Integrating generative AI with other AI models and applications can enhance their capabilities and create more comprehensive and effective solutions. Here are several ways this integration can be achieved:

1. Natural Language Processing (NLP):

• Chatbots and Virtual Assistants: Integrative generative AI can create more human-like and contextually aware responses, improving user interaction and satisfaction.
• Text Summarization and Translation: Combining generative AI with existing NLP models can improve the accuracy and fluency of summaries and translations.

2. Computer Vision:

• Image Generation and Enhancement: Generative AI can be used for creating high-quality images from text descriptions, improving image resolution, and filling in missing parts of images.
• Object Detection and Recognition: Integrating generative models can help in generating synthetic data to train and enhance object detection models.

3. Healthcare:

• Medical Imaging: Generative AI can enhance medical images, assist in creating synthetic medical data for training purposes, and improve diagnostics by integrating with existing imaging analysis models.
• Personalized Medicine: By generating patient-specific simulations and treatment plans, generative AI can assist in precision medicine efforts.

4. Finance:

• Fraud Detection: Generative models can simulate fraudulent transactions to improve the training of detection algorithms.
• Financial Forecasting: Integrating generative AI with predictive models can enhance scenario analysis and risk assessment.

5. Entertainment and Media:

• Content Creation: Generative AI can assist in creating music, art, and writing, augmenting the creative process and providing new tools for artists.
• Game Development: It can be used to create characters, dialogues, and scenarios, enhancing the gaming experience.

6. Education:

• Tutoring Systems: Combining generative AI with educational models can create personalized learning experiences, generating tailored content and feedback for students.
• Content Generation: Automating the creation of educational materials, such as quizzes and study guides, based on curriculum data.

7. Robotics:

• Behavior Simulation: Generative AI can simulate various robotic behaviors in different scenarios, improving the robustness of robotic models.
• Human-Robot Interaction: Enhancing the interaction by generating more natural and context-aware responses from robots.

8. Data Augmentation:

• Training Data Generation: Generative models can create synthetic data to augment training datasets, improving the performance of machine learning models.
• Anomaly Detection: Generating normal behavior patterns to help identify deviations and anomalies more effectively.

9. Personalization and Recommendation Systems:

• Content Personalization: Generative AI can create personalized content recommendations based on user preferences and behavior.
• Dynamic User Interfaces: Generating adaptive and personalized user interfaces that change based on user interactions and preferences.

Integrating generative AI with other AI models and applications requires careful consideration of data quality, model training, and ethical implications to ensure the effectiveness and reliability of the integrated solutions.

The post How can generative AI be integrated with other AI models and applications? appeared first on Artificial Intelligence.

As technologies like artificial intelligence and machine learning become more widely available and ubiquitous, they are having a real effect on payment processes. In less than two decades, the public has both become more aware and more comfortable with using technologies like machine learning and AI in their day-to-day life. There has also been a meaningful increase in investment and adoption of machine learning and AI by companies. On top of that, computer processing technology has made huge leaps and bounds within the last decade. Companies, institutions, and governments now gather massive amounts of data as more consumer interactions and transactions go digital. In short, high-performance computing is becoming increasingly affordable and accessible, so it’s no surprise that this type of technology is already transforming the payments landscape.

Fraud Prevention

With new payment methods like card-not-present (CNP) transactions come new opportunities for fraud (CNP fraud is on the rise). Artificial intelligence and machine learning are at the forefront of not just detecting fraud, but preventing it before it happens. These technologies can already uncover patterns and drive hidden insights, but the technology is moving towards refining these insights further. Instead of relying on supervised learning with input, advances are allowing companies to move past this more static model to unsupervised learning. An unsupervised, deep learning based, neural network doesn’t need a labeled training set: it will continuously update the model as new pattern emerges, allowing for a more robust, flexible, and updated fraud prevention detection tool — as long as there’s access to abundant data. Luckily, the available data has continued to grow as more commerce and payments move online. This more sophisticated algorithm uses machine learning to decreases false positives and more agile detection of actual fraud.

Improving Efficiency

Both machine learning and AI have the potential to revolutionize the way payments are processed, by improving operational efficiency and reducing cost. In fact, it’s already happening: AI is already being implemented with chatbots to lighten the load for customer service representatives, for example. And machine learning is already firmly in the payments scene too, with learning algorithms playing important roles in helping speed along authorization of transactions and monitoring.

AI can help reduce processing times for payments. It also can eliminate human error, saving precious time spent correcting those mistakes. Imagine a business that needs to process large amounts of data to generate financial reports and satisfy regulatory and compliance requirements; this process would typically involve a team of people performing repetitive data processing tasks. With AI, these tasks can be taught and left to machines that can accomplish these tasks faster and more accurately than human workers. These technologies can improve efficiency, while simultaneously gathering important user insights. And of course, these benefits also mean reduced operating cost in these sectors.

