Max Vilarasau Serra

About

Hey there! I’m Max, welcome to my personal site.

Here you’ll find links to my socials, a glimpse of my (very modest) contributions to scientific research, and my CV.

I currently work as an Associate at Bluecap, a Madrid-based strategy consulting boutique specialized in delivering innovative solutions for leading financial institutions. My role allows me to connect analytical perspectives with strategic insights, thus helping our clients tackle their complex business challenges.

I graduated from an M.Sc. in Machine Learning & AI with outstanding grades, but as unconventional as it may seem, my background is also in Classical Music (Piano), Management, Applied Statistics, and Finance—a mix that allows me to bring both scientific rigor and creative approaches to problem-solving.

When I’m not working, you’ll often find me doing Jiu-Jitsu or Grappling; although I also have a lot of fun fine-tuning algorithms, or exploring new intersections between technology, business, and creativity.

You can reach me directly through the contact details listed in my CV, or simply connect with me through my socials.

Socials

LinkedIn

https://linkedin.com/in/MaxVS

GitHub

https://github.com/MaxVilarasau

Research

Domain Randomization for Deep Reinforcement Learning Agents Trained for Financial Portfolio Management

This study investigates how Domain Randomization (DR) can make deep reinforcement learning agents more reliable in financial portfolio management. Normally, these agents learn from past market data and risk overfitting to specific situations, which weakens their performance when markets change. By deliberately adding random variations to market simulations—such as different levels of volatility, noise, and price behavior—the agents are forced to adapt to a wider range of conditions. Trained with the Deep Deterministic Policy Gradient (DDPG) algorithm and tested on Dow Jones data, the DR agents achieved higher Sharpe ratios than those trained conventionally. The results suggest that DR works as a kind of “regularizer,” helping AI trading systems avoid overfitting and remain more robust in unpredictable, real-world markets.

Open PDF Download

Resources on Escolà-Gascón et al.’s (2023) Remote Viewing Research per the Original CIA Experiments

This report shares data from a remote viewing experiment, a line of research originally explored by the CIA, where participants attempt to perceive information about distant or unseen targets. While the phenomenon is controversial, it has sparked ongoing debate in psychology and parapsychology. The study examined whether emotional intelligence (EI) relates to better performance in these tasks. Using structural equation modeling, the authors found a positive link between higher EI and more accurate remote viewing “hits.” To promote transparency, they explained details about how EI was measured, why their effect sizes had underestimated variability, and how the unusual statistical results should be interpreted with caution. Overall, the work contributes to clarifying the methods and discussions around anomalous cognition experiments.

Open PDF Download

CV

Corporate CV

Corporate-oriented CV focused on consulting, strategy, and client impact; please check this CV if you are a recruiter for Consulting or other Corporate roles.

Last updated on October 13th 2025

Open PDF Download

Tech CV

Tech-oriented CV emphasizing ML & AI, data, research, and open-source work; please check this CV if you are a recruiter for Tech or other Quantitative roles.

Last updated on October 7th 2025

Open PDF Download