The purpose of this course is to develop a solid understanding of fundamental probability theory for quantitatively assessing uncertain events. Each teaching topic focuses on the practical applications of probability concepts in fields such as economics, finance, actuarial sciences, and risk management.

Topics covered include: an overview of probability, random variables (discrete, continuous), probability distributions, mathematical expectation, functions of random variables, sampling distributions, jointly distributed random variables, the likelihood function, stochastic processes, and more.

This course uses Python and/or R. No prior programming experience is required.

This course introduces students to the application of foundational statistical methods for data modeling, with programming integrated throughout.

Topics covered include: probability calculations, A/B testing, statistical inference, probability modeling, simple linear regression, local regression, multiple linear regression, logistic regression, the bootstrap, survival analysis, and more.

This course uses Python and/or R. No prior programming experience is required.

This course provides an introduction to fundamental concepts, techniques, and tools in data analytics. Students will learn how to analyze data to extract meaningful insights, make data-driven decisions, and solve real-world problems using the Python programming language. Special emphasis is placed on examples involving data from economics, finance, and actuarial science.

Topics covered include: an overview of data analytics, composing data graphics, the general steps of a data analysis project (import, wrangle, visualize, model, communicate), Quarto, GitHub and GitHub Pages, combining multiple tables, tidy data principles, web scraping, data cleaning, exploratory data analysis (EDA), feature engineering, application programming interfaces (APIs), D3, interactive data graphics, dashboards, web apps, and more.

This course uses Python and may also include R. No prior experience is required.

The purpose of this course is to introduce students to modern applied statistics, with a primary focus on data analysis.

Topics covered include: a review of probability theory, the law of large numbers (LLN), the central limit theorem (CLT), point estimation (method of moments, maximum likelihood), properties of point estimators (unbiasedness, consistency, efficiency), descriptive statistics, skewness and kurtosis, Monte Carlo simulation, numerical optimization, hypothesis testing, A/B testing, confidence interval estimation, nonparametric methods, and more.

This course uses Python and may also include R. No prior experience is required.

This course provides an introduction to the fundamental concepts and principles of modern database management systems (DBMS). Through a balanced blend of theoretical foundations and practical skills, students will learn to design, implement, and manage databases efficiently. On completion of the course, students will possess a comprehensive understanding of database architecture, data modeling, query languages, and database administration techniques. Special emphasis is placed on examples and data from economics and finance (such as tick data, receipts, emails, and social media data).

Topics covered include: overview of data management systems, the relational model and relational database concepts, database design and implementation, database querying with Structured Query Language (SQL), exploring the limits of SQL, handling structured, semi-structured and unstructured data, distributed databases, introduction to Not Only SQL (NoSQL), types of NoSQL databases (document, key-value, column-family, graph), database administration best practices, connecting to and working with SQL and NoSQL databases in Python, ETL, and more.

This course uses SQL. No prior experience is required.

Causal inference encompasses tools that allow economists to determine what causes what. This course introduces students to methods from traditional econometric theory and modern machine learning, required to obtain meaningful answers to questions of causation. Using examples and data from economics (such as the effects of product price on sales volume, college on earnings, increases in the minimum wage on employment, and early childhood education on later incarceration) and the Python programming language, students will gain practical skills and theoretical understanding.

Topics covered include: design of experiments, review of probability and regression, structural equation models (SEMs), directed acyclic graphs (DAGs), structural causal models (SCMs), difference-in-differences, regression discontinuity designs, and more.

This course assumes basic proficiency in Python.

This course provides an overview of Machine Learning (ML) principals. The goal of the course is to teach you the basics of the ML theory and practice of ML algorithms. The course will build upon the knowledge and skills you gained in econometrics and statistics courses. Students will learn how to interpret, design, and execute empirical projects using software and skill building in critical thinking and problem solving will also be emphasized. We will additionally explain important issues and topics that recently happened in the ML literature.

