Data Analysis on Big Data Applications with Small Samples and Incomplete Information

The EU and other public organizations at different levels of national and local government across the world have funded and invested in numerous research and development projects on big data transport applications over last few years. The mid and long term effectiveness of these applications is very difficult to measure, and the benefits and usability of these applications are not easy to calculate. NOESIS, funded under EU H2020 program, aims to design a decision supported tool by gathering and analyzing these applications as use cases to formulate sufficient knowledge for policy makers to make informed decisions for their big data transport applications. The challenges in this work are associated with a small number of samples, with incomplete information, but having a good size of features that need to be analyzed to make a confident enough recommendation. This paper reports various statistical and machine learning approaches used to address these challenges and their results.