The Econometrics and Business Analytics section conducts research into business intelligence, climate econometrics, econometric methods and theory, operations research, analytics and logistics as well as time series and financial econometrics.

We conduct research in business intelligence to support strategic and operational business decisions. We utilise statistical methodologies to extract insights from complex data and analyse the impact of digital technologies on business performance. Our research spans diverse data types: structured, semi-structured, and unstructured, acquired through channels like transactions, surveys, clickstreams, experiments, case analyses, secondary sources, social media, and internal metrics.

Main topics: Data capabilities, digital technologies, causal inference, artificial intelligence, machine learning, structural equation modeling, behavioral patterns, data-driven decision making, business performance

Climate econometrics investigates the statistical connections between macroeconomic and climate data, focusing on understanding the causal link between economic activity and climate dynamics, as well as the macroeconomic consequences of climate change. We employ econometric methods to address climate physics problems, integrating insights from various disciplines and fostering an interdisciplinary approach to problem-solving. By utilising a wide range of data sources, we strive to deepen our knowledge and contribute to this vital and complex field.

Main topics: Climate data and models, emissions modeling and forecasting, green transition

In econometrics methods our research develops tools to analyse complex economic data, with a focus on cutting-edge areas such as causal inference, high-dimensional models, and robust methods. We strive to develop innovative and rigorous methodologies that address real-world challenges in economics and related fields.

Main topics: Bootstrap methods, cluster-robust inference, high-dimensional models, machine learning, nonparametric statistics, treatment effects and causal inference

Many companies face the question how they should get their products and services to the customer (and in some cases, back). Several decisions have to be taken to enable this: The choice of suppliers, of how much should be kept on stock, when we produce and transport, how we ensure that our capacity is utilised, and so on. These decisions should be taken to achieve objectives, such as minimisation of costs and maximisation of resilience or responsiveness. The decision-making process has a solid foundation in mainly quantitative data.

Our research focuses mainly on the development of quantitative methods in the mentioned problem area. These methods compare a set of solutions that are possible within in a problem situation to achieve the relevant objectives, in some cases to prescribe a course of action and in other cases to analyse the situation and provide insights. Our methods are in the intersection of analytics and operations research, and include simulation, (integer) linear programming, heuristics, dynamic programming, and analytical approaches.

Main topics: Supply chain management, logistics, business analytics, operations research, operations management, management science, revenue management, multi-objective optimisation, routing, inventory control, closed loops and circularity

We conduct research in all areas of time series analysis and financial econometrics, including, for example, forecasting, nonstationarity, and volatility modeling. We strive to develop rigorous methodologies and engage in empirical research that addresses real-world challenges with economic and financial time series data.

Main topics: High-frequency data, long memory and fractional integration, nonstationary time series and cointegration, volatility modeling and forecasting