This course covers models used in the econometric analysis and forecasting of economic time series, particularly macroeconomic time series. The models covered include stationary and non-stationary autoregressive moving average models, autoregressive distributed lag models, error correction models, vector autoregressions, and vector error correction models. Topics include correct inference and interpretation of model parameters, model selection, structural change, and forecasting, forecast uncertainty, and forecast evaluation.

This course introduces more advanced machine learning methods applicable in economics, finance, risk management, and actuarial science.

Topics covered include: supervised and unsupervised learning, principal components analysis (PCA), recommender systems, gradient descent, K-means clustering, hierarchical clustering, principal component regression, partial least squares (PLS), regression splines, generalized additive models (GAMs), bagging, random forests, boosting, Bayesian additive regression trees, support vector machines (SVMs), neural networks (deep learning), and more.

This course uses Python and may also include R.

This course explores various techniques for the analysis of text, audio, images, and videos. Special emphasis is placed on examples and data from economics and finance (such as satellite imagery, earnings calls transcripts and recordings, CEO and Executive interviews, financial news, and social media data).

Topics covered include: natural language processing (NLP), sentiment analysis, text classification, speech recognition, image processing, face detection, face recognition, and more.

This course uses Python and may also include R.

This course is designed to cover specialized topics in data science relevant to economics, with the aim of equipping students with the current knowledge and practical skills necessary to tackle data-driven challenges. Students will explore tools, applications, and insights across various domains within data science. Talks and workshops will be delivered by representatives from both industry and academia (possibly online).

Tentative topics include: data governance, data storytelling, network analysis, natural language processing (NLP), large language models (LLMs), generative AI (GenAI), AI agents, Bash, Docker, quantum machine learning, Power BI, Tableau, how to prepare for your first data science job, navigating a career in data science, and more.

In this course, students will explore big data analytics using the powerful framework of Apache Spark, with a focus on PySpark, the Python API for Spark. Through a hands-on approach, students will develop practical skills in handling large-scale data, perform statistical analysis, and apply machine learning techniques. Special emphasis is placed on examples and data from economics and finance (such as tick data, emails, IoT data, and social media data).

Topics covered include: sources of big data, structured, unstructured and semi-structured big data, big compute and parallel computing, data wrangling, exploratory data analysis (EDA), machine learning (ML), clusters, Hadoop (HDFS, MapReduce), Spark (RDD, Spark SQL, MLlib, Structured Streaming), feature engineering, training and testing statistical models (supervised and unsupervised learning), Spark ML Pipelines (operating modes, interoperability, deployment).

Python is used throughout the course.

This course surveys some of the major cloud infrastructure providers for big data analytics and data science. Students will learn how to get started with cloud providers and gain valuable hands-on experience with cloud services such as Amazon Web Services (AWS). Special emphasis is placed on examples and data from economics and finance (such as tick data, healthcare records, IoT data, and social media data).

Topics covered include: overview of cloud providers, large-scale projects, scaling out, cloud clusters, cloud storage systems and data management, cloud computing and compute instances, how to launch, access and manage cloud clusters, troubleshooting and deployment of automated solutions, best practices, and more.

Python and SQL are used throughout the course.

This course explores the foundational concepts and techniques for analyzing complex networks, with a special emphasis on examples from economics and finance (such as business model design, market analysis, and developing user growth strategies).

Topics covered include: graph theory, distance and centrality measures, clustering, random network models, social networks, exploration, analysis, and visualization of complex networks, and more.

Python is used throughout the course.

This course includes concepts and tools used in econometric modelling and statistical analysis of spatial data: data on attributes that are correlated in ‘space/location’ (a.k.a. geo-tagged data). Spatial data are commonly used in regional science and urban economics (related to property prices, crime, household income, etc.), epidemiology and public health (such as disease clusters, etc.), environmental science (climate change, air pollution, ozone density, etc.), ecology, biology, geology, social interactions and network effects, and other disciplines.

