Mario Martínez is a data and engineering leader with 10 years’ experience who currently heads Data at Magnific, driving rapid, reliable insights across analytics and ML teams. He holds a PhD (cum laude) in Telecommunications where he applied optimization, stochastic modelling, game theory and reinforcement learning to spectrum trading and published in high-impact venues like IEEE Transactions on Mobile Computing. Mario blends research rigor with product and platform delivery—leading data platform and Snowflake migrations, building IaC tooling, and improving time-to-insight in retail and ad tech settings. He’s an active open-source contributor to PyCaret, notably enhancing time-series seasonality handling across ARIMA, TBATS and Prophet models. A valued mentor and former instructor of Data Science with Python, he pairs hands-on engineering with people-first leadership and a knack for prioritization in chaotic migrations. Based in Valencia, he’s also known for pragmatic trade-offs: shipping incremental, well-tested solutions that reduce waste and accelerate impact.
10 years of coding experience
7 years of employment as a software developer
Beca Erasmus: Proyecto Final de Carrera, Beca Erasmus: Proyecto Final de Carrera at Loughborough University
Product Management Executive Programme, Product Management Executive Programme at Instituto Tramontana
Doctor of Philosophy (Ph.D.) Information and Communication Technologies, Doctor of Philosophy (Ph.D.) Information and Communication Technologies at Universidad Politécnica de Cartagena
An open-source, low-code machine learning library in Python
Role in this project:
ML Engineer / Data Scientist
Contributions:10 reviews, 22 commits, 1 PR in 21 days
Contributions summary:Mario primarily focused on enhancing the time series analysis capabilities of the pycaret library. Their contributions involved modifying various time series models, including ARIMA, TBATS, and Prophet, to incorporate the `sp_to_use` parameter, which is used to determine the seasonal period. They also corrected code formatting, added default values for seasonal periods, and improved documentation. Overall, the user made changes to integrate and refine seasonality handling across different time series models within pycaret.
Contributions:1 push, 1 branch in 3 years 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.