This project will build understanding of networked data through a combination of data processing for firm-to-firm transactions data held by Office for National Statistics (ONS), economic modelling and forecasting using data from the whole economic system, and the development of methods for efficiently reducing the dimensionality and complexity of network-generated data.

Explaining the science

When analysing high-dimensional panels of macroeconomic or financial time series state-of-the-art methods tend to suffer from at least two main limitations.

Firstly, they often consider only linear dependencies. In contrast, real such time series are interconnected through a complex network of dependencies, and this network can display systemic risky behaviour. Secondly, the way in which factors affect data is seldom modelled, and typically only fully pervasive factors that affect all time series with similar magnitude are considered. In contrast, real such time series are collections of heterogeneous time series with different types of series influences by a diverse range of factors. 

Furthermore, traditional theoretical models in economics and finance assume that in large ecosystems the influence of a few individual agents is negligible. Yet in large economic and financial panels there often exist one or more subsets of time series that influence the entire cross-section. For example, with a few time series leading on other time series which can be viewed as lagging behind the leading series. One potential modelling approach is to suppose that the set of agents can be partitioned into clusters, such that within clusters there are no consistent lead-lag relationships, while across clusters there exist stable lead-lag relationships. 

The envisioned research will combine methods from machine learning and network analysis to reveal such hidden factors in the analysis of two types of high-dimensional data sets, with the aim of revealing complex relationships inherent within the data and improving forecasting accuracy. The first type of data is a network capturing pairwise interactions, such as cross-sectoral networks of input-output connections. The second type is a panel of economic time series, where the network structure can be examined by considering the correlations between different data streams.

Project aims

The project aims to produce a dataset of firm-to-firm transaction flows in the UK to provide high frequency/high geographic resolution indicators to help understand the impact across the UK on issues such as:

  • Reorganisation of supply chains and Brexit
  • Supply chain fragility
  • Propagation of localised supply disruptions through the production network

Alongside this, the project aims to provide methodological improvements for working with network and high dimensional economic data in order to provide accurate and informative aggregates for policy dimensions and forecasts.


The outputs of this project will provide policy makers with detailed economic indicators at high levels of frequency and regional specificity. These indicators could be used to explore:

  • Supply chain disruptions and bottlenecks, supply chain fragility and systemic risk analysis
  • Propagation of shocks (e.g. COVID-19 or Brexit-related)
  • Monetary and fiscal policy transmission


Keith Lai

Assistant Deputy Director, Office for National Statistics

Researchers and collaborators

Contact info

Tony Zemaitis
[email protected]