Machine learning is proving to be a golden opportunity for the financial sector. Financial quantitative records are kept for decades, so the industry is perfectly suited for machine learning. Machine learning is already transforming finance and investment banking for algorithmic trading, stock market predictions, and fraud detection. In economics, machine learning can be used to test economic models and predict citizen behavior to help inform policy makers.
Financial & Economic Datasets for Machine Learning
- Quandl: Quandl is the premier source for financial and economic datasets for investment professionals. Over 250,000 people, including analysts from the world’s top hedge funds, asset managers, and investment banks trust and use Quandl’s data.
- EU Open Data Portal: The EU Open Data Portal gives access to open data published by EU institutions and agencies about the economy, as well as employment, science, environment, and education.
- World Bank Open Data: The World Bank Open Data provides datasets covering population demographics and a huge number of economic and development indicators from across the world.
- IMF Data: The International Monetary Fund publishes data on international finances, debt rates, foreign exchange reserves, commodity prices, and investments.
- Financial Times Market Data: Up-to-date information on financial markets from around the world, including stock price indexes, commodities, and foreign exchange.
- Google Trends: UseGoogle Trends to examine and analyze data on internet search activity and trending news stories around the world.
- American Economic Association (AEA): The AEA is a useful source for finding US macroeconomic data.
- School System Finances: This dataset contains a survey of the finances of school systems in the US.
- US Stock Data: This source provides historical data of US stocks since 2009, updated daily.
- CBOE Volatility Index (VIX): The CBOE Volatility Index (VIX) is a key measure of market expectations of near-term volatility conveyed by S&P. This is a time-series dataset including daily open, close, high and low.
- Dow Jones Weekly Returns: This dataset includes percentage of return that stock has each week, for the purpose of training your algorithm to determine which stock will produce the greatest rate of return in the following week.
- EconData: EconData includes thousands of economic time series, produced by US government agencies and distributed in various formats and media. Data has been organized in a standard, highly efficient, easy-to-use form for personal computers and made publicly available through the site.
- Simfin: Simfin provides data from financial statements uploaded on the SEC website, cleaned and organized in a single document that you can download and work with in a matter of seconds.
- Saudi Arabia Public Debt: This datasets includes data on Saudi Arabia Public Debt for 2005-2017 provided from Saudi Arabian Monetary Agency.
- AssetMarco: AssetMacro is a macroeconomic database that includes 25,000+ indicators for 120+ countries.
- Eurostat Comext: Eurostat Comext includes datasets on trade flows since 1988, organized by commodity.
- CIA World Factbook: The CIA World Factbook includes economic stats of countries, as well as other stats on demographics, geography, communications, and military.
Learn more about machine learning in finance and economics
For more about machine learning uses in finance and economics, we recommend our recent interview with Francesco Corea, who has spent his career so far consulting for financial institutions large and small. Francesco currently uses his research experience in machine learning and PhD in economics to advice AI startups.
Still can’t find what you need?
Lionbridge AI can provide you with a custom machine learning dataset that fits your needs exactly. Our crowdsourcing platform includes over 500,000 qualified contributors, and Lionbridge AI manages the entire process from designing a custom workflow to sourcing qualified workers for your project.