This module is about a core set of modern analytical techniques that are often used to manage Big Data in finance. First, students will be taught on the module unsupervised machine learning data management techniques that are often used in finance (e.g. clustering algorithms). Second, students will also be taught Deep Learning techniques that are often used to manage Big Data in finance, including Neural Networks. Third, Reinforcement Learning techniques and their potential applications to portfolio selection and trading strategies will also be covered in the module. Throughout, this course spends a significant amount of time on practical applications of theories introduced along with their role in promoting ethical and sustainable businesses, financial systems and economies.
Learning Outcomes
By the end of the module students should be able to:
Critically apply a range of techniques to manage Big Data and carry out projects by using data obtained from Birmingham Business School’s Trading Room that have access to Bloomberg, WRDS, ORBIS Bankfocus, COMPUSTAT, CRSP, Datastream, etc.
Demonstrate critical knowledge and understanding of Deep Learning Techniques and Reinforcement Learning Techniques.
Critically apply a range of Big Data management techniques to solve problems in finance (such as in asset management, portfolio choice, trading strategies, etc.).
Design, collect, disseminate and manage data in an ethical and responsible manner.
Assessment: An individual computer-based project containing about 2,000 words (or equivalent) (50%) and A 15-minutes video on a big data management exercise (50%) Reassessment: A 4,000 word Individual Assignment (100%)