Connect with us


Complexities When AI Autonomous Cars Attempt Zipper Merging




The zipper merge with the arrival of self-driving cars, will likely be a thorn in the side of all drivers, both human and AI driving systems. (Credit: Getty Images)

By Lance Eliot, the AI Trends Insider

You undoubtedly know what a zipper merge is, though the name of it might seem unfamiliar.

Here’s how it goes. Imagine you are driving along on the highway, minding your own business, when you spy up ahead an indication that your lane is being narrowed out and you’ll need to get over into the other lane next to you. An electronic board sign is flashing warnings that your existing lane is going to end soon (“Merger Ahead” it veritably screams at you). In addition, a series of weather-worn red cones are set up in your lane that inch you over, step-by-step, and are positioned to gradually shunt all traffic out of the lane you are in.

It is the classic 2-into-1 traffic control squeeze play.

This is also commonly known as the zipper merge because it looks like a zipper as cars are pinned into veering from two lanes into one. Anyone that drives around with any frequency is apt to encounter these 2-into-1 situations on any given day and during any given driving journey. They exist aplenty.

So, what do you do?

One answer is that upon immediately spotting that a merger request is being proffered, you would as quickly and as safely as feasible guide your car into the next lane over and expeditiously get out of the lane that is going to disappear. You would not wait. You would not remain in the vanishing lane. You would act decisively and obey what you believe to be a lawful order to switch lanes. Let’s label that kind of driver as an Early Merge type of person, employing a driving strategy of trying to perform the merging action as soon as possible.

Another answer to the driving scenario is to try and remain in the fading lane as long as you can. The idea is to wait until the last possible moment and then dart over into the remaining available lane. In some ways, this is kind of exciting and maybe provides a bit of a thrill. In any case, the person using this approach is apt to be thinking that there is no particular reason to act like a scaredy-cat and abandon a perfectly good lane, postponing the abandonment until the only option left involves getting out and into the bordering lane. We’ll label this kind of driver as the Late Merge type of person.

Okay, so which camp do you fall into, the Early Merge members of society or the Late Merge members of our world? This is where the heated and acrimonious debates start to unfold.

The Early Merge types are bound to exhort that the Late Merge people are miscreants. Those Late Merge drivers are outright idiots that do not realize they ought to obey the indicated signs and get over in a prudent, timely, and earliest feasible way. Doing so is decidedly safer for all concerned. When those dolts dart over at the endpoint of merging, they are going to create trouble, heaps, and heaps of trouble. The odds are that it will cause the traffic to react in a knee jerk way, unfairly forcing other drivers to avert getting into a collision with these wrongdoers that have no civility, no politeness, and are steeped in pure unadulterated driving greed when behind the wheel of a car.

In contrast, the Late Merge types are likely to exclaim that the Early Merge drivers are skittish dimwits. The Early Merge types are so frightened at being on the highways that they get frazzled at the drop of a hat. If they see a posted roadway sign, they feel compelled to instantly do what it says, regardless of using any semblance of common-sense as to what to do. Those Early Merge nervous nellie drivers are the real troublemakers since they react to the traffic conditions without letting a single thought enter into their noggin. Furthermore, they seem to think that they alone are the arbiters of controlling traffic and will often attempt to force others to abide by their dictums about how to respond to a 2-into-1 merging situation. They are busybodies, acting high-and-mighty that they somehow own the road and want everyone to get over just like them, unwilling to allow freedom of thought or expression to other drivers.

Obviously, these are two diametrically opposed viewpoints.

Indeed, when the Early Merge purist meets with the Late Merger perfectionist, during a roadway 2-into-1 traffic condition, there is a sizable potential for sparking road rage. Each is upset at the other. Each believes they are truly in the right. Each profusely believes the other is absolutely and unquestionably in the wrong.

It is a combustible interaction, that is for darned sure. The conundrum and discourse about which driving strategy is right and which is wrong has been going on since the invention of the revered and at times loathed 2-into-1 contrivance. Using everyday intuitive logic does not seem to help clear-up the matter.

