Federico Albanese, Developer in Buenos Aires, Argentina
Federico is available for hire
Hire Federico

Federico Albanese

Verified Expert  in Engineering

Predictive Modeling Developer

Buenos Aires, Argentina

Toptal member since January 9, 2019

Bio

Federico is a developer and data scientist who has worked at Facebook, where he made machine learning model predictions. He is a Python expert and a university lecturer. His Ph.D. research pertains to machine learning. He can continuously learn and implement state-of-the-art algorithms during this process and become a better data scientist each day.

Portfolio

University of Buenos Aires
XGBoost, Keras, TensorFlow, Scikit-learn, MATLAB, R, Python
Facebook
Python, Machine Learning, SQL, C++, Unsupervised Learning, Statistics...
Facebook
Python, Machine Learning, Bayesian Statistics, SQL, Data Visualization, Git...

Experience

  • Python 3 - 5 years
  • Predictive Modeling - 5 years
  • Data Visualization - 5 years

Availability

Part-time

Preferred Environment

Git, Spyder, Jupyter, Windows, Linux

The most amazing...

...prediction model I've coded outperformed the state-of-the-art models in that area by 15%. This model was also fast and easy to interpret.

Work Experience

Research intern

2017 - PRESENT
University of Buenos Aires
  • Analyzed the texts of news using natural language processing techniques. In particular, recursive deep models for semantic compositionality over sentiment treebank in order to detect the sentiment of a sentence, dimensional reduction algorithms and topic detection methods were used with the intention of characterizing the mass media bias during presidential elections.
  • Focused my study on developing better machine learning techniques which efficiently uses the information of a node and its neighbours. In addition, This new semi supervised methodology will be validated using graphs of biological and social origin.
Technologies: XGBoost, Keras, TensorFlow, Scikit-learn, MATLAB, R, Python

PhD. Software Engineer Intern

2021 - 2021
Facebook
  • I proposed a lookalike model to generate expanded audiences for Facebook and Instagram ads, using user embeddings and graph clustering.
  • I implemented a lookalike model to generate expanded audiences in Python.
  • I evaluated my proposed machine learning method, and the results showed an improvement in the precision, recall, and conversion score on synthetic and real data.
Technologies: Python, Machine Learning, SQL, C++, Unsupervised Learning, Statistics, Predictive Modeling, Data Visualization, Git, Python 3, Pandas

PhD. Software Engineer Intern

2020 - 2020
Facebook
  • Experimented with and benchmarked uncertainty estimation methods for ad ranking models of Facebook.
  • Implemented deep learning models and analyzed more than 20 terabytes of data.
  • Improved the normalized entropy score for the ads matching task by 1.6%.
  • Designed and develop Bayesian deep learning models.
Technologies: Python, Machine Learning, Bayesian Statistics, SQL, Data Visualization, Git, Python 3, Pandas

Machine Learning Team Leader

2018 - 2019
Mototech
  • Developed a forecasting algorithm that predicts the performance of NFL players.
  • Managed a group of four software engineers and data scientists.
  • Used web scrapping tools to automatically download data from different types of websites.
  • Outperformed the results of the state-of-the-art techniques by reducing the MSE from 8.541 to 5.576.
Technologies: Keras, TensorFlow, Scikit-learn, R, Python, Data Visualization, Python 3, Pandas

Invited Professor

2018 - 2019
Digital House
  • Dictated theoretical and applied lectures with code examples.
  • I used TensorFlow, Python, and Keras during the lessons.
  • The syllabus included the following topics: topic detection, dimensional reduction, embeddings, time series analysis, sentiment analysis, and text analysis/text mining.
Technologies: Keras, Matplotlib, TensorFlow, Scikit-learn, Python, Statistics, Data Visualization, Pandas

Data Scientist

2016 - 2017
Hexagon Consulting
  • Implemented different machine learning forecasting models using financial datasets.
  • Designed and implemented a recommendation system that used text analysis (natural language processing, topic detection, sentiment analysis, and word embedding).
  • Created and developed software that statistically calculates a personal index of inflation based on a big economic and financial database.
Technologies: JavaScript, Predictive Modeling, Scikit-learn, Python, Data Science, Data Visualization, Python 3

Transparentar

https://github.com/YamilaBarrera/transparentar
Created and developed software which uses statistics in order to analyze a complex network of fishing data.
2018 - 2022

Ph.D. Candidate in Computer Science and Machine Learning

Buenos Aires University - Buenos Aires, Argentina

2011 - 2017

Licenciatura (Equivalent to a Bachelor + Master Degree) in Physics

Buenos Aires University - Buenos Aires, Argentina

Libraries/APIs

Scikit-learn, PyTorch, Pandas, Keras, Matplotlib, XGBoost, TensorFlow

Tools

MATLAB, Jupyter, Spyder, Git

Languages

Python 3, Python, JavaScript, R, SQL, C++

Platforms

Linux, Windows

Other

Neural Networks, Text Mining, Natural Language Processing (NLP), Embedded Software, Word2Vec, Regression Modeling, Predictive Modeling, Data Visualization, Data Science, Statistics, Data Analysis, Web Scraping, Generative Pre-trained Transformers (GPT), Generative Adversarial Networks (GANs), Machine Learning, Bayesian Statistics, Unsupervised Learning

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring