{"id":16226,"date":"2018-06-12T14:20:59","date_gmt":"2018-06-12T08:50:59","guid":{"rendered":"https:\/\/www.subex.com\/?p=16226"},"modified":"2018-06-12T14:20:59","modified_gmt":"2018-06-12T08:50:59","slug":"why-artificial-intelligence-powered-fraud-management","status":"publish","type":"post","link":"https:\/\/dev.enki.studio\/test\/?p=16226","title":{"rendered":"Why Artificial Intelligence Powered Fraud Management"},"content":{"rendered":"<p>Artificial Intelligence (AI) is not new and it has been around for decades. However, with the advent of big data and distributed computing that is available today, it is possible to realize the true potential of AI. From what started as an\u00a0interesting story line in\u00a0SCI-FI\u00a0movies to programs like Alpha-Go which has been beating humans, AI has been evolving. AI also has branched out into multiple sub categories such as Machine Learning, Deep Learning, Re-enforcement learning etc.<\/p>\n<p>An effective Fraud Management (FM) strategy includes 3 important pillars: <strong>Detect, Investigate &amp; Protect<\/strong>. We believe AI can positively influence all the\u00a03 pillars of fraud management, from\u00a0reducing false positives to helping in mining root cause analysis to creating enhanced customer experience in protection.<\/p>\n<p>In this post I would like to look at the starting pillar of the Fraud Management strategy \u2013 \u201cDetection\u201d and look at AI&#8217;s influence in this very important step. A traditional approach to <strong><a href=\"https:\/\/dev.enki.studio\/test\/fraud-management\/\">Fraud detection<\/a><\/strong> has been through Rule Engines which could be:<\/p>\n<ul>\n<li>If-Else Conditions<\/li>\n<li>Thresholds<\/li>\n<li>Expressions<\/li>\n<li>Evaluating Data Patterns<\/li>\n<\/ul>\n<p>These are widely known as deterministic solutions where an event triggers an action. The biggest pros and cons with this approach is that human intervention is needed to feed the logic.<\/p>\n<p><em>For\u00a0eg: for a threshold based detection humans have to feed the rule engine that count of records above a certain threshold is suspicious.<\/em><\/p>\n<p>Following diagrams shows how this looks like<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/rule-engine.jpg\" alt=\"rule-engine\" width=\"624\" height=\"239\" \/><\/p>\n<p>After looking at the diagram above an important question arises, should this threshold value be a straight line or can it bend based on how data behaves. Now there are ways for rule engine to behave like mentioned in the diagram,<\/p>\n<div class=\"col-md-6\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/variable-threshold.jpg\" alt=\"variable-threshold\" width=\"337\" height=\"250\" \/><\/div>\n<div class=\"col-md-6\">\n<p>for\u00a0eg, instead of having a single rule lets have multiple rules<\/p>\n<ul>\n<li>Per Customer Category<\/li>\n<li>Per Destination<\/li>\n<li>Per Age of Customers<\/li>\n<\/ul>\n<p>And multiply that with other dimensions in data which are<\/p>\n<ul>\n<li>Phone Number<\/li>\n<li>Caller Number<\/li>\n<li>Called Number<\/li>\n<li>Country Code<\/li>\n<\/ul>\n<p>And multiple that with other set of measures per dimensions<\/p>\n<ul>\n<li>Count<\/li>\n<li>Duration<\/li>\n<li>Value<\/li>\n<\/ul>\n<p>And throw an additional billion volumes at the datasets<\/p>\n<\/div>\n<div class=\"col-md-6\">Quickly FM teams ends up with something like this<br \/>\n<img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/AI-Blog1.png\" alt=\"AI Blog1\" width=\"476\" height=\"250\" \/><\/div>\n<div class=\"col-md-6\">\n<p>But what they wanted or dreamt was this<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/AI-Blog2.png\" alt=\"AI Blog2\" width=\"476\" height=\"250\" \/><\/p>\n<\/div>\n<p>Now I am not saying FM teams are not skilled enough to fly, but a fraud team in a modern Digital Service provider should be more focused on other important factors.