Machine learning is already an invaluable part of fraud detection, but the possibilities for including it in product sales, customer care, and retention are promising. Machine learning can draw on vast amounts of available data to profile customers and guess their product needs, offering new opportunities for upselling. This technology can also identify customers that companies are at risk for losing before it happens. Instead of playing catch-up when churn rates rise, companies can halt customer loss before it happens. Finally, machine learning can help automate many customer service interactions. This technology, using deep insights, cognitive engines, and natural language processing is already widely available. Usage will only grow with time.

New Opportunities

The implications for humans workers are interesting too. McKinsey Global Institute estimates that by 2030 47 percent of the US workforce will be automated. Replacing jobs involving repetitive and laborious tasks gives employees the chance to re-skill or up-skill — taking on more engaging roles. Forbes research actually indicates that, by 2034, AI could boost labour productivity by up to 40 per cent.

Conclusions

It’s clear that machine learning and AI have come a long way in the past decade. This technology has been adopted by many sectors, transforming many aspects of traditional processes, and the payments landscape is no different. Though many exciting new technologies have been adopted by companies to improve the payments process and customer experience already, the possibilities for future implementation are nearly endless.

The post How AI & Machine Learning Are Transforming the Payments Landscape appeared first on Artificial Intelligence.

The financial services industry has witnessed considerable hype around Artificial Intelligence (AI) in recent months. We’re all seeing a slew of articles in the media, at conference keynote presentations and think-tanks tasked with leading the revolution. AI indeed appears to be the new gold rush for large organisations and FinTech companies alike. However, with little common understanding of what AI really entails, there is growing fear of missing the boat on a technology hailed as the ‘holy grail of the data age.’ Devising an AI strategy has therefore become a boardroom conundrum for many business leaders.

How did it come to this – especially since less than two decades back, most popular references of artificial intelligence were in sci-fi movies? Will AI revolutionise the world of financial services? And more specifically, what does it bring to the party with regards to fraud detection? Let’s separate fact from fiction and explore what lies beyond the inflated expectations.

Why now?

Many practical ideas involving AI have been developed since the late 90s and early 00s but we’re only now seeing a surge in implementation of AI-driven use-cases. There are two main drivers behind this: new data assets and increased computational power. As the industry embraced big data, the breadth and depth of data within financial institutions has grown exponentially, powered by low-cost and distributed systems such as Hadoop. Computing power is also heavily commoditised, evidenced by modern smartphones now as powerful as many legacy business servers. The time for AI has started, but it will certainly require a journey for organisations to reach operational maturity rather than being a binary switch.

Don’t run before you can walk

The Gartner Hype Cycle for Emerging Technologies (Figure 1 below) infers that there is a disconnect between the reality today and the vision for AI, an observation shared by many industry analysts. The research suggests that machine learning and deep learning could take between two-to-five years to meet market expectations, while artificial general intelligence (commonly referred to as strong AI, i.e. automation that could successfully perform any intellectual task in the same capacity as a human) could take up to 10 years for mainstream adoption.

Other publications predict that the pace could be much faster. The IDC FutureScape report suggests that “cognitive computing, artificial intelligence and machine learning will become the fastest growing segments of software development by the end of 2018; by 2021, 90% of organizations will be incorporating cognitive/AI and machine learning into new enterprise apps.”

AI adoption may still be in its infancy, but new implementations have gained significant momentum and early results show huge promise. For most financial organisations faced with rising fraud losses and the prohibitive costs linked to investigations, AI is increasingly positioned as a key technology to help automate instant fraud decisions, maximise the detection performance as well as streamlining alert volumes in the near future.

Data is the rocket fuel

Whilst AI certainly has the potential to add significant value in the detection of fraud, deploying a successful model is no simple feat. For every successful AI model, there are many more failed attempts than many would care to admit, and the root cause is often data. Data is the fuel for an operational risk engine: Poor input will lead to sub-optimal results, no matter how good the detection algorithms are. This means more noise in the fraud alerts with false positives as well as undetected cases.

On top of generic data concerns, there are additional, often overlooked factors which directly impact the effectiveness of data used for fraud management:

• Geographical variances in data.
• Varying risk appetites across products and channels.
• Accuracy of fraud classification (i.e. which proportion of the alerts marked as fraud are effectively confirmed ones).
• Relatively rare occurance of fraud compared to the huge bulk of transactions; having a suitable sample to train a model isn’t always guaranteed.

Ensuring that data meets minimum benchmarks is therefore critical, especially with ongoing digitalisation programmes which will subject banks to an avalanche of new data assets. These can certainly help augment fraud detection capabilities but need to be balanced with increased data protection and privacy regulations.

For instance, the General Data Protection Regulation (GDPR) comes in force in May 2018 across EU member states and utilising new data assets such as device, geo-location or behavioural insight derived from session data may not be possible, unless consented. This is a notable change from previous national legislations such as the UK’s Data Protection Act where the Section 29(1) exemption allowed for ‘personal data processed for specified purposes of crime prevention/detection, apprehension/prosecution of offenders or imposition of tax or similar duties’ without explicit consent.