The Early Merge logically allows for a more measured approach that calmly allows for drivers to exit from their existing lane and comfortably merge into the next lane over, giving the drivers in that lane some breathing room to let in the other drivers. This would seem to provide a more seamless meshing of traffic and not cause any disruptive leaps or skirmishes, enabling a smoother and ultimately more effective flow of traffic. Seemingly this should mean fewer car crashes in a zipper merging context and less frustration and angst for all drivers involved.

Indubitably solid logic.

The Late Merge logically allows for better use of the roadway availability. If drivers prematurely get out of an available lane, they are going to crowd into the other remaining lane, thus underutilizing the lane that still has room and time available for usage. When you attempt to cram one queue or line of cars into another lane, it is going to cause an adverse and unwarranted distending of traffic and disturb the overall flow of traffic, therefore you should only do so when there are no other viable means to continue using the second lane.

Well, seems like more absolutely sound logic.

Maybe they are both wrong, or then again, maybe they are both right. But that doesn’t solve any of this matter and leaves us with nothing tangible as to what ought to be strictly done.

Numerous simulations have been undertaken to try and ferret out the proper choice.

A robust simulation will consider a variety of factors such as traffic throughput, queue lengths, travel times, car crashes, near collisions, and so on. These are computer-based models that attempt to simulate or pretend what might occur during actual driving situations. Not all such simulations are the same, and different authors or developers take differing paths to how they structure and program their particular simulation of a zipper merge scenario.

By-and-large, the simulations tend to suggest that waiting to merge is the “better” option, assuming that you are aiming to make maximal use of the roadway. Unfortunately, few of these studies incorporate the foibles of human drivers and assume that a human driver will always do the right thing in terms of how they drive, acting as a kind of driving automata.

In other words, in a simulated setup, the simulated drivers are oftentimes mathematically composed as though they will always anticipate that all other drivers will be doing the Late Merge, and none of the simulated drivers will do the Early Merge and that all drivers will accordingly drive to accommodate the sole driving strategy of the Late Merge.

This is an unheard-of and rarely if ever witnessed homogenization of driving.

Humans do not drive that way, and we would be dreaming to assume that they would act in such a wholly consistent and unerringly way while at the driving controls of their cars. Simulations that incorporate both the day-to-day mindful and at times mindless ways that humans drive are usually more likely to be better aligned with the realities of driving in a messy, confounding world composed of zany and emotionally spurred human drivers.

All told, the real-world question about the zipper merge is a tough one to resolve.

Except that the future might provide a ready resolution. Consider this intriguing point: Will the advent of AI-based true self-driving cars make zipper merges into an easy peasy situation and thus obviate any further qualms about dealing with the infamous 2-into-1 quandary?

Let’s unpack the matter and see.

For my framework about AI autonomous cars, see the link here:

Why this is a moonshot effort, see my explanation here:

For more about the levels as a type of Richter scale, see my discussion here:

For the argument about bifurcating the levels, see my explanation here:

Understanding The Levels Of Self-Driving Cars

As a clarification, true self-driving cars are ones that the AI drives the car entirely on its own and there isn’t any human assistance during the driving task.

These driverless vehicles are considered a Level 4 and Level 5, while a car that requires a human driver to co-share the driving effort is usually considered at a Level 2 or Level 3. The cars that co-share the driving task are described as being semi-autonomous, and typically contain a variety of automated add-on’s that are referred to as ADAS (Advanced Driver-Assistance Systems).

There is not yet a true self-driving car at Level 5, which we don’t yet even know if this will be possible to achieve, and nor how long it will take to get there.

Meanwhile, the Level 4 efforts are gradually trying to get some traction by undergoing very narrow and selective public roadway trials, though there is controversy over whether this testing should be allowed per se (we are all life-or-death guinea pigs in an experiment taking place on our highways and byways, some contend).

