Biography

Davide Farinati

Based in Milan, Dr. Farinati is a researcher specialized in Data Science, with a PhD from Universidade NOVA de Lisboa – NOVA Information Management School (NOVA IMS). His main research interests lay in Evolutionary Computation and Artificial Intelligence and its applications.

He has extensive expertise in applying explainable AI models, both in academia (documented by his publications in top journals and conferences) and in the industry (given his various hands-on experiences). He extremely values the explainability of AI algorithms. He believes the key to success is combining the power of machine learning with the domain knowledge of experts.

His primary field of application is biomedical, with experience working on biological data and collaborating with hospitals and pharmaceutical companies.

Research Interests

Evolutionary Computation

Geometric Semantic Genetic Programming, dynamic populations, bloating reduction

Explainable AI

Interpretable models, combining ML power with domain expertise

Biomedical AI

Genomic data, neuro-muscular diseases, urological applications

Generative AI & RAG

Applications in pharmaceutical and healthcare sectors

Experience

Oct 2025 – Present
Ospedale San Raffaele – Urological Research Institute
Data Science Researcher, Milan
Working closely with clinicians and urologists to develop AI and ML-based methods to support urological applications and decision making. Different works also resulted in scientific publications.
Sep 2025 – Present
DareData Engineering
Freelance Data Scientist, Remote
Providing support in the development of different AI-based projects, focusing in the application of Generative AI and RAG across different industries, with a specific focus in the pharmaceutical and healthcare sector.
Sep 2022 – Aug 2025
NOVA IMS
PhD Candidate, Lisbon
Pursued doctoral research in Evolutionary Computation, developing new techniques to address bloating in Geometric Semantic Genetic Programming, which led to the SLIM algorithm.
PhD Research Scholarship
Sep 2023 – Aug 2024
IsRetail
Data Scientist & AI Consultant, Paço de Arcos
Supported the implementation of an intelligent warehouse management system. Implemented ML techniques producing accountable forecasts to reduce logistics costs, and supported deployment into warehouse software.
Dec 2021 – Apr 2022
Intesa SanPaolo
IT Junior Analyst Intern, Milan
Worked in the Specialistic Information Systems division. Gained experience with servers' planning, construction, maintenance, and the opening of streams.
Jan 2020 – Jun 2020
VINHOOD
Data Science Intern, Milan
Developed a tool for automatic classification of wines from their literal description. Worked with BERT, Hugging Face, and Generative AI, deepening knowledge in Artificial Neural Networks.

Education

Sep 2022 – Aug 2025
Ph.D. in Data Science
NOVA IMS, Lisbon
Thesis: Enhancing Geometric Semantic Genetic Programming: A Study on Dynamic Population and Deflate Geometric Mutation. Developed new techniques to solve bloating in GSGP, leading to the SLIM algorithm with unimodal fitness landscape and interpretable solutions.
Sep 2020 – Oct 2022
M.Sc. in Data Science and Advanced Analytics
NOVA IMS, Lisbon — 18/20
Thesis: A Study on Variations of Genetic Programming Applied to Time Series Forecasting: Machine Learning for Energy Consumption Forecasting.
Sep 2017 – Jul 2020
B.Sc. in Economics, Management and Computer Science
Università Commerciale Luigi Bocconi, Milan — 103/110
Thesis: Analysis of wines' description using machine learning and BERT, a revolutionary technology for automatic classification and comparison with human sommeliers.

Publications

Journal Articles

SLIM: The non-bloating genetic programming with geometric semantic mutations and meaningful semantic crossover
L. Vanneschi, S. Pereira, and D. Farinati
Genetic Programming and Evolvable Machines, vol. 27, no. 1, p. 9, Mar. 2026
doi: 10.1007/s10710-026-09535-y
A study on the dynamics and effectiveness of the deflate geometric semantic mutation
D. Farinati, G. Pietropolli, and L. Vanneschi
IEEE Transactions on Evolutionary Computation, 2025
doi: 10.1109/TEVC.2025.3611226
An Empirical Study of GM4OS for Imbalanced Binary Classification
D. Farinati and L. Vanneschi
SN Computer Science, vol. 6, no. 5, May 2025
doi: 10.1007/s42979-025-04048-4
Semantic-based recombination and mutation in cellular-inspired genetic programming
L. Rovito et al.
Genetic Programming and Evolvable Machines, vol. 26, no. 2, Nov. 2025
doi: 10.1007/s10710-025-09524-7
A survey on dynamic populations in bio-inspired algorithms
D. Farinati and L. Vanneschi
Genetic Programming and Evolvable Machines, vol. 25, no. 2, Jul. 2024
doi: 10.1007/s10710-024-09492-4
A study of dynamic populations in geometric semantic genetic programming
D. Farinati, I. Bakurov, and L. Vanneschi
Information Sciences, vol. 648, 2023
doi: 10.1016/j.ins.2023.119513
Simplifying fitness landscapes using dilation functions evolved with genetic programming
D. M. Papetti, A. Tangherloni, D. Farinati, P. Cazzaniga, and L. Vanneschi
IEEE Computational Intelligence Magazine, vol. 18, no. 1, 2023
doi: 10.1109/MCI.2022.3222096

