Using Palantir to implement the TARP

January 22nd, 2009 | AlexF

We talk often with our contacts in finance and intelligence, and an increasingly common subject is the U.S. Government’s Troubled Assets Relief Program (TARP — part of the Treasury Department). Our friends see the large problems facing the TARP and the Federal Reserve, and have been asking how our technology can help.

Some of the problems are out of our hands, but many others are solvable with the proper analytics. Taking a closer look at the task before TARP, we noticed that many challenges mirror those facing the intelligence community:

Entity and relationship data is scattered across many sources in a wide variety of formats; some are structured, some are unstructured.
Entity structure and relationships are not always known upfront, so the solution must adapt to new data structures on the fly.
It is costly, time-consuming, and unnecessary to impose one structure on the entire industry.
Scalability is a must: millions of mortgages have been securitized into hundreds of thousands of entities.
Sensitive, private data requires sophisticated access control and knowledge management — understanding who is accessing which data, what the organization knows, when it was known, and how it was discovered.
Specialists from different fields and geographical regions must be able to collaborate effectively.

Palantir’s technology already solves these problems for the intelligence community. Our dynamic ontology makes it easy to import TARP data and entities, so we’ve created a short video using Palantir that shows the power of our approach. We analyze individual mortgage loans, mortgage-backed securities comprising these loans, and institutions holding tranches of the securities:

For more detail on the similarities, click the link to see a detailed breakdown of intelligence vs. TARP workflows.

Workflows

The types of questions the TARP and the Federal Reserve need to answer successfully are similar to those in the intelligence community. In essence, TARP is performing the sort of analysis performed at intelligence agencies: making sense of large amounts of data to create a coherent and accurate picture of the world. TARP is performing analysis on domestic financial data rather than global intelligence data, and using those insights to craft solutions to the current financial crisis. Our breakdown and comparison of the different aspects of the workflows along the same broad lines looks like this:

Strategic: Mission Planning and Policy Design

Classical Intel	TARP
How have nation-states’ methods of supporting terrorist organizations evolved over the last 10 years? How has deploying more troops to specific hot spots affected the overall level of violence in those areas? What types of surrogate forces should be recruited and trained to support missions across theater?	Which institutions will require intervention and what markets are they most exposed to? Which geographical regions and communities most urgently need federal support? Which asset classes and types of mortgages should be purchased first?

Operational: Asset Class Level Management and Tactical Planning

Classical Intel	TARP
What known terrorist cells are present in a given region and what is the most effective way to combat them based on their ideology? What are the various touch points for these organizations’ logistical networks and what measures have proved effective in dismantling them in the past? How can we measure the efficacy of various actions against the objectives through observable phenomena, including communications, financial information, and human source collection?	What are the characteristics of loans most likely to default in Florida and what is the best strategy for preventing foreclosure? Which players were most involved in originating commercial loans in Florida? What tactics were used to justify appraisals, and how can these tactics be adjusted for? What policy for mortgage adjustment yields the fairest outcome in Palm Springs, Florida?

Classical Intel

TARP

What known terrorist cells are present in a given region and what is the most effective way to combat them based on their ideology?
What are the various touch points for these organizations’ logistical networks and what measures have proved effective in dismantling them in the past?
How can we measure the efficacy of various actions against the objectives through observable phenomena, including communications, financial information, and human source collection?

What are the characteristics of loans most likely to default in Florida and what is the best strategy for preventing foreclosure?
Which players were most involved in originating commercial loans in Florida? What tactics were used to justify appraisals, and how can these tactics be adjusted for?
What policy for mortgage adjustment yields the fairest outcome in Palm Springs, Florida?

Tactical: Asset Targeting, Program Implementation, Specific Action Support.

Classical Intel	TARP
What times are most likely for a patrol to be attacked in this neighborhood? What methods are used during the day vs. the night? Which repercussions are likely to occur as result of arresting a specific individual? What organizations is this person associated with and who is likely to retaliate? Which human sources are likely to be able to provide actionable intelligence to move against the time sensitive target?	What is the notional size of credit default swaps written on this tranche of this commercial MBS? Which banks are the major holders, and how have their assets ratings changed? Who originated this loan, and how close are the comparables used in the due-diligence report? Who is the servicer for this mortgage, and which branch needs to be contacted if the size of the loan is adjusted down?

Classical Intel

TARP

What times are most likely for a patrol to be attacked in this neighborhood? What methods are used during the day vs. the night?
Which repercussions are likely to occur as result of arresting a specific individual? What organizations is this person associated with and who is likely to retaliate?
Which human sources are likely to be able to provide actionable intelligence to move against the time sensitive target?

What is the notional size of credit default swaps written on this tranche of this commercial MBS? Which banks are the major holders, and how have their assets ratings changed?
Who originated this loan, and how close are the comparables used in the due-diligence report?
Who is the servicer for this mortgage, and which branch needs to be contacted if the size of the loan is adjusted down?

Mission

We believe that the TARP’s success is critical to the global financial markets and the health of our nation. We’ve said from the beginning that our mission is to change the way the world approaches data, and today Palantir is a technology leader in both intelligence and finance. As we begin work on this new challenge we’re excited to be making a difference where it’s needed most.

Posted in palantir, problemspace - finance, problemspace-government | 3 Comments »

Digg This |

del.icio.us

3 Responses to “Using Palantir to implement the TARP”

Andrew Coleson Says:

Very cool video and comparison. It’d be helpful if you could upload a high-quality Youtube video so that more of the text is legible, but otherwise a nice demonstration of using Palantir!

January 22nd, 2009 at 10:15 pm
Akash Says:

Hey Andrew,

We’ll try to get a higher quality vid up shortly. In the interim, you can see one here:
http://www.palantirtech.com/government/videos/mbs/

Thanks,
-Aki

January 22nd, 2009 at 11:30 pm
Ari Says:

Updated post to include link to higher-resolution video.

January 23rd, 2009 at 3:34 pm