I want to apply symbolic machine learning (e.g. case-based reasoning, inductive logic programming) to OSM data. In detail, I want to use OSM Map Features to predict characteristics of residential buildings.

Does anyone know algorithms, applications or related work to that problem?

closed as too broad by John Powell, Michael Stimson, underdark Jun 27 '15 at 15:54

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 2
    Can you name us an example of a residential building characteristic that could be predicted out of OSM data? I have trouble understanding your question and I guess I won't be the only one. – scai Jun 26 '15 at 11:57
  • e.g. single-family home or multi-apartment home, or if the building is next to the city centre or in the country – hopfk Jun 26 '15 at 12:20
  • 1
    But that's nothing which has to be "predicted". This kind of information is already available within OSM, at least partly. – scai Jun 26 '15 at 12:51
  • Yes, some of these information are present in OSM, but the density of information is low. I'm searching for a method to combine OSM data with other data sources to retrieve information about private houses - symbolic machine learning could be a solution for that. – hopfk Jun 26 '15 at 12:56
  • 1
    Please switch to the OSM Forum/mailinglists as your question is pretty broad. Please see Wiki Research for papers and projects related to OSM – Mapper Jun 27 '15 at 5:31