In this project, we pretend to analise, use and justify the use of Big Data nowadays in different areas like companies, research laboratories, etc., as well as different tools and Open Source technologies behind it that make it possible. The methodology used for this project has consisted on doing an exhaustive analysis of the current and future situation of Big Data, the introduction of the tools and Open Source technologies available, the study and comparative of each of them and the final experimental development with our own data. We highlight the use of Big Data, along with the associated technologies and tools such as Hadoop and Spark, as a great alternative to classic way of storing and processing big amounts of data. Given that it is a new concept for us, we are going to try to exploit as much as possible the Open Source functionalities related to Big Data and we are going to give our own personal recommendation on each one evaluating their main characteristics. Finally, we are going to dig further on the concept of Machine Learning on which a lot of companies are focusing their development. In order to do this, we are going to do an experimental project aiming to detect people's position based on the access points whose devices are connected to. The main objective is to study different algorithms to obtain the best possible accuracy of personal position and to compare the different results throw the analysis and processing of obtained data such as Building, Floor, etc.