Conference Proceedings

NEVO-GSPT: Population-based neural network evolution using inflate and deflate operators
D. Farinati, F. J. J. B. Santos, L. Vanneschi, and M. Castelli
EuroGP, Toulouse, France, Apr. 2026
arXiv: 2601.08657
A0710 The role of an AI-based model to predict long-term oncological outcomes in prostate cancer treated with radical prostatectomy
D. Farinati et al.
European Urology, vol. 89, Elsevier BV, Mar. 2026
doi: 10.1016/s0302-2838(26)00759-1
Developing a novel comorbidities index for predicting 10-year mortality in prostate cancer patients: A computational data-driven approach
D. Farinati et al.
Parallel Problem Solving from Nature – PPSN XIX, LNCS, Trento, Italy, Springer Nature, Aug. 2026 Forthcoming
A0751 Validation of the Cambridge, EAU, and STARCAP prognostic score in predicting biochemical recurrence in contemporary prostate cancer patients treated with radical prostatectomy
S. Scuderi et al.
European Urology, vol. 89, Elsevier BV, 2026, pp. S1–S2
Revisiting SLIM: Improved learning dynamics and model compactness in symbolic regression
G. Silva et al.
Genetic Programming (EuroGP 2026), LNCS vol. 16521, Cham: Springer, Apr. 2026, pp. 156–172
doi: 10.1007/978-3-032-23005-8_10
Exploring the impact of data scale on mutation step size in SLIM-GSGP
D. Farinati, G. Pietropolli, and L. Vanneschi
European Conference on Genetic Programming, EuroGP 2025, Trieste Forthcoming
An empirical study on the feature selection ability of SLIM-GSGP
D. Farinati and L. Vanneschi
Genetic and Evolutionary Computation Conference (GECCO '25 Companion), Malaga, 2025
doi: 10.1145/3712255.3726642
Introducing crossover in SLIM-GSGP
G. Pietropolli, D. Farinati, L. Manzoni, M. Castelli, and L. Vanneschi
European Conference on Genetic Programming, EuroGP 2025, Trieste Forthcoming
Slim_gsgp: A python library for non-bloating GSGP
L. Rosenfeld et al.
Genetic and Evolutionary Computation Conference (GECCO '25), Malaga, 2025
doi: 10.1145/3712256.3726398
Exploring the integration of cellular structures in genetic programming-based methods
L. Rovito et al.
European Conference on Genetic Programming, EuroGP 2025, Trieste Forthcoming
Exploring Non-bloating Geometric Semantic Genetic Programming
L. Vanneschi, D. Farinati, D. Rasteiro, L. Rosenfeld, G. Pietropolli, and S. Silva
Genetic Programming Theory and Practice XXI, Springer, Feb. 2025, pp. 237–258
doi: 10.1007/978-981-96-0077-9_12
GM4OS: An evolutionary oversampling approach for imbalanced binary classification tasks
D. Farinati and L. Vanneschi
Applications of Evolutionary Computation, Springer, 2024, pp. 68–82
doi: 10.1007/978-3-031-56852-7_5

Skills

Languages
🇮🇹 Italian (native) 🇬🇧 English (proficient, C1 IELTS) 🇵🇹 Portuguese (advanced) 🇪🇸 Spanish (basic)
Programming
Python R MatLab
Big Data & Analytics
Spark PySpark Databricks
Databases
MySQL MongoDB Neo4j Redis
Research & Soft Skills
Academic Research Paper Structuring Experimental Design Flexibility Teamwork Information Management

Miscellaneous

Reviewer

  • IEEE Trans. on Evolutionary Computation
  • Int. Journal of Data Science and Analytics
  • Scientific Reports
  • Parallel Problem Solving from Nature (PPSN)

Teaching

  • 2026Università Vita e Salute San Raffaele — Surgery in the Third Millennium: The Role of Robotics and Artificial Intelligence
  • 2022–2024Universidade NOVA de Lisboa — Computation III, Optimization Algorithms and Computational Methods for Optimization

Visiting Periods

  • 06/2026King's College London — Dept. of Surgical & Interventional Engineering (Supervisor: Prof. Alejandro Granados)
  • 04–06/2025Università degli Studi di Trieste — Dipartimento di Ingegneria e Architettura (Supervisor: Prof. Eric Medvet, ROAR-NET Scholarship)
  • 01–04/2025Università Milano Bicocca — Dipartimento di Informatica, Sistemi e Comunicazione (Supervisor: Prof. Daniela Besozzi, Erasmus Trainership Scholarship)

Thesis Mentoring

  • 2027Lucrezia Bonavia (Medicine, Università Vita e Salute San Raffaele)
  • 2026Vittoria Maestroni (Medicine, Università Vita e Salute San Raffaele)
  • 2026Daniele Sarnino (Medicine, Università Vita e Salute San Raffaele)
  • 2025Sofia Pereira (MSc, NOVA IMS)
  • 2025Beatriz Xavier (MSc, NOVA IMS)
  • 2024Lena De Waele (MSc, NOVA FCT)
  • 2023Ana Silva (MSc, NOVA FCT)
  • 2023Antonio Ladeira (MSc, NOVA IMS)

Schools

06/2023
EUTOPIA Summer School, Participant, Lisbon

Conferences

07/2025
GECCO 2025, Speaker, Malaga
An empirical study on the feature selection ability of SLIM-GSGP
04/2025
EvoStar 2025, Speaker, Trieste
Exploring the impact of data scale on mutation step size in SLIM-GSGP
04/2024
EvoStar 2024, Speaker, Aberystwyth
GM4OS: An evolutionary oversampling approach for imbalanced binary classification tasks
07/2023
GECCO 2023, Volunteer, Lisbon

Beyond Research

Solo hiked 130km (11000m D+) in the Italian Alps, from Gressoney to Courmayeur
Solo cycled 800km from Milan to Foggia
Passionate climber — up to 7a sport and 6c boulder
Played organized basketball until 25 (6th Italian division & Lisbon District University Champion)
Coached and refereed youth basketball