RAVN Systems, experts in Artificial Intelligence, Enterprise Search, Unstructured Big Data and Knowledge Management, announced today the release of RAVN ACE for automated data extraction for ISDA (International Swaps and Derivatives Association) Master Agreements and Credit Support Annexes (CSAs) using Artificial Intelligence.
In response to increasing regulatory requirements, banks and other participants in the OTC derivatives market need to improve their ability to manage counterparty exposures and their corresponding collateral obligations.
Operations departments are now being pushed to their limits with an extensive and time consuming exercise of repapering (re-negotiating) certain existing contracts to reduce unacceptable levels of risk. In turn, this causes significant documentation management problems for users of derivatives.
RAVN’s ground-breaking technology, RAVN ACE, joins elements of Artificial Intelligence and information processing to deliver a platform that can read, interpret, extract and summarise content held within ISDA CSAs and other legal documents. It converts unstructured data into structured output, in a fraction of the time it takes a human – and with a higher degree of accuracy.
RAVN ACE can extract the structure of the agreement, the clauses and sub-clauses, which can be very useful for subsequent re-negotiation purposes. It then further extracts the key definitions from the contract, including collateral data from tabular formats within the credit support annexes. All this data is made available for input to contract or collateral management and margining systems or can simply be provided as an Excel or XML output for analysis.
RAVN ACE also provides an in-context review and preview of the extracted terms to allow reviewing teams to further validate the data in the context of the original agreement.
Even where companies have a good understanding of their contracts and collateral, RAVN ACE can offer an audit service to compare the actual terms in the documents with what has been manually abstracted. Due to the historic nature of some agreements, and from past experience of other manual abstraction exercises, there are likely to be differences.
Having extracted or audited the metadata, RAVN ACE can then analyse the content estate, identify the high credit risk relationships and as a result, quickly and easily scope the size of the repapering exercise required.
By automating the pushing of extracted metadata into a firms collateral management system, institutions will be able to tackle the challenges they face and manage time efficiently, stay regulatory compliant and keep costs to a minimum.