, Z., Stevens, A., Ouyang, C., De Smedt, J., Barros, A. J., Moreira, C., Crafting Imperceptible On-Manifold Adversarial Attacks for Tabular Data. Applied Soft Computing. 2025. (In review)

[2] Stevens, A., De Smedt, J., Peeperkorn, J., De Weerdt, J., Realistic Adversarial Examples for Business Processes using Variational Autoencoders. ACM Transactions on Knowledge Discovery from Data. 2025. (In review)

[3] Van Wallendael, L., Vanneste, L., Zhang, Y., Stevens, A., De Smedt, J., Mitigating downside risk: ESG Integration in Portfolio Construction with Stock Preselection Using Machine Learning and Mean-CVaR Optimization. Journal of International Financial Markets, Institutions & Money. 2025. (In review)

[4] Stevens, A., Ouyang, C., De Smedt, J., Moreira, C., Plausible and Feasible Counterfactuals for Predictive Process Monitoring. IEEE Transactions on Services Computing. 2025.

[5] Bertrand, Y., Stevens, A., Deforce, B., De Smedt, J., De Weerdt, J., Serral, E., Approaches for IoT-enhanced Predictive Process Monitoring. Process Science. 2024.

[6] Reusens, M., Stevens, A., Tonglet, J., De Smedt, J., Verbeke, W., vanden Broucke, S., Baesens, B., Evaluating Text Classification: A Benchmark Study. Expert Systems with Applications. 2024.

[7] Stevens, A., De Smedt, J., Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models. European Journal on Operational Research. 2023.

Conference Publications

[1] Stevens, A., Peeperkorn, J., De Smedt, J., De Weerdt, J., Manifold Learning for Adversarial Robustness in Predictive Process Monitoring. International Conference on Process Mining. 2023.

[2] Stevens, A., De Smedt, J., Peeperkorn, J., De Weerdt, J., Assessing the Robustness in Predictive Process Monitoring through Adversarial Attacks. International Conference on Process Mining. 2022.

[3] Peeperkorn, J., Vázquez, C.O., Stevens, A., De Smedt, J., vanden Broucke, S., De Weerdt, J., Outcome-Oriented Predictive Process Monitoring on Positive and Unlabelled Event Logs. Machine Learning for Process Mining. 2023.

[4] Stevens, A., De Smedt, J., Peeperkorn, J., Quantifying Explainability in Outcome-Oriented Predictive Process Monitoring. Machine Learning for Process Mining. 2023.

[5] Stevens, A., Deruyck, P., Van Veldhoven, Z., Vanthienen, J., Explainability and Fairness in Machine Learning: Improve Fair End-to-end Lending for Kiva. IEEE Symposium Series on Computational Intelligence (SSCI). 2020.

Academic Service

Supervision

• Successfully supervised 17 master thesis groups (2-3 students) across Master of Information Management, Master of Business and Information Systems Engineering, and Master of Business Engineering.
• Supervised 2 Best Thesis Award winners.
• Topics: Fairness, Bias Mitigation, Explainability, Robotic Process Automation, Topic Modeling.

Journal Reviewing

• Data & Knowledge Engineering (2024)
• Information Sciences (2023)
• IEEE Transactions on Services Computing (2023)
• ACM Transactions on Knowledge Discovery from Data (2023)
• Decision Support Systems (2023)

Conference Reviewing

• International Conference on Process Mining (2024, 2022, 2021)
• International Conference on Business Process Management (2023)
• Conference on Advanced Information Systems Engineering (2024, 2023)
• International Conference on Cooperative Information Systems (2023)

Invited Talks & Lectures

• ELA Triangle AI Workshop (2024)
• School of Information Systems, QUT (2023)
• Belgian Operational Research Society (2024, 2023)
• International Conference on Process Mining (2022)
• Machine Learning for Process Mining (2021)
• Guest lectures on Explainable and Ethical AI (2022-2025)