02 September 2026
As machine learning becomes increasingly embedded in investment processes, quantitative finance professionals need more than familiarity with new technologies. Understanding how statistical models work, where they can fail and how they can be translated into robust financial applications is becoming an increasingly important part of the investment toolkit.
The ARPM Certification in Machine Learning for Quantitative Finance addresses this intersection through a one-year advanced professional learning programme designed for quantitative finance, investment and risk professionals. The next cohort is scheduled to start on 21 September 2026 - and this year, ARPM is offering an enhanced 35% discount to CFA Society Italy members.
Unlike a short intensive programme, the Certification is structured around two complementary tracks. The Machine Learning track comprises four courses - i.e., Mathematical Statistics for Finance, Mean-Covariance Learning, Probabilistic Machine Learning, and Time Series and Reinforcement Learning - while the Quantitative Finance track consists of Financial Engineering, Portfolio and Enterprise Risk Management, and Portfolio Construction and Trading. The tracks can be taken in either order and may also be attended individually, depending on participants’ backgrounds and objectives.
The emphasis is not simply on learning individual techniques, but on developing the analytical independence required to move from theoretical models to practical implementation. ARPM positions the Certification for professionals seeking advanced roles in financial engineering, quantitative risk management and quantitative investing, with particular attention to identifying and avoiding modelling pitfalls that can have material financial consequences.
The programme is delivered online and is designed to accommodate working professionals. Each track takes approximately five months, with courses following a defined sequence. The learning model combines live classes, recordings, homework and practical projects reviewed by instructors. Participants who need to refresh their foundations can also access optional, self-paced primers in mathematics, finance and Python, free of charge.
A distinctive component of the programme is the ARPM Lab, a continuously updated 4,000-page digital learning environment integrating mathematical theory with case studies, Python code, exercises, animations and an AI tutor. Participants who complete the full Certification qualify for lifetime access to the Lab.
Successful completion of the programme leads to the Certification in Machine Learning for Quantitative Finance, together with a Statement of Completion for each of its seven courses. Each course is also eligible for 40 GARP Continuing Professional Development credits, for a total of 280 credits across the Certification.
The faculty brings together academic and industry expertise and includes ARPM founder Attilio Meucci, Javier Peña of Carnegie Mellon University, Til Schuermann and Ugur Koyluoglu of Oliver Wyman, Tai-Ho Wang of Baruch College, as well as ARPM researchers and practitioners.
For professionals operating at the intersection of data, markets and investment decisions, the programme offers a structured route into some of the areas that are reshaping quantitative finance. Rather than treating machine learning as a standalone technological skill, the Certification integrates it with the financial engineering, portfolio construction and risk-management frameworks in which quantitative techniques ultimately need to operate.
Discover the ARPM Certification in Machine Learning for Quantitative Finance here.