{"id":100,"date":"2019-05-02T04:08:36","date_gmt":"2019-05-02T04:08:36","guid":{"rendered":"https:\/\/cusjc.ca\/mrp\/dataandthedisplaced\/?page_id=100"},"modified":"2019-06-05T19:41:15","modified_gmt":"2019-06-05T19:41:15","slug":"predicting-how-a-crisis-unfolds","status":"publish","type":"page","link":"https:\/\/cusjc.ca\/mrp\/dataandthedisplaced\/predicting-how-a-crisis-unfolds\/","title":{"rendered":"Predicting how a crisis unfolds"},"content":{"rendered":"

[et_pb_section bb_built=”1″ fullwidth=”on” _builder_version=”3.22.5″ background_image=”https:\/\/cusjc.ca\/mrp\/dataandthedisplaced\/wp-content\/uploads\/sites\/20\/2019\/04\/IMG_8001.jpg” parallax=”on” min_height=”816px” custom_padding=”188px||2px|||” next_background_color=”#ffffff”][et_pb_fullwidth_header title=”Predicting how a crisis unfolds” subhead=”Using artificial intelligence in the humanitarian sector has become increasingly popular. Here\u2019s how a predictive form of the technology works and why it could change how the world responds in the aftermath of a crisis. ” content_max_width=”63%” _builder_version=”3.22.5″ title_font=”Jura|600|||||||” title_text_color=”#ffffff” title_font_size=”68px” title_line_height=”1.1em” title_text_shadow_style=”preset2″ title_text_shadow_blur_strength=”0.05em” title_text_shadow_color=”rgba(48,48,48,0.63)” subhead_font=”Georgia||||||||” subhead_text_align=”left” subhead_font_size=”22px” subhead_line_height=”1.4em” subhead_text_shadow_style=”preset2″ subhead_text_shadow_blur_strength=”0.04em” subhead_text_shadow_color=”rgba(0,0,0,0.64)” background_color=”rgba(0,40,150,0)” parallax=”on” min_height=”461px” custom_margin=”||0px|||” custom_padding=”0px|||||” text_shadow_style=”preset2″ \/][\/et_pb_section][et_pb_section bb_built=”1″ _builder_version=”3.22.5″ min_height=”2368px” custom_margin=”-54px|||||” prev_background_color=”#000000″][et_pb_row custom_margin=”-43px|auto||auto||” _builder_version=”3.22.5″ min_height=”910px”][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.22.5″ width=”80%” width_last_edited=”on|desktop” module_alignment=”center”]<\/p>\n

F<\/span>or Rana Novack, a program leader at IBM, everything began with an orthodontist\u2019s appointment. <\/span><\/p>\n

Not her own, but her 15-year-old cousin\u2019s, nearly 10,000 kilometres away in Damascus, Syria. It was 2013, two years into the country\u2019s civil war, and violence was creeping closer to the city where the majority of Novack\u2019s family still lived. The internet would cut out intermittently and keeping in touch with loved ones became sporadic. Late one night that year, from her home in northern Virginia, Novack called her family to beg them to leave. <\/span><\/p>\n

[\/et_pb_text][et_pb_video src=”https:\/\/www.youtube.com\/watch?v=prt2cmXtVuc&t=5s” _builder_version=”3.22.5″ width=”80%” module_alignment=”center” \/][et_pb_text _builder_version=”3.22.5″ width=”80%” module_alignment=”center”]<\/p>\n

It would be two years before Novack\u2019s aunt and her family would leave Syria, along with many of Novack\u2019s other relatives. During that time, she began to wonder: what might happen if data scientists could predict a refugee crisis before it occurred? Why would people leave, how many would flee and where would they go? Novack hypothesized that if governments knew a crisis was coming far enough in advance, they might be better prepared to receive refugees and coordinate a global response. That preparation could open up more opportunities to leave, opportunities her family could have taken before the violence escalated. The idea led Novack and her colleagues at IBM to successfully develop such a tool \u2013 a version of which is planned to make real-life predictions later this year.<\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row custom_padding=”45px|||||” custom_margin=”-40px|auto||auto||” _builder_version=”3.22.5″ min_height=”880px”][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.22.5″ width=”80%” module_alignment=”center” min_height=”833px”]<\/p>\n

Behind a prediction<\/strong><\/span><\/h3>\n

<\/strong><\/span><\/p>\n

It all starts with predictive analytics, a statistical technique that uses existing data, machine learning and artificial intelligence to generate predictions about future events. The technique involves analyzing data and running it through algorithms \u2013 a set of rules that tells a computer what to do \u2013 to create a model. Current data is then fed into the model, which results in a prediction. It\u2019s a form of technology that people interact with every day. Predictive analytics is how variables like humidity and wind direction are used to forecast the weather, how Amazon and Netflix can tell you what you should buy or watch next or how you\u2019re assigned a credit score to determine whether or not you can take out a loan. Companies like Microsoft and IBM have long experimented with the technology, primarily for commercial purposes. Most recently, IBM achieved<\/span> 95 per cent accuracy<\/span><\/a> in identifying employees thinking of quitting a company so bosses could retain them before they decided to leave. <\/span><\/p>\n

In the past several years, tech companies and aid organizations began to realize that the technique could also be applied to the humanitarian sector. This paved the way for new programs like Microsoft\u2019s AI for Humanitarian Action, a five-year, $40 million initiative that launched in \u00a0September 2018. Already, the company says it is using predictive analytics to isolate future famines and disrupt human trafficking networks. <\/span><\/p>\n

There are some clear benefits to predicting massive events before they occur. If a natural disaster was predicted months before it happened, for example, governments and organizations could be proactive instead of reactive, potentially slashing death tolls and mitigating costly damage. Microsoft\u2019s famine model, developed in partnership with the World Bank and a number of other organizations, is hoping to identify food crises that could turn into full-blown famines. The idea is that exposing a crisis before it escalates can save lives and reduce the amount of money spent on aid.<\/span><\/p>\n