Since semi-autonomous cars require a human driver, the adoption of those types of cars won’t be markedly different than driving conventional vehicles, so there’s not much new per se to cover about them on this topic (though, as you’ll see in a moment, the points next made are generally applicable).

For semi-autonomous cars, it is important that the public needs to be forewarned about a disturbing aspect that’s been arising lately, namely that despite those human drivers that keep posting videos of themselves falling asleep at the wheel of a Level 2 or Level 3 car, we all need to avoid being misled into believing that the driver can take away their attention from the driving task while driving a semi-autonomous car.

You are the responsible party for the driving actions of the vehicle, regardless of how much automation might be tossed into a Level 2 or Level 3.

For why remote piloting or operating of self-driving cars is generally eschewed, see my explanation here:

To be wary of fake news about self-driving cars, see my tips here:

The ethical implications of AI driving systems are significant, see my indication here: 

Be aware of the pitfalls of normalization of deviance when it comes to self-driving cars, here’s my call to arms:

Self-Driving Cars And Zipper Merges

For Level 4 and Level 5 true self-driving vehicles, there won’t be a human driver involved in the driving task. All occupants will be passengers. The AI is doing the driving.

Not only will the AI be doing the driving, but it will also most likely have a means to electronically communicate with other nearby self-driving cars.

This is aiming to be accomplished via the use of V2V, vehicle-to-vehicle electronic messaging. Suppose a self-driving car notices some debris in the roadway, it can quickly send out a V2V message to other nearby self-driving cars to be wary of the debris. This would give those other AI driving systems a heads-up to perhaps change lanes before coming upon the debris or otherwise take any needed evasive driving actions beforehand.

What does this all portend for the zipper merge?

I’m betting that you’ve already added together the one-plus-one involved and come to a logically apparent conclusion that the zipper merge problem is solved.

Each AI-based self-driving car could coordinate with each other, during a zipper merge, and readily handle the merging activity. By communicating to each other via the V2V, and by allowing each other the courtesy of getting into the remaining lane, this whole matter would be as seamless as watching a flock of birds that weave back-and-forth together effortlessly.

The self-driving cars will do a dance that is undertaken without any visible waving of hands or arms, and nor any dangerous attempts at cutting each other off. They will instead be conveying their requests to each other electronically and silently fall into a beauteous pattern of streaming without hesitation and absence of any disturbances through the zipper. The timing can happen at the fastest speeds that traffic will allow.

Adding to the impressive nature of this effort, there is also going to be V2I, vehicle-to-infrastructure electronic communications. That means that roadway infrastructure such as road closures and the like will be sending out beaconing signals to warn about various traffic conditions. When a zipper merge is put in place, a V2I indicator will start broadcasting to alert any upcoming traffic. The AI driving systems would know then about the zipper due to either the V2I or via the V2V (as tipped from another nearby self-driving car).

Yay, excitedly, the zipper merge is another one of life’s many problems that we can put to rest.

Sorry to say, life is never that easy.

We’ll start with the biggest hurdle and then make our way to smaller ones.

The 500-pound gorilla is the fact that we are still going to have human drivers on our roadways for quite a while to come, despite the emerging advent of true self-driving cars.

Keep in mind that there are about 250 million conventional cars in the United States today, and those aren’t going to be tossed into the junk heap anytime soon merely due to the appearance of self-driving cars. Economically it is just not a feasible notion. As such, there will still be tons upon tons of human-driven cars on our roadways for decades to come.

Furthermore, we do not yet know whether human driving is really going to be given up entirely. One argument is that people must give up their driving to allow for the saving of the 40,000 annual driving fatalities and the 2.3 million estimated car-related injuries that occur each year in the U.S. It is assumed and hoped that the use of self-driving cars is going to diminish dramatically that volume of carnage.

But will people really be willing to stop driving? Many fervently assert that driving is their right (well, it is legally considered a privilege rather than a right), and you cannot force them to give up driving. Some insist you will only do so when you pry their cold dead hands from their steely grip upon the steering wheel.

How does the continued human-driven element make a difference in the zipper merge and self-driving cars?

