Regional trade flow

• Regions are more specialised and open than countries
• Important external trade dependences (Thissen et al. 2016)
• Regions vary in terms of their specialisation patterns and, therefore, in their trade relationships and openness

Regional trade flow

• Knowing and predicting regional trade then helps to understand:
  • regional economic performance
  • exposure to external shocks
  • place-based development
• Employment vulnerability and transmission of internal and external shocks is different for different regions.
• Workers in regions in the US with a specialisation in specific manufacturing industries were more vulnerable for the emergence of China (Autor et al. 2013)

Regional trade flow: hardly any data

• Big caveat: interregional trade data
• Europe: spatially disaggregated IO for NUTS2 regions (Thissen et al., 2018)
• Coslty, difficult exercise

Our contribution

• Utilise the digital traces that interregional trade leave behind
• Model and predict interregional trade flows for the UK
• Scrape open web data
• Hyperlinks between commercial websites
• Machine learning techniques for out-of-sample predictions
• Hypothesis: such hyperlinks reflect business and trade relations

Web data and businesses

• Businesses may not expose all of their strategies on their websites, but neither do they do during surveys (Arora et al. 2013)
• Business websites:
  • spreading information
  • establishing a public image
  • supporting online transactions
  • sharing opinions

Spatial studies using hyperlinks

• Hyperlinks tend to follow national borders and gravitate towards the US (Halavais 2000)
• Keßler (2017) used the hyperlinks between German Wikipedia webpages to represent the hierarchy of urban centres in Germany
• Salvini and Fabrikant (2016) used a the English Wikipedia to build a graph of world cities
• Hyperlinks between and to administrative websites to study spatial relationships and structure (Holmberg and Thelwall 2009; Holmberg 2010; Janc 2015)

Spatial studies using hyperlinks

• Lin, Halavais, and Zhang (2007) used webblog hyperlinks to analyse the spatial reflections of the blogsphere
• Jones, Spigel, and Malecki (2010) focused on the New York City theatre scene to investigate the existence and role of a ‘virtual buzz’

Business studies using hyperlinks

• Hyperlinks to business websites reflect business motivations and contain useful business information (Vaughan, Gao, and Kipp 2006)
• Significant correlations between the number of incoming links and business performance (Vaughan 2004; Vaughan and Wu 2004)
• Krüger et al. (2020) used hyperlinks between business websites in Germany to test the role of different proximity frameworks
• Ιnnovative businesses share more hyperlinks with other business, which also tend to be innovative

Spatial interaction predictions

• Plenty of ML applications predicting out-of-sample flows:
  • Robinson and Dilkina (2018) used XGBoost and Artificial Neural Network models to predict global migration
  • Tribby et al. (2017) used RF to select variables associated with walking route choice models
  • Guns and Rousseau (2014) use RF to predict and recommend high-potential research collaborations, which have not yet been materialised

Spatial interaction predictions

• Current economic thinking advocates towards the use of ML algorithm such as Random Forest
• They tend to outperform ordinary least squares in out-of-sample predictions even when using moderate size training datasets and limited number of predictors (Mullainathan and Spiess 2017; Athey and Imbens 2019).

Web data: The Internet Archive

• The largest archive of webpages in the world
• 273 billion webpages from over 361 million websites, 15 petabytes of storage (1996 -)
• A web crawler starts with a list of URLs (a seed list) to crawl and downloads a copy of their content
• Using the hyperlinks included in the crawled URLs, new URLs are identified and crawled (snowball sampling)
• Time-stamp

Web data: The Internet Archive

Web data: The Internet Archive

Our web data

• JISC UK Web Domain Dataset: all archived webpages from the .uk domain 1996-2010
• Curated by the British Library
• Tranos, E., and C. Stich. 2020. Individual internet usage and the availability of online content of local interest: A multilevel approach. Computers, Environment and Urban Systems 79:101371
• Tranos, E., T. Kitsos, and R. Ortega-Argilés, R. 2020 Digital economy in the UK: Regional productivity effects of early adoption. Forthcoming

