AI could transform open source intelligence in the developing world – C4ISRNet

In developed nations, there is a rich trove of data that the intelligence community can and does mine.

Valuable information can be pulled from media reports, public financial information and social media posts. Websites track user activity, and smartphones are constantly gobbling up information about their users, from geolocations to search histories and more. By using artificial intelligence tools, analysts are able to make sense of this torrent of publicly available data and turn it into usable open-source intelligence, known as OSINT.

But not every part of the world produces that vast torrent of data.

That exists in a very small handful of places throughout the world where that doesnt existbasically every developing economy, said Ben Leo, chief executive of FRAYM, a geospatial data and analytics company. [In developing economies] you are not able to get a comprehensive and representative picture of what the population looks like through the same types of techniques that are being used in the U.S.

The U.S. military and intelligence community are increasingly interested in leveraging OSINT for predictive analysisafter all, properly collected and processed OSINT can help warn regional commanders of upcoming political protests, political violence, extremist attacks or other kinds of security related events could take place, said Leo. Notably, the Army awarded BAE Systems a $437 million task order for open source intelligence support in October.

Of course, in order to create usable and reliable OSINT, companies like FRAYM will need to create data rich analysis in data poor areas.

What we do is we gobble up the very high quality, underutilized datasets that are out there. We bring in additional public datasets and we bring them all together using our AI/ML algorithms to produce this hyper local data at scale, said Leo.

The company takes geotagged household data and feeds that into its machine learning algorithm, and from there it can then produce data down to a 1 km x 1 km grid level across dozens of characteristics, such as religion, ethnicity, language, age, education access, electricity, media consumption and more.

Sign up for the C4ISRNET newsletter about future battlefield technologies.

(please select a country) United States United Kingdom Afghanistan Albania Algeria American Samoa Andorra Angola Anguilla Antarctica Antigua and Barbuda Argentina Armenia Aruba Australia Austria Azerbaijan Bahamas Bahrain Bangladesh Barbados Belarus Belgium Belize Benin Bermuda Bhutan Bolivia Bosnia and Herzegovina Botswana Bouvet Island Brazil British Indian Ocean Territory Brunei Darussalam Bulgaria Burkina Faso Burundi Cambodia Cameroon Canada Cape Verde Cayman Islands Central African Republic Chad Chile China Christmas Island Cocos (Keeling) Islands Colombia Comoros Congo Congo, The Democratic Republic of The Cook Islands Costa Rica Cote D'ivoire Croatia Cuba Cyprus Czech Republic Denmark Djibouti Dominica Dominican Republic Ecuador Egypt El Salvador Equatorial Guinea Eritrea Estonia Ethiopia Falkland Islands (Malvinas) Faroe Islands Fiji Finland France French Guiana French Polynesia French Southern Territories Gabon Gambia Georgia Germany Ghana Gibraltar Greece Greenland Grenada Guadeloupe Guam Guatemala Guinea Guinea-bissau Guyana Haiti Heard Island and Mcdonald Islands Holy See (Vatican City State) Honduras Hong Kong Hungary Iceland India Indonesia Iran, Islamic Republic of Iraq Ireland Israel Italy Jamaica Japan Jordan Kazakhstan Kenya Kiribati Korea, Democratic People's Republic of Korea, Republic of Kuwait Kyrgyzstan Lao People's Democratic Republic Latvia Lebanon Lesotho Liberia Libyan Arab Jamahiriya Liechtenstein Lithuania Luxembourg Macao Macedonia, The Former Yugoslav Republic of Madagascar Malawi Malaysia Maldives Mali Malta Marshall Islands Martinique Mauritania Mauritius Mayotte Mexico Micronesia, Federated States of Moldova, Republic of Monaco Mongolia Montserrat Morocco Mozambique Myanmar Namibia Nauru Nepal Netherlands Netherlands Antilles New Caledonia New Zealand Nicaragua Niger Nigeria Niue Norfolk Island Northern Mariana Islands Norway Oman Pakistan Palau Palestinian Territory, Occupied Panama Papua New Guinea Paraguay Peru Philippines Pitcairn Poland Portugal Puerto Rico Qatar Reunion Romania Russian Federation Rwanda Saint Helena Saint Kitts and Nevis Saint Lucia Saint Pierre and Miquelon Saint Vincent and The Grenadines Samoa San Marino Sao Tome and Principe Saudi Arabia Senegal Serbia and Montenegro Seychelles Sierra Leone Singapore Slovakia Slovenia Solomon Islands Somalia South Africa South Georgia and The South Sandwich Islands Spain Sri Lanka Sudan Suriname Svalbard and Jan Mayen Swaziland Sweden Switzerland Syrian Arab Republic Taiwan, Province of China Tajikistan Tanzania, United Republic of Thailand Timor-leste Togo Tokelau Tonga Trinidad and Tobago Tunisia Turkey Turkmenistan Turks and Caicos Islands Tuvalu Uganda Ukraine United Arab Emirates United Kingdom United States United States Minor Outlying Islands Uruguay Uzbekistan Vanuatu Venezuela Viet Nam Virgin Islands, British Virgin Islands, U.S. Wallis and Futuna Western Sahara Yemen Zambia Zimbabwe

Subscribe

By giving us your email, you are opting in to the C4ISRNET Daily Brief.

FRAYM has provided its services to the U.S. government in the past, but company officials declined to name any agencies they were currently working with or would like to work with.

In the past, he explained, there were really only two ways to make predictions in data poor areas. First, analysts could monitor events through social media. While that can help commanders understand the situation on the ground, it has very limited predictive power.

Previously, youve been stuck in two worlds, said Leo. Youve either been stuck in a world where Im going to monitor social media and try to apply natural language processing or other tools that will aggregate and make sense of that data so that I can try to identify a tipping point. When is the chatter getting to a certain point where it feels like something important is happening in a particular city? Its too late at that point. That might be helpful for basic situational awareness, but that is not nearly as helpful or powerful for a practitioner or combatant commander than getting way left of boom.

When is the chatter getting to a certain point where it feels like something important is happening in a particular city? Its too late at that point. That might be helpful for basic situational awareness, but that is not nearly as helpful or powerful for a practitioner or combatant commander than getting way left of boom, he explained.

The other method was to basically plot out how and where events have unfolded in the past and try to find correlations that can predict future events. That, too, is very limited.

But with access to proprietary data the U.S. government does not have, Leo says his company has been able to create a unique source of OSINT for data starved areas.

This is the first time that this kind of very comprehensive and rich data has been brought to bear in developing markets. Basically, anywhere where there is not a data identity-centric ecosystem, FRAYM brings a tremendous set of powerful solutions to the marketplace, said Leo.

See the original post here:

AI could transform open source intelligence in the developing world - C4ISRNet