Machine Learning

Machine learning (ML) refers to the development of computer algorithms and statistical models to perform predictions and specific tasks without explicit instructions, rather using inferences and patterns instead. Machine learning is a subset of artificial intelligence and generally falls into two main categories: 1) supervised learning, in which the outcomes are known and labelled in training data sets and 2) unsupervised learning, in which no outcome is known and the goal is to have items self-organized into clusters based on common characteristics or features. Supervised learning uses techniques like neural networks, bayesian models, regression models, statistical models, or a combination thereof. Unsupervised learning uses techniques like k-means clustering and is often used for anomaly detection. Some computer systems have the ability to “learn” or make progressive improvements on a task based on algorithms and subsequent outcomes. As an example, machine learning in fraud prevention allows algorithms to make immediate decisions on new transaction decisions, but over time "learn' from the outcomes of the purchases and from that new data, self-correct to make increasingly accurate predictions going forward. The fastest and most reliable path towards the learning component relies on analysts’ insights, assisted by machine-learned predictions, to make well-informed decisions.

Mail Fraud and Wire Faud

Mail fraud and wire fraud are federal crimes in the United States that involve mailing or electronically transmitting something associated with fraud. Jurisdiction is claimed by the federal government if the illegal activity crosses interstate or international borders.

Mail Order Telephone Order (MOTO)

Mail Order Telephone Order (MOTO) is a type of card-not-present (CNP) transaction in which services are paid and delivered via telephone, mail, fax, or internet communication. With the introduction of chip technology on most cards, there has been reduced fraud in “card present” transactions, but a corresponding increase in fraud in CNP transactions. The word stands for “mail order telephone order,” although those types of financial transactions are increasingly rare. MOTO has, therefore, become synonymous with any financial transaction where the entity taking payment does not physically see the card used to make the purchase.

Malware

Malware is software that is intentionally designed to cause damage to a computer, client, server or the network of a computer. Hostile, intrusive, and intentionally nasty, malware seeks to invade, damage, or disable computers, often by taking partial control over a device’s operations.

Man-In-The-Browser

A man-in-the-browser is a type of online threat, where a hacker uses a trojan horse virus to gain access to your computer. From there, the hacker manipulates the content you see within your web browser, which can allow them to record your personal information and passwords, as well as manipulate your transactions so that the money you think you are spending on an online product actually goes to the hacker, without anything looking any different from normal on that webpage.

Man-In-The-Middle

Man-in-the-middle (MITM) is an attack where the attacker secretly relays and possibly alters the communications between two parties who believe they are directly communicating with each other.

Manpower Direct and Indirect Costs

Manpower Direct Costs include wages for the employees that produce a product, including workers on an assembly line, while indirect costs are associated with support labor, such as employees who maintain factory equipment.

Manual Review

Manual review is a technique that can be performed in-house or may be outsourced to or managed by a third party vendor. In either case, staff members perform manual checks on orders to determine the authenticity of an identity and transaction to establish which orders are fraudulent.

Manual Submission

Manual submission describes when somebody adds URLs to a search engine manually, filling out the form fields individually. This differs from automatic submissions, which involve filling out information only one time; the necessary information is then used by a software program to submit to many search engines.

Marketplace

A marketplace is the real, virtual or metaphorical space in which a market operates. The term is also used in the trademark law context to denote the actual consumer environment, i.e. the 'real world' in which goods and services are provided and consumed.

Marketplace Fraud

What is Marketplace Fraud?

Marketplace fraud is the illegal practice of making false or misleading claims through a company. This includes exaggerating the qualities of a product or service in advertising, selling imitations as the genuine article, or hiding negative aspects or side effects. False advertising is a type of the marketplace fraud.

An online marketplace creates a streamlined process for buyers and sellers to find one another. The first wave
of digital marketplaces came about with eBay’s launch in 1995. More product-focused marketplaces like these followed swiftly, from Amazon to WALMART's Jet.com.

Since then, online marketplaces have evolved to combine products and services. Whether it’s to buy something, rent a living space or get a ride, these marketplaces have spanned across various market segments from food to crowdfunding.

Marketplace Fraud Inforgraphic

Types of Marketplace Fraud

  1. Fake Profile or Product Fraud - Common on marketplaces like Wish.com or Alibaba, a fraudulent seller copies the profile of a legitimate seller in order to deceive victims and turn a profit. This is damaging to the original sellers as well, as business is stolen. A potential customer is lost, and in some cases may never even receive a product.
  2. False Advertising - Misleading representation of goods or services through false or fraudulent claims or statements.
  3. Fake Buyer and Seller Closed Loop Account Fraud - A fraudster creates multiple fake buyer and seller accounts created. The fake buyers pay the fake seller for nonexistent items or services using stolen credit cards.

How to Stop Marketplace Fraud

Stopping marketplace fraud can be difficult for businesses. Keeping an important eye on marketplaces with similar products is vital to deter product fraud. Additionally, keeping an eye on your own customers, and those who purchase with fraudulent information, might indicate further resellers. Keeping tabs not only on public marketplaces, but the needs of those who are trying to manipulate the deep web, is another practice that will keep you ahead on the latest fraud trends.

The best way you can improve your fraud prevention on either sides of the market is by relying on ecommerce fraud prevention software. Machine learning fraud detection leverages billions of consortium transactions and outcomes to detect fraud.  This is done at every stage of the customer life cycle, in real-time to detect unusual transaction patterns. AI crawlers that scan the deep and dark web keep the system up to date without the need to constantly set new rules in the software. 

Fraud.net addresses these problems with a comprehensive and flexible fraud prevention platform, including AI / Deep Learning models, consortium fraud data, highly customizable case management and advanced analytics.

Learn More