{"id":2663,"date":"2015-11-22T20:49:23","date_gmt":"2015-11-23T01:49:23","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-digit\/submission\/how-forter-is-fighting-online-fraud\/"},"modified":"2015-11-22T20:49:47","modified_gmt":"2015-11-23T01:49:47","slug":"how-forter-is-fighting-online-fraud","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/how-forter-is-fighting-online-fraud\/","title":{"rendered":"How Forter is Fighting Online Fraud"},"content":{"rendered":"

Forter developed a fraud prevention solution for online merchants. Forter\u2019s technology gives merchants an answer on each payment transaction whether it is fraudulent or not in real time. They use cyber intelligence and behavioral data analysis in order to create fraud detection technology.<\/p>\n

Today if a merchants delivers a product to fraudulent order they lose on the product and the money. Because banks often look for reimbursement from the merchants, since they were the ones who approved the fraudulent transaction. Moreover, above certain amount of fraudulent transactions payment processors firms could blacklist the business, which means that businesses would find it very difficult to find another payment provider. Obviously, big corporations have more negotiation power when resolving fraud with banks and they also have more resources invest in securities. On the other hand, online frauds can be devastating for small businesses.<\/p>\n

Based on CyberSource<\/a>, retailer\u2019s revenue lost to online fraud in 2012 was $3.5 billion. In order to protect themselves, merchants invest resources to minimize the credit card fraud. For example: they verify the validity of the credit cards, call customers to verify their identities and look for suspicious behavior. The reviews are mostly manual, and based on a simple rule based approach.<\/p>\n

Forter offers automated platform that gives a decision within less than one second on whether a transaction is fraudulent.<\/p>\n

Forter creates value in several areas:<\/p>\n

    \n
  1. Businesses have increased sales from international markets. With ruled based solutions, countries such as Nigeria and Indonesia were blacklisted. These countries are known as common source of fraud. With blacklists, it caused anyone in these countries to be blocked from purchasing online. Forter\u2019s machine learning algorithm analyzes online shopping behaviors and opens up sales in these countries.<\/li>\n
  2. Improved customers satisfaction and fewer lost customers due to \u201cfalse\u2013positive\u201d sales that were declined. A rule based system is very risk averse which creates a situation where sales of legitimate customers were declined. Sometime customer have to wait a few days till their transaction is approved, which can create a lot of frustration and loss of sales. Forter\u2019s system give real time instant approval, by that allowing customers to purchase instantly.<\/li>\n
  3. Reduce costs related to time spent on reviewing the transactions manually. Organizations spent much less time on transaction reviews and invest same resources to customer service and sales.<\/li>\n
  4. In case of bad transaction was approved, Forter takes full responsibility on reimbursing the business within three business days. This also protects merchants from being blacklisted with payment providers firms.<\/li>\n<\/ol>\n

    Forter captures value capture per transaction that is approved. Forter ideology is that they are going to make money only if the merchandiser makes money too. This is to align their incentives with the customers\u2019 incentives. Forter charges between 0.5% and 1.5% per transaction.<\/p>\n

    Forrester <\/a>study finds that Forter\u2019s customers report on average increase of 8% number of transactions approved. This means more sales for the business.<\/p>\n

    Forter\u2019s technology is a machine learning solution that examines each transaction individually. It evaluates the transaction validity based on customer\u2019s behavior such as: mouse tracking while shopping, time spent on reading the reviews, money spent on insurance. For example: Forter learned that in fraudulent transactions customers spent less time on reading the reviews and comparing the prices. Also, they are less likely to purchase insurance for products. Using behavioral analysis, the system is able to identify fraudsters before they reach checkout.<\/p>\n

    Forter developed machine learning capability in three steps:<\/p>\n