Many distance-related algorithms, such as knearest neighbor learning algorithms, locally weighted learning algorithms etc, depend upon a good distance metric to be successful. In this kind of algorithms, a key problem is how to measure the distance between each pair of instances. In this paper, we provide a survey on distance metrics for nominal attributes, including some basic distance metrics...

EAR4 and CAAR are lazy learners applying the case-based reasoning (CBR) paradigm to numerical prediction tasks. Both augment standard instance-based learning methods by applying automatically generated case adaptation rules to adjust solutions of prior cases, and both apply ensembles of the generated rules. CAAR augments the EAR approach with a richer treatment of case context, more context-awa...

Data mining, the extraction of hidden predictive information from large databases, is a powerful new technology with great potential used in various commercial applications including retail sales, e-commerce, remote sensing, bioinformatics etc. Education is an essential element for the progress of country. Mining in educational environment is called Educational Data Mining. Educational data min...

The dataset used in this exercise is the heart disease dataset available in heart-c.arff obtained from the UCI repository. This dataset describes risk factors for heart disease. The attribute num represents the (binary) class attribute: class <50 means no disease; class >50_1 indicates increased level of heart disease. The main aim of this exercise is to predict heart disease from the other att...