Project description

  1. Consider a data set of your choice: e.g. from Kaggle or from any other source (e.g. job or your master thesis).
  2. Apply the KD and Data Mining algorithms described in the first three lectures. Describe the results you have obtained and the knowledge you have extracted.
  3. Use either the result of this analysis or any other many-valued context to build a ToscanaJ system as explained in Lecture 7. Describe in detail the scales you have built and the amount of knowledge you was able to extract here from. Be inventive and creative in the scale building, usually the knowledge gems are there, but you need to dig after them.
  4. Choose a set of attributes from any source you are comfortable with (master thesis, job, computer science, etc.) Perform attribute exploration on this set of attributes and collect the relevant knowledge from experts in that field. Explain your results and what you have learned here from.
  5. Choose a triadic data set and perform knowledge discovery as discussed at the course.

This project will be your final mark, so please solve it careful. You need to provide a detailed report with your results.