The point is that the self-driving cars will not merely be able to coordinate with each other, they will also need to contend with human drivers. Recall that human drivers are, well, human, and therefore will continue to drive in their haphazard and perplexing ways. This means that you can toss aside the aforementioned harmonious dance of the self-driving cars.

Human interlopers will trounce the dance.

You can readily bet your bottom dollar that if self-driving cars choose to do the Late Merge, there will be humans that instead choose the Early Merge. If self-driving cars choose the Early Merge, there are undoubted will be Late Merge oriented human drivers. The earlier chaos of each driver tackling the matter in their own proprietary way has come back into the picture.

Once self-driving cars are prevalent, the numbers might end-up inexorably in a gradual shift toward the AI winning the zipper merge game. In essence, the fewer number of human-driven cars still on the roadways will be but a speck and therefore the AI driving systems will be pretty much able to drive around in a relatively smooth and coordinated fashion, only contending from time-to-time with those irritating and irascible human drivers.

In any case, the zipper merge in the near term, even with the arrival of self-driving cars, will continue to be a thorn in the sides of all drivers, both human drivers and AI driving systems.

This does bring up another facet about that state of the world, namely, how should an AI driving system act or react to a human-driven car during a zipper merge?

Right now, most of the automakers and self-driving car tech firms are making the AI rather timid when it comes to driving near humans. Generally, whatever a human driver wants, they will get, in terms of a nearby AI-based self-driving car that will readily give way to the human driver. If you are driving your car in the vanishing lane and suddenly want to move over, a self-driving car in that other lane is going to let you in, assuming that it is physically possible to do so. No questions asked. Unlike a human driver in that lane that might be spiteful at your interruption, the AI is just going to be, shall we say, a pushover.

Plus, human drivers will realize that AI driving systems are pushovers. In that case, the human drivers that already think of other human drivers as sheep will assuredly consider the AI driving systems to be like sheep, or whatever is even more docile and unaggressive in the animal kingdom.

One significant concern overall about the advent of self-driving cars is that some human drivers are going to try and exploit the situation. Those scofflaw pushy human drivers will routinely and gladly cut off the AI self-driving cars. This is going to up the ante on potential car crashes, which at first glance might not seem possible, since the AI will do what it can to avoid a collision, but the physics of the vehicles might not allow for an evasive maneuver and we’ll end-up with human drivers and AI driving systems getting into car crashes.

For human drivers desiring to exploit the AI timidity (as programmed), their opinion is going to be that if those AI driving systems were made to be taken advantage of, they surely ought to be so skewered.

For more details about ODDs, see my indication at this link here:

On the topic of off-road self-driving cars, here’s my details elicitation:

I’ve urged that there must be a Chief Safety Officer at self-driving car makers, here’s the scoop:

Expect that lawsuits are going to gradually become a significant part of the self-driving car industry, see my explanatory details here:


I earlier mentioned that some other less apparent considerations can toss a monkey wrench into the zipper merge riddle when it comes to adding self-driving cars into the mix.

Here’s a taste.

Assume that only self-driving cars are about to converge on a zipper merge (no human drivers are nearby).

In what order or sequence should the AI driving systems jointly ascertain which cars get through the squeeze play?

First come, first serve is not necessarily a completely viable option per se, due to the cars arriving at the bottleneck in relative unison. In that case, you might assert it is simply a matter of a random selection, done without preference to any particular AI or self-driving car. On the other hand, suppose we decide as a society that it is permitted to have passengers that can up the priority of their self-driving car, perhaps by being a highly ranked government official or being a celebrity. Or, perhaps by paying an added fee to the fleet owner of the self-driving car.

A final question to ponder, beyond the realm of discussing just the zipper merge, involves whether we will be willing to allow self-driving cars to operate differently depending upon the passenger or the payment by a passenger. Some say this smacks of elitism and undercuts hoped-for democratization of mobility for all that the promise of self-driving cars seems to offer.

