Objective

In this research project we have developed an algorithm capable of transforming pre-trained neural network models into tree structures.
Despite the great generalization power of neural networks and their success in solving complex problems in many industries, they render inadequate when the problem requires, in addition to a solution, an explanation of the decisions taken to reach such conclusion. This fact makes them unsuitable for use in sectors that require interpretability, either due to legal or commercial restrictions.
For this reason, during the project we have worked on an alternative interpretation of these models that allows us to extract features from the attributes without any loss of generalization of the original model during the process, contrary to other similar attempts. The tree representation allows, on the one hand, to represent the network output as a decision making sequence based on the values of the input variables and, on the other hand, to carry out an analysis of the local linear models that are generated by the network in order to apply statistical techniques to them.
This lays the groundwork for a deeper analysis of the network structure and the application of different techniques to exploit this alternative representation.

BACHELOR’S THESIS BY:

ERNESTO VIEIRA MANZANERA

Academic Experience

  • Master in Artificial Intelligence applied to financial markets (October 2022 – December 2023).
  • Double Degree in Computer Engineering and Business Administration, Universidad Carlos III de Madrid (september 2017 – september 2023).
  • ERASMUS+ at Politechnika Wroclawska, Poland (2019 – 2020).

Work Experience

  • AI Tech Specialist at MASORANGE (October 2023 – now).
  • Data Specialist – Grupo MásMóvil (June 2023 – October 2023).
  • Machine Learning Researcher – Universidad Carlos III de Madrid – Grupo MásMóvil (September 2022 — May 2023).

Awards and Certifications

  • Non-professional trader license in SIBE – Spanish stocks and markets
  • Options and Futures Trader License – Spanish stocks and markets.
  • Certificate of Proficiency in English (C2 in CEFR).
  • Excellence Scholarship of the Community of Madrid 2017/2018.


Technical skills

  • Programming languages: Python, Java, C, SQL and R.
  • Development libraries: Pandas, Numpy, Tensorflow, Sci-kit Learn.
  • Cloud Platforms: Google Cloud, Amazon Web Services, Docker, Kubernetes, Terraform and Git.

LinkedIn