The project's objective is to develop a methodology and tools for creating and populating a prototype real estate securitization chain. Residential and commercial mortgage loans are pooled and then securitized as mortgage backed securities (MBS). Several financial institutions participate along the chain, playing the “role” of mortgage originator, service provider, trustee, MBS issuer, etc. The MBS financial contract is represented by a “waterfall structure”, connecting the mortgage pools and the securities, and a set of “distribution rules” to control payments. This wealth of knowledge about the interconnected network of participant financial institutions, and the dynamics of the chain, is captured within unstructured or semi-structured financial contract documents. An initial challenge for MBS+ is to identify relevant sections of the MBS contract document; to determine a relevant template for knowledge extraction from each section; to develop extractors; and finally to validate the results. Integrating MBS+ with other heterogeneous datasets, e.g., historical payments against mortgages, performances of securities, etc. will complete the modeling of the supply chain. MBS contracts were at the center of the 2008 financial crisis. This project will demonstrate the use of text analytics and is in partnership with the IBM System T team and Fischer Real Estate Center at the Haas School at the University of California Berkeley.