Anyway, please be careful of other human drivers when doing those maddening zipper merges, and if you can, take it easy on the AI driving systems too.

Copyright 2020 Dr. Lance Eliot. This content is originally posted on AI Trends.

[Ed. Note: For reader’s interested in Dr. Eliot’s ongoing business analyses about the advent of self-driving cars, see his online Forbes column:]


Artificial Intelligence

Google Meet gets a refreshed UI, multi-pinning, autozoom and more




Google today announced a major update to Meet, its video-meeting service, which brings several user interface tweaks for desktop users, as well as quite a bit of new functionality, including multi-pinning so that you can highlight multiple feeds instead of just one, as well as new AI-driven video capabilities for light adjustments, autozoom, and a new Data Saver feature that limits data usage on slower mobile networks.

If you’re anything like me, you’re increasingly tired of video meetings (to the point where I often just keep the camera off). But the reality is that this style of meetings will be with us for the foreseeable future, whether we like them or not.

Image Credits: Google

Google notes that today’s release is meant to make meetings “more immersive, inclusive, and productive.” The new UI doesn’t look to be a radical change, but it puts more of the controls and features right at your fingertips instead of hiding them in a menu. It also consolidates them in the bottom row instead of the current system that spreads out features between the main menu bar and an additional small menu at the top.

For presenters who don’t want to see themselves on the screen, Meet now also lets you minimize or completely hide your own video feed — and if you really want to glance into your own eyes, you can also pin your feed to the rest of the grid. Google says it also plans to soon let you turn off your self-feed across all Meet calls.

Image Credits: Google

Talking about pinning, one feature that seems especially useful is the ability to highlight multiple feeds. This new multi-pinning capability will make it easier to focus on the participants in a chat that are most active, for example. This feature will roll out in the coming months.

And coming in a few months, some of those highlighted feeds may look a bit more interesting (or annoying, depending on your point of view) because one new feature Google has planned — but isn’t ready to roll out yet — is video background replacement. For now, Google will only offer three scenes: a classroom, a party and a forest. The company says more will follow, but it doesn’t look like you’ll be able to bring your own videos to this feature anytime soon.

Image Credits: Google

Other new features in this release include Meet’s capability to automatically spruce up your video feed a bit to make sure you’re more visible in a dark environment and enhance your video when you are sitting in front of a bright background. This will roll out in the coming weeks. There’s also autozoom, which uses AI to automatically zoom in on you and put you in the middle of your frame. That’s coming to paid Google Workspace subscribers in the coming months.

Coinsmart. Beste Bitcoin-Börse in Europa

Continue Reading

Artificial Intelligence

Tribal Credit, which provides credit cards to startups in emerging markets, raises $34.3M




The B2B payments space has seen an explosion in demand, and investor interest, in the wake of the COVID-19 pandemic as businesses try to figure out how to pay each other digitally. The challenges become even more complex when dealing with cross-border payments.

Startups that were formed before the pandemic stand to benefit from the shift. One such startup, Tribal Credit, launched its beta in late 2019 to provide payment products for startups and small to medium-sized businesses (SMBs) in emerging markets.

Today, Tribal Credit announced it has raised $34.3 million in a combined Series A and debt round led by QED Investors and Partners for Growth (PFG). Existing backers BECO Capital, Global Ventures, OTG Ventures and Endure Capital also participated in the round, along with new investor Endeavor Catalyst. The raise follows “10x” year-over-year growth, according to CEO and co-founder Amr Shady.

As part of the investment, Tribal received $3 million from the Stellar Development Foundation, a nonprofit organization that supports the development and growth of the open-source Stellar blockchain network. 

Tribal uses a proprietary AI-driven underwriting approval process to evaluate businesses and approve them for credit lines. Those businesses can then use those credit lines to spend on Tribal’s products, Tribal Card and Tribal Pay. Tribal Card is a business Visa card that allows users to create physical and virtual multi-currency cards. Tribal Pay allows them to make payments to merchants and suppliers that don’t accept credit cards. 

