João Pereira

Senior Data Scientist at adidas | EngD Data Science


Amsterdam ❌❌❌

The Netherlands

I am a Senior Data Scientist at adidas in the Global Digital Data Science team in Amsterdam where I am responsible for the technical lead of two demand forecasting products. Prior to joining adidas, I completed my Engineering Doctorate (EngD) in Data Science at Eindhoven University of Technology, where I worked on projects for companies like ASML (2x), Van Lanschot, TE Connectivity, Heijmans, and FIOD. Before the EngD, I conducted deep learning research on anomaly detection in time series data and completed my Master’s and Bachelor’s degree in Electrical & Computer Engineering at Instituto Superior Técnico (Portugal). Meanwhile, I was lucky to have spent a semester at Université Catholique de Louvain (Belgium). I am broadly interested in the field of machine learning and its endless applications and passionate about turning cutting-edge research into products.

In my free time, I enjoy working out, meeting friends, traveling, and cooking new dishes.

Feel free to reach out to me with any queries!


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!
Jan 15, 2023 I took up a new role at adidas as Senior Data Scientist!
May 20, 2020 I gave a talk on "Anomaly Detection with Variational Autoencoders".

Selected Publications

  1. Probabilistic Demand Forecasting with Graph Neural Networks   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   162 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   76 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