Data Mining Portfolio

Lin Guo

My portfolio started as a set of data mining projects for CSCI568 Data Mining Course instructed by Yong Bakos. In the data mining projects, I adopted the fundamental data mining strategies to different real world data sets and discoveres the internal patterns hidden in large data set using professional data mining toolkits WEKA. It then covers a complete description and examples of data mining techniques including similiary metrics, clustering, and predictive classification models. The classification models includes ANN, Bayesian classifier, decision tree classifier and k-Nearest Neighbors.

Date Mining Projects

• Project 6: Wikipedia Data Mining Project
• Project 7: Assocation Rule Mining with Wikipedia Tag Data Set
• Final Project: Mining Process with Real World Ski Resort Data Set

Date Mining Techniques

• Mining Similiary Using Euclidean Distance, Pearson Correlation,and Filtering
• Mining for Groups Using Clustering Algorithms
• Predicting Data Sets Using Classification Models
• Artificial Neural Network (ANN)
• Bayesian Classifier
• Decision Tree Classifier
• K-Nearest Neighbors