SC2320 DATA ANALYTICS & MINING

In the era of big data, organizations collect massive, rapidly growing datasets comprising text, images, graphs, and vectors. Turning stored data into reliable, actionable knowledge does not happen automatically; it needs principled methods that go beyond basic querying. This course addresses that gap by teaching algorithms and systems that convert raw data into insight at scale. Manual analysis does not scale and often misses structure in large, complex datasets. Modern data analytics combines statistics, machine learning, and database systems to automate this process. We will study methods that work effectively on large datasets, including scalable clustering, classification, frequent pattern mining, graph analytics, and nearest-neighbor search, along with practical tools such as Apache Spark and MapReduce. This elite course offering is up-to-date and research-aware. Students will examine recent award-level papers, analyze real research scenarios, and practice end-to-end workflows from data cleaning to evaluation. The aim is to equip you to reason about methods, build scalable pipelines, and communicate findings with rigor.