Increased regulatory pressure and the needs of downstream consumers (such as CVA Trading, Quant Strats and Collateral Management) for more granular legal contract data demands better legal documentation management, necessitating, at the very minimum, content management systems that facilitate sophisticated clause searches, data extraction and reporting over large documentation portfolios
- In place solutions do not support searchability and reporting on the clauses contained within legal documentation portfolios and this is an area of active investment across the industry.
- There is a focus on the implementation of sophisticated enterprise search, data extraction/mining and classification tools and a fit-for-purpose content management system for documentation.
- Institutions are moving to the next generation of systems allowing such reporting and removing the need for manual data entry of document terms into downstream systems, such as collateral terms in Credit Support Annexes into a collateral management system.
- Whilst trade confirmations are structured data forms and lend themselves to automation, documentation drafted by legal and documentation teams are unstructured data forms (more free-text and free-format in nature). The technology developed for confirmations management has struggled to be successfully applied to legal documentation.
- Systems and technology exist which can be coupled with business process management tools (i.e. workflow tools) to increase efficiencies and improve operational metrics across the legal documentation process.
- Legal and Documentation departments have typically seen little investment in technology and their technology support teams often lack awareness of the solutions available to implement sophisticated, cost effective solutions.
D2 Legal Technology has made significant investment in these areas and is uniquely positioned to offer related advisory, consultancy and implementation work.
Typically institutions will store executed contracts in image form and the text versions (e.g. MS Word) are either not always retained, or there is not enough confidence that the text version available is the final executed version of the contract (and may be a slightly earlier draft instead).
It is hard to harness the power of machine search and data extraction without therefore converting large portfolios of legacy documentation into machine readable form. This can be done using OCR (Optical Character Recognition) technology. Essentially a system analyses the structure of a document image, divides the pages into paragraphs and tables. These in turn are converted into their constituent lines, words and then characters. At this point, the characters singled out can be compared using sophisticated algorithms against various pattern images. A vast number of probabilistic hypotheses are computed, before presenting the statistically likely character stream.
By utilising certain technology steps and taking into account the language and drafting style typically used in legal contracts, it is possible to convert image-based documents into machine readable form in a cost-effective and accurate manner.
There is ever increasing pressure to improve the quality of the legal documentation to manage risk, managing non-standard clauses appropriately and ensuring appropriate internal authorisations for certain terms. This is balanced by the desire to reduce the cost of documenting these complex transactions and streamline processes. As a result, financial institutions are increasingly embracing document assembly / generation systems, allowing management to obtain key metrics and reports / management dashboards for the documentation process previously only available through very manual data collation exercises.
Financial institutions have struggled in their management of OTC legal documentation as reference data. Terms and values of key data points required by downstream consumers are typically manually extracted multiple times by downstream consumers, often inconsistently and even inaccurately. These are complex documents and downstream consumers such as those modelling collateral for capital purposes and CVA desks require very granular data. In the increasingly regulated world, with new regulations such as Basel III, Dodd-Franks and EMIR, the manual extraction of data points across these legal documentation portfolios is clearly inefficient and costly. Technology assisted systems are required, such that the addition of an extra data point is seamless and does not require a fresh review of the entire document portfolio.