Our client has built an ecosystem of blockchain-related solutions to better understand crypto assets. These solutions are an aggregation of alternative data that our clients sell to asset managers and hedge and investment funds.
- Our client collects data from over 100 alternative data sources that may have some predictive value to their customers.
- This non-market data can often give traders a strategic edge due to novel and uncorrelated alpha. However, mining such datasets is hugely time-consuming and resource-hungry.
- Before proceeding with various alpha hypotheses, it is essential to test their usefulness. There is an additional challenge regarding the nature of alternative data; building features is a primary step when using unstructured data sources.
- Combining business analytics and data science skills, Digital Bricks created numerous expert and mathematical custom variables modelled with various algorithms.
- Digital Bricks reverse-engineered these models and studied the most important features. In this way, we identified data sources that have predictive value.
- The transparent value model that shows how each separate data source and their combination affect trading decisions (5-10% predictive accuracy boost) was developed.
- Improved value propositions for the customers who can now acquire trusted and verified alpha features and trading signals.
People. products. power.