Introduction
Please note that this is a preliminary course description. The final version will be published in June 2026.
Sequence data, in the form of time series or text, is essential in most business domains. For example, Gross Domestic Product is measured across time and is the most widely used indicator of a nation’s economic activity. Similarly, written text follows in a natural order and investors use companies’ financial statements to gauge profitability, growth prospects, and risk.
In this course you will be given a thorough introduction to classical time series analysis, trend and cycle decompositions, the usage of state-space and factor models, and the celebrated Kalman Filter. These tools are used heavily not only in applied economics and finance, but also in all other domains where time series analysis is important.
You will also learn to use text as data. Standard Natural Language Processing (NLP) concepts and techniques are covered alongside recurrent neural networks and more modern Transformer-based models. These types of architectures underlie recent advances in NLP and Large Language Models (LLMs). However, since both text and time series are sequence data, these methodologies can be used for modelling both types of data modalities.
The course is organized as a blend of theoretical concepts and hands-on practical exercises. Prior exposure to quantitative subjects within programming, statistics and machine learning is mandatory.