<\/p>\n<div class=\"col-md-6\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/machine-learning.jpg\" alt=\"machine-learning\" width=\"210\" height=\"176\" \/><\/div>\n<div class=\"col-md-6\">So, let&#8217;s look at how a very evolved class of Artificial Intelligence known as Machine Learning looks at this problem statement. Rather than humans feeding domain information or thresholds, Machine Learning Algorithms mine data from historic fraudulent behaviors and create models. These models are then used to evaluate real production datasets to score whether they certain activity is fraud or not. An advantage is that these models are very good at looking the datasets from multiple dimensions and measures at the same time and concluding whether event is fraud or not.<\/div>\n<div class=\"col-md-6\">\n<p>This approach thereby helps in achieving multiple KPI&#8217;s of fraud management teams there by increasing efficiency.<\/p>\n<ul>\n<li><strong>Higher Accuracy<\/strong> &#8211; Because AI can learn and adapt to Business scenarios faster, AI can significantly increase True Positive ratio<\/li>\n<li><strong>Reduced time to detect<\/strong> &#8211; How fast a fraud event can be detected<\/li>\n<li><strong>Self-Learning<\/strong> &#8211; How over a period changing business scenarios and seasonality in data can be adopted to Fraud detection<\/li>\n<li><a href=\"https:\/\/dev.enki.studio\/test\/fraud-management\/signalling-for-fraud\/\"><strong>Fraud Intelligence<\/strong><\/a>&#8211; How customer or any other entity\u00a0behaviors can be learnt and categorized for better\u00a0fraud detection<\/li>\n<li><strong>Proactiveness<\/strong> &#8211; Ability to mine for unknown patterns not seen in the data earlier<\/li>\n<\/ul>\n<\/div>\n<div class=\"col-md-6\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full img-responsive\" src=\"https:\/\/dev.enki.studio\/test\/wp-content\/uploads\/2018\/06\/FM-4.jpg\" alt=\"FM-4\" width=\"256\" height=\"236\" \/><\/div>\n<div class=\"row\">\n<div class=\"col-md-12\">Application of Artificial Intelligence has its own significant challenges and requires a new frame of thought, however looking at the Data Tsunami that has hit the fraud management teams, it looks an <strong><a href=\"https:\/\/dev.enki.studio\/test\/fraud-management\/\">AI pro approach would only help Fraud Management teams to scale further<\/a><\/strong>.<\/div>\n<\/div>\n<p style=\"text-align: center; font-size: 22px;\"><span style=\"color: #00a1d6;\">To learn more about how AI\/ML would transform the Fraud Management Systems, Join us on our two-part series of \u201cAI Master Class for Fraud Management\u201d to familiarize yourself with AI\/ML through a live demo.<\/span><\/p>\n<p style=\"text-align: center;\"><a class=\"cta-btn\" href=\"https:\/\/info.subex.com\/ai-master-class-for-fraud-management\">Register Now<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Artificial Intelligence (AI) is not new and it has been around for decades. However, with the advent of big data and distributed computing that is available today, it is possible to realize the true potential of AI. From what started as an\u00a0interesting story line in\u00a0SCI-FI\u00a0movies to programs like Alpha-Go which has been beating humans, AI [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":24082,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[28],"tags":[220,221,222,27,223,29,224],"class_list":["post-16226","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-fraud-management","tag-artificial-intelligence","tag-deep-learning","tag-fm","tag-fraud","tag-fraud-dectection","tag-fraud-management","tag-machine-learning"],"acf":[],"_links":{"self":[{"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/posts\/16226","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=16226"}],"version-history":[{"count":0,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/posts\/16226\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=\/wp\/v2\/media\/24082"}],"wp:attachment":[{"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16226"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16226"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dev.enki.studio\/test\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16226"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}