Course Detail


CSE445


Data Mining and Information Retrieval

3 Credit Hour Course

Intended For Level 4 Term 1 Students

Prerequisite:

Introduction to Data Mining; Finding similar items: applications of set similarity, shingling of documents, locality-sensitive hashing, distance measures, the theory of locality-sensitive functions, LSH families for other distance measures, applications of locality-sensitive hashing, methods for high degrees of similarity; Mining Data Streams: the stream data model, sampling, filtering, counting distinct elements, estimating moments, counting ones in a window, decaying windows; Link Analysis: PageRank algorithms, topic-sensitive PageRank, link spam, hubs and authorities; Frequent itemsets: the Market-Basket model, the A-Priori algorithm; Clustering: hierarchical clustering, K-means algorithms, the CURE algorithm, clustering in non-Euclidean spaces, clustering for streams and parallelism; Advertising on the Web: issues in on-line advertising, on-line algorithms, the matching problem, adwords, search engine optimization; Recommendation systems: content-based recommendations, collaborative filtering, UV-decomposition; Mining social-network: clustering of social-network graphs, discovery of communities, partitioning of graphs, finding overlapping communities, Simrank, counting triangles, neighborhood properties of graphs; Dimensionality reduction: principal component analysis (PCA), singular-value decomposition, CUR Decomposition.