The company says its value proposition lies not only in its ability to provide SMEs with virtual and physical corporate cards, but also a digital platform that allows founders and CFOs “to give access to and manage the spend of their distributed teams.”

“We’ve seen more demand for making B2B online payments amidst the ongoing COVID-19 pandemic, with many SMEs migrating to digital and spending more on online products and services,” Shady told TechCrunch. “Companies in this new economy are digital and global first. The need for a corporate card was accelerated. As card spend grew during the pandemic, this meant greater liability on founders’ using their personal cards, or other competing cards linked to their personal credit.” 

Tribal, he said, underwrites the company without impacting the founders’ credit. 

Another accelerator for its products was how the pandemic forced teams to work remotely. Founders and CFOs needed a way to provide access to corporate payments while maintaining control, Shady pointed out. Tribal’s platform aims to streamline financial operations for a distributed team. 

Of course, Tribal is not the only company offering credit cards for startups. Brex, which has amassed $465 million in venture capital funding to date, also markets a credit card tailored for startups. While the companies are similar, there is a distinct difference, according to Shady: “Emerging market SMEs have different pains, particularly when it comes to cross-border payments.”

Tribal’s initial efforts are focused on Latin America, in particular Mexico, which is the startup’s biggest market.

Its new capital will go toward accelerating its growth in the region, according to Shady. In particular, the equity will go toward growing Tribal’s leadership team in Mexico, while the debt will fuel the company’s customers’ growing credit lines, Shady said.

“We have invested heavily in our product over the past year,” Shady said. “We’re the first mover in our segment in LatAm with a diverse suite of SME products that includes corporate cards, wire payments and treasury services. We’re incredibly excited by the future ahead of us in Mexico and beyond.” 

Customers include Minu, Ben and Frank, Fairplay and SLM, among others.

Looking ahead, Tribal is exploring four other Latin American markets and expects to be operational in one new market by year’s end, according to Shady.

Image Credits: Tribal Credit

QED Investors partner Lauren Morton said her firm has been following payments and the lending needs of SMEs in emerging markets closely.

“Compared with everything else we’ve seen in this market, Tribal has a differentiated and superior product that meets customers’ needs in a way that no competitor can match,” she said in a written statement. 

Morton went on to note that Tribal has had strong traction in Mexico, with adoption from “fast-growing startups” across the country, including many companies within QED’s own portfolio. 

PFG is providing the debt facility for Tribal. In addition to funding from PFG’s global fund, the firm will be co-investing from its Latin America Growth Lending Fund in partnership with IDB Invest and SVB Financial Group, the parent company of Silicon Valley Bank. 

Tribal Credit previously raised $7.8 million in a series of seed rounds. The latest round brings its total raised to $42.1 million. Tribal Credit also joined Visa’s Fintech Fast Track Program, a move that it said should accelerate its integration with Visa’s global payment network.  The company currently has 75 employees, up from 31 last year.

Coinsmart. Beste Bitcoin-Börse in Europa

Continue Reading


Anomaly Detection in Finance




Consumers and businesses worldwide are losing billions of dollars every year to neverending attacks from cybercriminals. Financial institutions spend billions more investigating and recovering the stolen money. As attacks become more and more sophisticated, money-handling companies need to incorporate strong fraud-prevention mechanisms into their strategies to protect their customers and themselves from unnecessary expenses. 

The ever-growing amount of data captured by financial institutions makes anomaly detection an invaluable tool for identifying fraudulent transactions and behaviors.

Cybercrime complaints and reported losses 2015-2019 

Source: FBI Internet Crime Complaint Center

What is anomaly detection?

Anomaly detection in financial transactions classifies data into normal distribution and outliers. When a transaction or a data point deviates from a dataset’s normal behavior, it can be considered potentially fraudulent. 

How does anomaly detection work in payments and finance? 