Our web data

1. Geoindex: a subset of the .uk archived webpages which contain a UK postcode
   • circa 0.5 billion URLs with valid UK postcodes
   • 20080509162138/http://www.example_website_1.co.uk/contact_us IG8 8HD
2. Hyperlinks
   • http://www.example_website_1.co.uk | http://www.example_website_2.co.uk | 3
   • much larger pool, only part is geolocated

Modelling strategy

\[trade_{ijt} = hyperlinks_{ijt} + distance_{ij} + \\ pop.density_{it} + pop.density_{it} + empl_{it} + empl_{jt} + e_{ijt}\]

• Avoid overfit
• Predict inter-regional trade flows using Random Forests (RF)
• Widely used both for regression and classification problems (Biau 2012)
• Can handle skewed distributions and outliers
• Effectively model non-linear relationships
• Small number of hyperparameters that need to be tuned, low sensitivity
• Short training time (Caruana, Karampatziakis, and Yessenalina 2008; Liaw, Wiener, and others 2002; Yan, Liu, and Zhao 2020)

Modelling strategy: Random Forests

• RF is a tree-based ensemble learning method (Breiman 2001)
• Creates random samples of the training data, which are then used to grow an equivalent number of regression trees to predict the dependent variable
• Decision trees are trained in parallel on their own sample of the training data created with bootstrapping
• To make a prediction for regression problems, RF average the predictions of all decision trees

Modelling strategy: rolling forecasting

• Train RF models on data from years \(t\) and \(t + 1\) to increase the size of the training dataset
• 10-fold cross validation
• Predict unseen data from year \(t + 2\)
• No data pooling to maintain their temporal structure both for methodological and conceptual reasons.
• No data leakage

Modelling strategy: predictive performance

\[\begin{align} R^2 = 1 - \frac{\sum_{k} (y_{k} - \hat{y_{k}})^2} {\sum_{k} (y_{k} - \overline{y_{k}})^2} \label{eq:rsquared} \end{align}\]

\[\begin{align} MAE = \frac{1}{N} \sum_{k = 1}^{N} |\hat{y_{k}} - y_{k}| \label{eq:mae} \end{align}\]

\[\begin{align} RMSE = \sqrt{\frac{\sum_{k = 1}^{N} (\hat{y_{k}} - y_{k})^2} {N}} \label{eq:rmse} \end{align}\]

• Larger errors carry more weight for \(RMSE\)

Data cleaning

• All the archived .uk webpages
• Archived during 2000-2010
• Commercial webpages (.co.uk)
• From webpages to websites: http://www.website1.co.uk/webpage1 and http://www.website1.co.uk/webpage2 are part of the http://www.website1.co.uk
• 1 vs. multuple postcodes in a website

Unique postcodes frequencies, 2000

• Websites with a large number of postcodes: e.g. directories, real estate websites
• Websites with a unique location \(\Leftarrow\) The focus of analysis for now

Directory website with a lot of postcodes

Website with a unique postcode in London

Interregional trade flows

Interregional hyperlinks

Scatter plots of trade vs. hyperlinks

Correlations with interregional trade

Modelling strategy

\[trade_{ijt} = hyperlinks_{ijt} + distance_{ij} + \\ pop.density_{it} + pop.density_{it} + empl_{it} + empl_{jt} + e_{ijt}\]

• Rolling forecasting
• Train RF models on data from years \(t\) and \(t + 1\)
• 10-fold cross validation
• Predict unseen data from year \(t + 2\)

Train on year t and t + 1

summary(fit.model.all.res)

Feature importance

Test on t + 2

Test on t + 2

Alternative models: hyperlinks no better than distance

Conclusions

• Interregional trade is difficult to capture
• Current state-of-the art: distance decay
• Interregional trade leaves digital paper trail
• Prediction framework
• Spatially and industrially disaggregated approaches
• Opportunity for local authorities to estimate their export base / specialisations
• Next steps: sectoral trade