We will start the course by looking at practical aspects of organising and visualising spatial data. We will also discuss how to use a coordinate reference system to give spatial awareness to a dataset and make meaningful maps – the main visual aid for spatial data. Then we will consider the statistical and econometric aspects behind spatial data analysis with a special focus on how to re-align classical statistical and econometric techniques towards spatial data for the three broad types of spatial data: (i) point patterns, (ii) areal data and (iii) geostatistical data.

Exploratory spatial data analysis methods, including various plots and tests for spatial autocorrelation, are discussed. Diagnostic tests for complete spatial randomness against spatial clustering or dispersion is an important step in the initial stages of exploratory spatial data analysis. Point pattern analysis and different methods used to measure the degree of spatial autocorrelation will also be discussed. Spatial econometric models and estimation will be discussed in terms of areal data. Spatial econometric models and methods are effective in modelling spatial dependence and thus useful in predicting attributes that are affected/related to its’ neighbours. We will focus on the main spatial regression models (spatial lag, spatial error, and spatial Durbin) with and without heteroskedasticity. The usual estimation techniques, quasi-maximum likelihood and GMM methods are discussed for model estimation and inferences. The course will end by discussing main methods of interpolation techniques used in spatial data analysis.

Applications of these techniques using R will be presented throughout the course including application examples on the assessment of climate change risks, spread of COVID cases and other diseases, economics of agglomeration, etc.

Prerequisites include probability theory, inferential statistics, and econometrics at an undergraduate level. Knowledge of R programming is useful but not required.

This course introduces econometric models and methods for analyzing panel and longitudinal data that arise from repeated measurements taken from a cross-section of units. These models have found substantive applications in social and biological sciences where the describer “panel” and “longitudinal” respectively arose. This course is primarily oriented to the applications in social sciences including business, economics, education, sociology, etc. Theories are presented lightly without much hustle of derivations and Python codes are provided for real world applications. Major topics include (i) panel data models with fixed effects; (ii) panel data models with random effects, (iii) panel data models with heteroskedasticity and serial correlation, (iv) tests of hypotheses with panel data, (v) cluster robust standard errors, (vi) two stage least squares and instrumental variables estimation, (vii) dynamic panel data models, and (viii) forecasting with panel data. Throughout, we emphasize on applications of panel data models and methods with Python, a dominant software package in data science, machine learning, and artificial intelligence, and an ideal software package for learning econometrics and data analysis.

A good understanding of Parts I & II of Wooldridge (2019). Introductory Econometrics: A Modern Approach, 7th Ed, would be sufficient for the learning of this course.

This course is designed to give students a thorough understanding of high-frequency trading (HFT)—the use of sophisticated algorithms and high-speed technology to execute trades in milliseconds. The course covers the evolution of HFT, explores the technological infrastructure required for low-latency trading, and teaches various HFT strategies such as market-making, arbitrage, and momentum trading.

Students will also investigate the impact of HFT on market liquidity, price discovery, and volatility, while considering the regulatory landscape that governs high-speed trading.

Group Project topics are related current industry practices. Through practical programming exercises, case studies, and simulations, students will develop the ability to design and evaluate HFT strategies, leveraging Python for algorithmic execution.

This course offers a comprehensive introduction to the economics of “Big Tech,” exploring the growing influence of economic principles in major technology companies such as Amazon, Meta, Netflix, and Uber. As economists increasingly shape strategic decisions within these firms, their unique skill set has become invaluable. The course highlights how economists’ expertise in market dynamics and causal inference complements the technical prowess of data scientists, creating a powerful synergy in the tech industry. Moreover, their deep understanding of incentives and economic systems proves crucial for organizations navigating the complex digital marketplaces and platforms of today’s world. Through a series of real-world business cases, students will examine how economic principles drive key business outcomes in the tech sector.

Topics covered include: pricing strategies, ad incrementality and effectiveness measurement, personalization algorithms and their economic impact, logistics optimization for efficiency and cost reduction, the design and analysis of online A/B testing, and more.

This course is designed to be accessible to students from diverse backgrounds, requiring no prior knowledge of economics or programming.