This course presents the techniques most commonly employed in the analysis of large volumes of data, in the extraction of knowledge from this data, and in making decisions based on the knowledge acquired. It also presents the problems related to data mining that are not yet resolved satisfactorily at present and, therefore, are open research areas. More specifically, after finishing this course, students will be able to: (1) Collect and integrate data arising from different sources to build a data warehouse. (2) They will know the different architectures and implementations of a data warehouse, as well as the guidelines to be followed in its maintenance. (3) They will know the different types of problems (tasks) that can be addressed through data mining: classification, regression, clustering, correlations and association rules; and they will have criteria to discern which of these tasks must be resolved to address a real problem. (4) They will know the different data mining techniques which can be used to solve the different tasks. (5) They will be capable of obtaining new knowledge in the form of patterns or models from a data set. (6) They will be capable of assessing the quality and interpretability of knowledge obtained by using different validation techniques. (7) They will know the problems that are still not resolved in the field of data mining and, therefore, they are open research fields.
- General description
- Course definition document