MAT 386E - Computational Data Science

Course Objectives

1. To teach data warehouse, data extraction, transformation and loading and their applications.
2. To teach mathematical background of data processing algorithms.
3. To apply data processing algorithms to the real life problems.
4. To teach architecture and tools of big data platforms.
5. To teach data analysis and to visualize and to report the results.1. To teach data warehouse, data extraction, transformation and loading and their
applications.
2. To teach mathematical background of data processing algorithms.
3. To apply data processing algorithms to the real life problems.
4. To teach architecture and tools of big data platforms.
5. To teach data analysis and to visualize and to report the results.

Course Description

Big Data and project management. Statistical methods and machine learning in data science: Regression analysis and modelling, basic classification and clustering methods. Data warehousing and structure, data extraction, transform and loading (ETL). Performance metrics and risk management. Big data platforms: Architecture (Hadoop, Spark), tools (MapReduce, Spark ML, Kafka, Flink, Hive). Data processing methods. Sectoral applications. Model visualization and evaluation. Data Visualization and reporting and interpretation of results.