Reliable real-time economic information is essential for policy making but difficult to obtain: publications of official statistics are often delayed, and autoregressive estimates fail to capture unanticipated events. Economic nowcasting can fill the data gap. We present a granular nowcasting method for macro- and industry-level GDP by using a network-based approach, that relies on a novel data set of real-time monthly inter-industry payments in the UK covering 2016-2023. The data captures shocks travelling along the supply chain. Our model is an extended version of generalised network autoregressive model, tailored for networks with time-varying edge weights and nodal time series. This framework allows us to track the impact of network effects arising from input-output dynamics in supplier and customer industries. Supply chains are important for understanding economic outcomes, as powerfully illustrated by recent supply chain disruptions.
About the speaker
Kerstin Hoette
Kerstin is an academic visitor at INET and a postdoctoral researcher in the Finance and Economics Programme at The Alan Turing Institute in London.
She studied economics at the Universities Tübingen and Bonn in Germany, and obtained her PhD in a joint degree programme from the universities Paris-1 Sorbonne-Panthéon and Bielefeld. In 2020-2022 she was a postdoctoral researcher at the Oxford Martin School before joining the Turing Institute.
Kerstin's research focuses on technological change and, more specifically, on technology transitions when incumbent technologies are replaced by emerging alternatives. Major applications of her work are climate technologies and substitution patterns in economic and technological networks.
She has published empirical and theoretical work using macroeconomic, agent-based simulations, patent citation and input-output networks, and other applied empirical analyses. An overview of her research can be found on her Google Scholar entry. In her current role at the Turing Institute, Kerstin is exploring a novel data set based on granular financial transactions data of businesses in the UK.
Anastasia Mantziou
Anastasia is a Postdoctoral Research Associate at The Alan Turing Institute supervised by Gesine Reinert and Mihai Cucuringu from the University of Oxford. Prior to that, she was a Research Assistant in statistical cyber-security at Imperial College London. She completed her PhD in Statistics at Lancaster University under the supervision of Dr Simon Lunagomez, Dr Robin Mitra and Professor Paul Fearnhead. Her research interests include network analysis, Bayesian methods and topic modelling. Her research has been applied to networks emerging from various scientific fields such as neuroscience, ecology and computer science (human tracking systems). Anastasia is currently working on network time series data with application on economics, under the economic networks and transaction data project in The Alan Turing Institute.