The fundamental problem of processing big data lies in the data's diversity and abundance. Analysing heterogeneous information allows for a more complete description of reality to be formed, enabling more accurate forecasting. At the same time, volumes of such data are growing at an exponential rate, and special preparation is required to work with big data effectively. With the aim of creating a world-class practical centre to improve expertise in big data processing and analysis, the LAboratory of Methods for Big Data Analysis (LAMBDA) was created in February 2015. LAMBDA currently focuses on using machine-learning and data analysis methods to solve issues in fundamental sciences such as particle physics and astrophysics. The Laboratory’s main developmental direction is to work with leading scientists from these fields to search for answers to the universe’s mysteries. Specifically, the Laboratory cooperates with the European Organization for Nuclear Research (CERN), researching the events of the Large Hadron Collider and raising the efficiency of data analysis. In addition, the Laboratory’s educational activities include organizing and carrying out academic seminars and summer/winter schools on big data analysis and providing scientific guidance to thesis and dissertation work.