The anomaly detection approach for transaction data is advantageous because it provides simple binary answers. Any unexpected change from normal data patterns or an event that does not conform to model predictions is considered an anomaly. If a transaction looks suspicious and potentially fraudulent, the system may ask the customer to verify details or go through additional verification steps. By analyzing multiple data points, anomaly detection can be applied to flag technical outages, glitches, and potential opportunities such as a positive change in consumer behavior.

However, there are no universal patterns or business as usual when it comes to everyday life. The same unusually large amount of payments expected on Black Friday would stand out on any other day, and vice versa. But even the most well-established peaks in the natural business cycle can shift from time to time. 

The coronavirus pandemic, for example, resulted in a skyrocketing volume of online payments and a fall in in-store purchases. Datasets used to train static anomaly detection systems didn’t have any similar historical patterns, which resulted in countless transactions being flagged as fraudulent when they were not. Many financial institutions worldwide saw their anomaly detection anti-fraud systems fail for this exact reason. 

Machine Learning powered anomaly detection

Incorporating Machine Learning (ML) anti-fraud systems is an advanced approach that reduces uncertainty by automating the complex anomaly detection process. ML algorithms can be used to find the very subtle and usually hidden events and correlations in user behavior that may signal fraud. By comparing numerous variables in real-time, anomaly detection with machine learning can process large datasets to determine the likelihood of fraudulent transactions or actions. 

ML has been used to spot fraudulent transactions since the 1990s. Since then, the technology has matured to track and process transaction size, location, time, device, purchase data, and many other variables simultaneously. ML-enabled anomaly detection can process much more financial data much faster than human rule-based systems. Smart algorithms that monitor consumer behavior help to reduce the number of verification steps that impede the consumer purchasing journey and reduce false positives, drastically improving user experience. 

Real-time anomaly detection in financial transactions enables companies to immediately respond to deviations from the norm, potentially saving millions that would have been lost to fraud otherwise. By eliminating the delay between spotting the problem and resolving it, payments and finance companies maximize the efficiency of their anti-fraud strategies. 

Manual anomaly detection with a human monitoring a dashboard with a few KPIs is not scalable to millions of transactions consumers make every day and millions more metrics associated with them. Maintaining real-life responsiveness requires a sophisticated anomaly detection system powered by machine learning that can monitor and correlate multiple complex metrics with different amounts of variability to sift through millions of data points every second. 

Source: Federal Trade Commission, Consumer Sentinel Network

Anomaly detection: build vs. buy?

The importance of fraud detection for payments and finance companies is hard to overstate. Real-time anomaly detection is already used by the leading financial institutions worldwide to prevent losses from occurring in the first place. Businesses aiming to stay a step ahead of the cybercriminals can either buy a complete anomaly detection system or build it from scratch. 

To make the right decision that will generate the greatest return on investment, companies need to consider their size and the volume of financial data that must be processed. The budget and time to value tie in with the capacity for development and maintenance of the IT team building it. Lastly, it is essential to factor in future growth and how it will impact all of the previous factors. Real-time anomaly detection for transaction data is a sophisticated tool that requires specialist knowledge and an expert IT team to develop.  Building from scratch enables complete control over the final product but includes a great deal of uncertainty. Partnering with a technology vendor minimizes risk as anomaly detection can be integrated quickly and predictably. real-time anomaly detection feature, a white-label digital payment platform, is proud to announce the new anomaly detection feature.

An anomaly detection dashboard allows to detect unexpected transaction amounts and frequencies and take actions.  Machine learning (ML) algorithms process large datasets with many variables to help find these hidden correlations between user behavior and the likelihood of fraudulent actions.

The transaction anomalies table provides a detailed view of every highlighted transaction as anomalous.

Source: Transaction Anomaly Detection Analysis

New anomaly detection feature will allow our Clients to prevent losses from occurring in the first place. If a transaction looks suspicious and potentially fraudulent, the system may ask the customer to verify details or go through additional verification steps.

What is

The digital retail banking platform built by a team with 15+ years of experience in FinTech is available in all popular formats: web, iOS, and Android applications to reach the new generation of mobile-first customers. 

