Insights, Technology, Use Cases


Since data resides in various systems, data mapping helps bridge the gap between two systems, so that when data is moved from a source, it remains highly accurate and usable at the destination.

For any financial institution, operational risk management is critical. Prior to analysing operational risk data, organisations must map data to homogenise them in a way that makes them available and accessible to risk professionals.

The amount of data and sources has increased rapidly. Presently, operational risk data consists of operational risk loss data with other data sources, including transaction data, non-transaction data (e.g., human resources, compliance), and external data (e.g., social media, customer complaints). These datasets provide millions of data combinations. Furthermore, every data source can define similar data points in different ways. As a result, the process of data mapping has become extremely complex, needing highly automated tools to make it feasible for large data sets.


With EvoML, financial institutions can automatically build models to automate data mapping. By combining various data sources into one single and trusted database, AI-powered data mapping can help classify large amounts of risk data based on custom taxonomy. AI can automatically transform data from various sources into a standard format defined by risk professionals. AI can also recognise errors such as duplications or missing values and improve data quality. AI can then automatically fill in these transformed and improved data into target destination, following the standard data maps. In addition to matching data fields and attributes, AI can also describe the contents in a data source, enabling risk professionals to better understand their data.


  • • Faster Mapping ProcessManual data mapping is time-consuming. With EvoML, financial institutions can quickly build AI to enable a fully automated process, accelerating mapping time while easily scaling.
  • • Accurate Mapping ResultEvoML’s Evolutionary Optimisation feature enables financial institutions to build highly accurate AI models that can quickly adapt to new changes, avoiding human errors.
  • • Ready for advanced analyticsAI-powered data mapping provides a holistic view of risk data. This can help financial institutions uncover hidden risk insights in time, prevent unpredictable outcomes and reduce operational losses and capital impacts.
  • • Cost SavingAutomated process avoids the need of hiring a huge team to manually map data.

EvoML can be used by:

  • • Operational Risk Team
  • • Tech Experts in Data Management Platforms

Footnote 1: The Basel Committee on Banking Supervision (BCBS) is the primary global standard setter for the prudential regulation of banks and provides a forum for regular cooperation on banking supervisory matters.