João Pereira

Data Science Lead @ adidas

prof_pic.png

Amsterdam, The Netherlands

I work at adidas where I build scalable machine learning solutions in the cloud that enable better product discovery and deliver personalized experiences to millions of users across adidas.com and App. My passion lies in building a culture of innovation, technical excellence, and where people feel empowered to be the best version of themselves. Most of the time, my focus is on transforming cutting-edge AI technologies into impactful products that elevate customer experiences and drive business growth.

Outside of work, I’m a fitness enthusiast, avid traveller, and a blogger.

News

Sep 22, 2023 Our adidas X AWS paper on "Probabilistic Demand Forecasting with Graph Neural Networks" was presented at ECML-PKDD23'!
Jun 20, 2023 Published a new Medium article: “Fine-tune MPT-7B on Amazon SageMaker”
Mar 20, 2023 I joined the AWS weekly series Build on Generative AI.
Mar 3, 2023 My Medium article on “Fast and scalable hyperparameter tuning and cross-validation in AWS SageMaker” is out!

Selected Publications

  1. Probabilistic Demand Forecasting with Graph Neural Networks   1 citations
    Kozodoi, Nikita, Zinovyeva, Liza,  Valentin, Simon and 2 more authors
    In ECML-PKDD 2023 International Workshop on Machine Learning for Irregular Time Series 2023
  2. Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention   186 citations
    Pereira, João,  and Silveira, Margarida
    In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) Dec 2018
  3. Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection   96 citations
    Pereira, João,  and Silveira, Margarida
    In 2019 IEEE International Conference on Big Data and Smart Computing (BigComp) Feb 2019
  4. EngD Thesis
    FIOD Image Intelligence: An Application for Large-Scale Object Detection and Analysis
    Pereira, João
    Feb 2021