AFTAs 2016: Best Middle-Office Initiative: Data Management, Reconciliation and Clearing—Indus Valley Partners

middle-office-initiative-data-management-reconciliation-and-clearing-indus-valley-partners

For the first time in the history of the American Financial Technology Awards there are vendor categories on offer, and it seems somewhat fitting that Indus Valley Partners (IVP), winner of the best buy-side reconciliation platform/service in the 2015 Buy-Side Technology Awards, is again in the winners’ circle.

And if all the industry chatter is anything to go by, 2017 might well turn out the be the year that machine learning and artificial intelligence-two terms used interchangeably for ostensibly the same class of technologies-make a measurable impact across the capital markets. There has been lots of talk and speculation about how these technologies are likely to shape the industry, and if ever one was looking for an example of what that impact might look like in practice, one need look no further than IVP and its outstanding Robo Reconciliation offering.

The New York-headquartered firm has built a proprietary AI engine into IVP Recon, its middle-office reconciliation platform that supports $590 billion in assets under management across 50 clients and 108 counterparties, which it claims takes the post-trade function into a new era of machine learning and big data.

According to IVP, the AI capability learns how to identify breaks and flags non-normal activity and automatically suggests resolutions. This moves beyond rudimentary rules-based algorithms and into the next generation of machine-learning tools that recognize, react to and resolve issues in patterns within data in real time. The scope for efficiencies in processing times and streamlining processes is significant.

IVP Robo Recon enables file streams from specific counterparties to be identified and then runs proprietary matching algorithms to target breaks. Once these have been identified, an auto-reconciliation process will be invoked to resolve them, while an interactive heatmap will display the results and be continuously updated to reflect ongoing activity.

IVP Robo Recon has the ability to set up any new reconciliation from raw data files in under five minutes by leveraging genetic algorithms and natural-language processing to automatically decipher and auto-map files. Alongside a “suggestion engine” that learns break-resolution patterns over time, automatically suggesting matches and providing one-click acceptance/rejection, the entire middle-office reconciliation workflow becomes self-learning.

IVP Robo Recon enables file streams from specific counterparties to be identified and then runs proprietary matching algorithms to target breaks. Once these have been identified, an auto-reconciliation process will be invoked to resolve them, while an interactive heatmap will display the results and be continuously updated to reflect ongoing activity.

The reconciliations space—a function critical to the efficient running of all capital markets firms even though it does not provide them with a direct competitive advantage—has been primed for an initiative like IVP Robo Recon for a while now. It will be interesting to note how the rest of the industry reacts to IVP’s bold AI move.

  • LinkedIn  
  • Save this article
  • Print this page  

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact [email protected] or view our subscription options here: http://subscriptions.waterstechnology.com/subscribe

You are currently unable to copy this content. Please contact [email protected] to find out more.

You need to sign in to use this feature. If you don’t have a WatersTechnology account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: