The "Big Data and Machine Learning" research group is dedicated to the development of machine learning algorithms on large databases. More specifically, it develops new methods for analyzing, processing and predicting temporal data. Complex temporal interactions, massive and highly heterogeneous data, and high-dimensional modelling pose new statistical and computational challenges that the service addresses in collaborative research projects. The algorithms developed are then applied in many fields, such as energy (e.g. forecasting electricity consumption and production in smart power grids) or logistics (e.g. forecasting orders for parts from high-tech manufacturers).