News-implied economic networks
News-implied economic networks
Embedded Files
This website provides data for networks of financial assets extracted from financial news reporting. The data sets are based on a series of academic research papers developed by Prof. Gustavo Schwenkler at Santa Clara University.
Firm links
Firm links
Time span: January 1981 through December 2025.
Sources: New York Times, as the following as covered in the News On the Web (NOW) corpus: Barron’s, Bloomberg, Business Insider, CNBC, Forbes, Fortune, MarketWatch, Reuters, and The Wall Street Journal.
Frequency: Monthly.
Link categories: Credit, equity, leadership, peer, production, and other.
Network Data: Google Drive folder.
Training algorithms & data: Google Drive folder.
Related papers:
"Forecasting with News-Implied Firm Networks" (with V. Hilt). Online Appendix. Trading strategy and directional forecast results + news-implied connectivity metrics.
"News-Implied Production Networks and Aggregate Output" (with H. Zheng). Online Appendix. Codes.
These data contain labeled firm links between firms as reported by financial news. The links are categorized as credit, equity, leadership, peer, production, and other links. The data set contains the following monthly files (where YYYY-MM stands for the corresponding month and TYPE stands for the type of network):
news_entities_YYYY-MM.csv (Firm mentions in a given month)
news_network_TYPE_YYYY-MM.png (Estimated network for given type in given month)
For details, see the Online Appendix.
Crypto peer links
Crypto peer links
Time span: October 1, 2017, through November 30, 2020.
Source: Cryptocompare.
Frequency: Weekly.
Link types: Peer.
Data: Google Drive folder.
Related papers:
"News-Driven Peer Co-Movement in Crypto Markets" (with H. Zheng). Online Appendix.
These data contain competitive links between cryptocurrencies as reported by Cryptocompare. The data set contains the following files:
crypto_peers_training_sentences.csv: training data for deep learning classification model.
crypto_peers_all_link_sentences.csv: output of classification model containing all sentences that describe peer relationships between cryptocurrencies.
crypto_peers_weekly_peer_weekly_network.csv: weekly adjecency matrix for crypto peer network.
crypto_peers_exogenous_endogenous.xlsx: file characterizing shock events as endogenous or exogenous.
In addition, the folder also contains codes that were used to: 1) scrape online news articles, 2) extract crypto mentions from online news articles, and 3) label sentences mentioning two cryptos as describing a competitive or non-competitive relationship.
Page updated
Google Sites
Report abuse