European Union and governments of the member states are striving to respond to contemporary socio-economic challenges with social investments and enhanced social support, often relying on social innovation in their quest to welfare reforms. However, social policy innovations targeting to improve social welfare, often neglect objective data describing societal phenomena and European citizens’ perspectives and patterns of human behaviour, resulting of their real status of wellbeing. Systematic methods for measuring the impact of innovative social policy reforms and transformations in the provision of social services is an important research challenge in the European welfare system. In this chapter, a comprehensive model of evidence-based social policy making is proposed, driven by dynamic simulation methodologies and data mining techniques to extract evidence from two types of data. On the one hand, objective data coming from a multiplicity of sources, including governmental data and statistical data, are used to capture the interlinked policy domains and their underlying casual mechanisms. On the other hand, it considers behavioural aspects and citizens’ opinions as data analytics emerging from Web 2.0 sources, social media posts, polls and statistical surveys. To combine this multimodal information, our approach suggests a modelling methodology that bases on big data acquisition and processing for the identification of significant factors and counterintuitive interrelations between them, which can be applied in any policy domain. Then, the suggested methodology is applied within the context of a social policy innovation initiative aiming to counter adversities of the migration challenge. The presented model provides a first proof a concept on how ICT and specifically data intelligence can drive social policy reforms. However, further application and validation of the approach for driving policy design and implementation in the future in any domain, is suggested.