Pau Labarta Bajo, Quantitative Finance Developer in Belgrade, Serbia
Pau Labarta Bajo

Quantitative Finance Developer in Belgrade, Serbia

Member since January 23, 2019
Pau has over seven years of experience in quantitative finance and mobile gaming. He combines a deep understanding of statistics and machine learning with excellent Python skills. He enjoys extracting information from big datasets, combining classical statistical methods and machine learning techniques. He has built software for diverse problems like asset pricing, customer lifetime value prediction or automatic art generation for mobile games.
Pau is now available for hire

Portfolio

Experience

  • Quantitative Finance, 7 years
  • Python, 5 years
  • Machine Learning, 5 years
  • Deep Learning, 3 years
  • Natural Language Processing (NLP), 3 years
  • Computer Vision, 2 years
  • PySpark, 1 year
  • Amazon Web Services (AWS), 1 year

Location

Belgrade, Serbia

Availability

Part-time

Preferred Environment

Mac, PyCharm, Jupyter, Hadoop, Impala

The most amazing...

...model I've built is a generative neural network that creates realistic profile pictures for football players in a mobile game.

Employment

  • Data Scientist and Machine Learning Engineer

    2019 - 2019
    Toptal client
    • Developed statistical and machine learning models to understand the market valuation of financial institutions.
    • Created a reproducible pipeline for data science, from data transformation to hyper-parameter model tuning.
    • Special emphasis was placed on model interpretability.
    Technologies: Python, Jupyter, Scikit-learn
  • Data Scientist and Machine Learning Engineer

    2016 - 2019
    Nordeus
    • Created a neural network that is able to generate football player faces and that is used in one of the company‚Äôs games.
    • Improved the algorithms used to matchmake players in the game.
    • Worked with a player support team to automate the process of tagging player complaints using NLP techniques.
    • Developed a model used to predict the lifetime value of the users.
    • Implemented simulations of the game economy in order to balance it and ensure a good player experience and good monetization.
    Technologies: Python, Hadoop, Impala, Tableau
  • Quantitative Risk Analyst

    2012 - 2016
    Erste Group Bank
    • Implemented and validated in Matlab and Python all models used by Erste Group Bank to price and hedge interest rate derivatives.
    • Wrote exhaustive documentation for each validated model in order to present it to the European Central Bank.
    • Proposed and implemented improvements to the methodology used to estimate the credit market risk of the banking and trading books.
    • Backtested the performance of different Value At Risk models in order to propose improvements to the methodology used by the bank.
    • Mentored junior quantitative risk analysts.
    Technologies: Python, Matlab, Calypso

Experience

  • Realistic Human Face Generator for Mobile App Golden Boot 2019 (Development)
    https://play.google.com/store/apps/details?id=com.nordeus.goldenboot&hl=en

    The problem I wanted to solve was to fully automate the process of generating profile images of football players for several of the company's games. The system is used in the mobile game Golden Boot 2019, available in both iOS and Android, and with over 1 million installs since its release.

    I built a pipeline of three models, each applied sequentially. First, a cutting-edge GAN network, retrained to my own dataset, that generates realistically looking football player faces. Second, a logistic classifier built from the last layer of a VGG network, to classify the output of the GAN into "good" faces and "bad" faces ensuring that only images of sufficient quality are displayed to the user. Third, another logistic regression on top of the last layer of a VGG net to classify the face according to its ethnicity. This last step was necessary in order to have control over the correlation between football player nationality and his physical appearance.

  • Adversarial Machine Learning: How to Attack and Defend ML Models (Publication)
    The increasing accuracy of machine learning systems has resulted in a flood of applications using them. As machine learning models matured and improved, so did ways of attacking them. In this article, Toptal Python Developer Pau Labarta Bajo examines the world of adversarial machine learning, explains how ML models can be attacked, and what you can do to safeguard them against attack.

Skills

  • Languages

    Python, SQL
  • Frameworks

    Flask
  • Libraries/APIs

    Scikit-learn, Keras, PySpark, TensorFlow, LSTM, OpenCV
  • Tools

    Tableau
  • Paradigms

    Data Science
  • Other

    Machine Learning, Natural Language Processing (NLP), Statistics, Statistical Modeling, Computer Vision, Quantitative Finance, Time Series Analysis, Deep Learning, Recommendation Systems, Genomics
  • Platforms

    Google Cloud Platform (GCP), Amazon Web Services (AWS)

Education

  • Master's degree in Quantitative Economics
    2011 - 2012
    Ca'Foscari University Venice - Venice, Italy
  • Master's degree in Quantitative Economics
    2010 - 2011
    University of Bielefeld - Bielefeld, Germany
  • Master's degree in Mathematics
    2005 - 2010
    Polytechnic University of Catalonia - Barcelona, Spain

To view more profiles

Join Toptal
I really like this profile
Share it with others