¹û¶³Ó°Ôº

The Big Data in Quantitative Finance module combines lecture style presentations with hands-on coding challenges. The module will provide you with the skills to understand the design of big data systems (NoSql, Sql, Apache Kafka and Spark) as well as a theoretical understanding of big data modelling (machine learning, supervised and unsupervised learning) and analytics (e.g. data analytics, business intelligence, data mining).

The module is formed of three sections, and each section will involve a milestone project that contributes to the final assessment. In doing so, you will focus on the practical and technical aspects of Big Data and develop the expertise to optimise your resume or create your business portfolios.

The first section describes the realm of big data, challenges and opportunities. Alongside, the section delivers deep-dive in the main differences between Structured (PostgreSql) vs Non-Structured (MongoDB) databases and big data distributed processing frameworks (Apache Spark). Within this section, you will also be familiarised with Virtual Machines, Unix Commands and the syntax to query big data in finance.

In the second section, the database skills are put into practice and you will master the art of querying financial big data from a computational environment (R/Python/Java). The core part of this section focuses on the techniques used in finance for data mining and advanced statistics methods. By collaboratively working in teams, you will face real world challenges and deliver the first project on finance data analytics (RShiny). This is achieved by working with collaborative development tools (Git).

In the third section, one of the main techniques of Machine Learning (ML) is reviewed with an implementation on Big Data Examples. This unit covers the mathematical theoretical framework of ML and provides practical examples to overcome the main challenges of Big Data in Finance.

The objective is to instil a comprehensive understanding of the challenges faced by organisations on the journey of applying Business Intelligence and ML. In addition, as part of the Big Data in Finance Module, a non-mandatory seminar series will run. Experts from the industry will share knowledge on Big Data issues, challenges and demand from a business perspective.

Learning Outcomes

• Have a solid foundation in Big Data architecture, engineering and manipulation
• Know the use of large data sets and their applications in financial data analysis
• Gain the ability to approach issues in handling financial data
• Gain the ability to gather data and collate and analyse extremely large data sets
• Have a good understanding of the most advanced and cutting-edge models in statistical methods