A similar goal lies behind forecasting a refugee crisis. In one of the first projects to tackle the issue, IBM joined forces with the Danish Refugee Council (DRC) in 2017, a nonprofit humanitarian organization based out of Copenhagen. Together, their teams are working on a project called Mixed Migration Foresight, or MM4Sight, which is using predictive analytics to determine why displaced people move and where they are likely to go. The intent is not necessarily to stave off a crisis, but to predict how it will unfold to help policymakers organize a response. <\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_image src=”https:\/\/cusjc.ca\/mrp\/dataandthedisplaced\/wp-content\/uploads\/sites\/20\/2019\/05\/Screen-Shot-2019-05-01-at-11.28.16-PM.png” _builder_version=”3.22.5″ width=”80%” module_alignment=”center” \/][et_pb_text _builder_version=”3.22.5″ text_font=”||||||||” text_line_height=”1.4em” width=”80%” module_alignment=”center” custom_margin=”-20px|||||”]<\/p>\n

Novack flips through some of the few photos she has of her family in Syria. Though most of them have since left Damascus, she asked that their identities remain protected to ensure their safety. [Photo \u00a9 Raisa Patel]<\/span><\/em><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.22.5″ width=”80%” module_alignment=”center” custom_margin=”-30px|||||”]<\/p>\n

To get to that point, IBM needed to start experimenting. In 2016, a group of researchers completed the first step: a prototype of a tool that could predict the migration of refugees along a Balkan route spanning Greece to Austria. The tool couldn\u2019t predict a crisis, but it could predict the movements arising from one. Researchers fed a number of indicators into several models, including the UN High Commissioner for Refugees\u2019 registration data and information about policy changes (such as border closures) from news reports. Even weather data like wind speed was included in the model, because it was found that refugees were less likely to migrate in open water on a windy day. <\/span><\/p>\n

<\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”1_2″][et_pb_text _builder_version=”3.22.5″ custom_margin=”-58px|-44px||||” custom_padding=”12px|||111px||”]<\/p>\n

\u201cFor sea-faring refugees arriving in the Greek islands,\u201d a research paper<\/a> on the prototype noted, \u201cfactors such as wind speed were found to be negatively correlated with arrivals over the winter months.\u201d<\/span><\/p>\n

But not all factors were successful at predicting refugee migration, said Rahul Nair, one of the leading researchers at IBM\u2019s lab in Dublin, Ireland involved with the project.<\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_2″][et_pb_text quote_border_color=”#e04b43″ _builder_version=”3.22.5″ text_font=”||||||||” quote_font=”||||||||” quote_text_align=”left” quote_text_color=”#0c71c3″ header_font=”||||||||” min_height=”114px” custom_margin=”-60px|||||” custom_padding=”51px|103px||||”]<\/p>\n

\n

\u201cSometimes you’ll have an intuition that something should work and it doesn’t.” <\/em><\/span><\/h2>\n

\u2013 Rahul Nair<\/em><\/span><\/h2>\n<\/blockquote>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.22.5″ width=”80%” module_alignment=”center” custom_margin=”-55px|||||” custom_padding=”29px|||||”]<\/p>\n

\u201cSometimes you’ll have an intuition that something should work and it doesn’t,\u201d he said. \u201cAn example of that is social media.\u201d<\/span><\/p>\n

Nair and his colleagues studied a sample of Twitter users and hypothesized that \u201cif there is distress at a societal level, the volume of tweets should be correlated with that.\u201d The team thought that refugees might take to social media to describe their circumstances. But they found that between posts being written in different languages and posts containing irrelevant information, there was too much noise. It was left out of the model. <\/span><\/p>\n

After the relevant factors for the model were selected, the team had to verify whether their findings would be correct. To do that, data scientists turned to historical data. <\/span><\/p>\n

\u201cLet’s say you have 20 years worth of data. What you would do is, you would hold five years\u2019 worth of data and you would hide it from the system,\u201d Nair said. <\/span><\/p>\n

\u201cYou would train it on the 15 years of data that you have and then try to predict the values for the period that you hid from the system, knowing fully well what the actual answer was.\u201d<\/span><\/p>\n

After using historical data from October 2015 to January 2016, the team successfully predicted migration volumes at camps along the Balkan route three weeks in advance. The numbers were close to the volumes that had actually been recorded at that point in time. The tool\u2019s success meant that in the real world, it would be possible to predict where refugees or other displaced people would go weeks before they arrived and prepare accordingly.<\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_video src=”https:\/\/youtu.be\/vm2yXjgTPTA” _builder_version=”3.22.5″ width=”80%” module_alignment=”center” custom_margin=”-34px|||||” \/][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.22.5″ width=”80%” module_alignment=”center” custom_margin=”-39px|||||”]<\/p>\n

When the DRC came on board a year later, the data had to be adapted for the specific scenarios they wanted to test: the movement of displaced people out of Ethiopia. Gone were factors like wind speed and in came more relevant indicators like livestock production.<\/span><\/p>\n

\u201cIf there is a drop in livestock productivity, then it suggests some other systemic factors around food security,\u201d explained Nair. \u201cAnd food security is related to the propensity of people to move.\u201d<\/span><\/p>\n

Other important factors were less obvious, like access to tuberculosis treatment. <\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row custom_margin=”-23px|auto||auto||” _builder_version=”3.22.5″][et_pb_column type=”4_4″][et_pb_code _builder_version=”3.22.5″ width=”80%” module_alignment=”center” custom_padding=”0px|||||”]<\/p>\n

<\/div>\n