The platform is available in three formats:

Contact the team directly to learn more about what type of banking software will be perfect for your business needs.

Coinsmart. Beste Bitcoin-Börse in Europa

Continue Reading

Artificial Intelligence

Orca AI, which puts computer vision onto cargo ships, raises $13M Series A funding




Tel Aviv’s Orca AI, a computer vision startup that can be retrofitted to cargo ships and improve navigation and collision avoidance, has raised $13 million in a Series A funding, taking its total raised to over $15.5 million. While most cargo ships carry security cameras, computer vision cameras are rare. Orca AI hopes its solution could introduce autonomous guidance to vessels already at sea.

There are over 4,000 annual marine incidents, largely due to human error. The company says this is getting worse as the Coronavirus pandemic makes it harder for regular crew changes. The recent events in the Suez Canal have highlighted how crucial this industry is.

The funding round was led by OCV Partners, with Principal Zohar Loshitzer joining Orca AI’s board. Mizmaa Ventures and Playfair Capital also featured.

The company was founded by naval technology experts, Yarden Gross and Dor Raviv. The latter is an former Israel navy computer vision expert. Customers include Kirby, Ray Car Carriers and NYK.

Orca AI’s AI-based navigation and vessel tracking system supports ships in difficult to tricky to navigate situations and congested waterways, using vision sensors, thermal and low light cameras, plus algorithms that look at the environment and alert crews to dangerous situations.

On the raise, Yarden Gross, CEO, and co-founder said: “The maritime industry… is still far behind aviation with technological innovations. Ships deal with increasingly congested waterways, severe weather and low-visibility conditions creating difficult navigation experiences with often expensive cargo… Our solution provides unique insight and data to any ship in the world, helping to reduce these challenging situations and collisions in the future.” 

Zohar Loshitzer, Principal from OCV added: “Commercial shipping has historically been a highly regulated and traditional industry. However, we are now “witnessing a positive change in the adoption of tech solutions to increase safety and efficiency.

Coinsmart. Beste Bitcoin-Börse in Europa

Continue Reading
Esports5 days ago

C9 White Keiti Blackmail Scandal Explains Sudden Dismissal

Esports5 days ago

Overwatch League 2021 Day 1 Recap

Esports5 days ago

Fortnite: Epic Vaults Rocket Launchers, Cuddlefish & Explosive Bows From Competitive

Esports5 days ago

Gamers Club and Riot Games Organize Women’s Valorant Circuit in Latin America

Blockchain5 days ago

15. BNB Burn: Binance zerstört Coins im Wert von 600 Mio. USD

Esports5 days ago

LoL gameplay design director pulled, transferred to Riot’s MMO

Esports5 days ago

How to counter Renekton in League of Legends

Esports5 days ago

Lakeland University Partners With Bucks Gaming for the 2021 NBA 2K League Season

Blockchain4 days ago

Elon Musk twittert Dogecoin auf neues Allzeithoch

Esports5 days ago

How to play League of Legends’ newest champion Gwen

Esports5 days ago

3 big reasons why Dota 2’s new hero Dawnbreaker is just bad

Esports4 days ago

Dota 2 patch 7.29b brings nerfs to Phantom Lancer and Lifestealer amongst other hero balance changes

Blockchain5 days ago

NSA-Whistleblower Edward Snowden versteigert seinen ersten NFT „Stay Free“

Esports3 days ago

Code S: Trap & Zest advance to RO8, playoff bracket set

Esports4 days ago

New CSGO Update Makes Items Purchased From Store Non Tradable for a Week

Esports4 days ago

Sumail’s absence; A gap year or fall from grace?

Blockchain2 days ago

Mining Bitcoin: How to Mine Bitcoin

Esports4 days ago

Apex Legends Season 9 will add new hero, fix Banglore bugs

Esports4 days ago

Radiant Valorant streamer Solista banned for cheating on live stream

Esports5 days ago

Tencent Esports Partners With Hubei Province to Host CrossFire Franchise League in Wuhan