Specializing in data mining and deep learning for time series analytics.
I am a Research Scientist at EDF R&D (EDF Lab Paris-Saclay), where I conduct research on deep learning for time-series applied to smart-meter electricity analytics. My work aims to improve grid flexibility and provide insightful, actionable feedback to consumers based on their consumption data.
Methodologically, I'm currently working on representation-learning approaches using deep learning models that serve as foundations for downstream task applications, as well as proposing novel generative approaches to synthesize realistic load profiles for data augmentation. My research applications span advanced time-series classification, regression, forecasting, and Non-Intrusive Load Monitoring (e.g., appliance-level energy disaggregation).
I completed my Ph.D. in Artificial Intelligence at Université Paris Cité and EDF R&D, under the supervision of Prof. Themis Palpanas. My thesis, Deep Learning for Electricity Consumption Time Series Analytics, introduced novel scalable deep-learning methods for extracting information from very low-frequency smart-meter data.