A hybrid ecosystem for fraud detection

Techniques available under the banner of artificial intelligence such as machine learning, deep learning, etc. are powerful assets but all seasoned counter-fraud professionals know the adage: Don’t put all your eggs in one basket.

Relying solely on predictive analytics to guard against fraud would be a naïve decision. In the context of the PSD2 (Payments Services Directive) regulation across EU member states, a new payment channel is being introduced along with new payments actors and services, which will in turn drive new customer behaviour. Without historical data, predictive techniques such as AI will be starved of a valid training sample and therefore be rendered ineffective in the short term. Instead, the new risk factors can be mitigated through business scenarios and anomaly detection using peer group analysis, as part of a hybrid detection approach.

Yet another challenge is the ability to digest the output of some AI models into meaningful outcomes. Techniques such as neural networks or deep learning offer great accuracy and statistical fit but can also be opaque, delivering limited insight for interpretability and tuning. A “computer says no” response with no alternative workflows or complementary investigation tools creates friction in the transactional journey in cases of false positives, and may lead to customer attrition and reputational damage – a costly outcome in a digital era where customers can easily switch banks from the comfort of their homes.

Holistic view

For effective detection and deterrence, fraud strategists must gain a holistic view over their threat landscape. To achieve this, financial organisations should adopt multi-layered defences – but to ensure success, they need to aim for balance in their strategy. Balance between robust counter-fraud measures and positive customer experience. Balance between rigid internal controls and customer-centricity. And balance between curbing fraud losses and meeting revenue targets. Analytics is the fulcrum that can provide this necessary balance.

AI is a huge cog in the fraud operations machinery but one must not lose sight of the bigger picture. Real value lies in translating ‘artificial intelligence’ into ‘actionable intelligence’. In doing so, remember that your organisation does not need an AI strategy; instead let AI help drive your business strategy

The post Artificial Intelligence for fraud detection: beyond the hype appeared first on Artificial Intelligence.

Most people will at the very least know someone who has been the victim of online fraud. Recent figures from Cifas revealed that a record-breaking total of 89,000 cases of fraud were recorded in the first six months of the year in the UK. The study found that while the number of identity fraud attempts against bank accounts and plastic cards has fallen, these still account for more than half of all cases. Last year alone, payment card fraud amounted to $21.84 billion globally.

Efforts to gain personal or financial information to commit fraud have evolved to highly sophisticated operations. It’s no longer a case of optimistically sending out emails about princes from foreign lands trying to send you large sums of cash. Now, fraudsters buy stolen credit card and personal information in bulk on the dark web and write programs or code to go about testing each card to determine if they can be mined for financial gain. The origin of fraudulent payments can normally be traced back to a data breach of an organisation. The recent case of Equifax, the US-based consumer credit reporting agency that compromised 143 million people’s data, is a prime example of this. Equifax then directed customers to a spoofed customer support page, failing to identify that it was deception and demonstrating how easy it is to mimic a business’ page.

The pressure on merchants

While having one’s card details stolen or used to make a fraudulent payment is undoubtedly stressful and inconvenient, it’s relatively straightforward for an individual to get the funds refunded through their bank. For merchants, fraudulent payments represent a rather different challenge. For a consumer to get their money back, their bank collects a refund from the merchant. But, if the merchant has shipped the goods or performed the service, they often have little recourse to recover costs. One study has found that every dollar spent fraudulently costs merchants $2.40. This means that merchants, particularly those selling goods or services online where the card is not physically present, must be extra vigilant to try and determine if the person buying the product is who they say they are.

One approach to manage risk is to simply decline any transaction that trips a card issuer’s fraud system – for example if the card has been used in a different country that it’s issued, or if the billing address is different to the shipping address. While this is likely to reduce fraud, chances are the merchant will also lose legitimate revenue opportunities as a result. Blocking legitimate transactions because they trip a fraud system is known as a ‘false positive’ and is reported to cost merchants close to $8.6 billion last year alone. Some tools such as 3D secure can help with this by asking for additional information on a stand-alone secure site before completing the transaction, but they are not fool-proof and often seen by consumers as ‘friction’ to the customer experience. In an era where consumers demand a frictionless experience, as Uber and Airbnb have become known for, adding the 3D secure layer can harm conversion.

Identifying the shopper behind the transaction

It’s no longer the case that the targets of online fraud are old people who fall for email scams – Cifas research suggests that it is actually people in their 30s who are most likely to fall victim. In fact the over-60s is the only age group that has seen fraud cases fall this year. Identifying the customer behind the transaction is the key to prevent fraud.

Device fingerprinting is a useful solution for creating a clearer picture of the person behind the transaction. This is the process of understanding the device that a shopper uses to make purchases and can help to eliminate false positives. For example, people buying gifts for friends in other countries can be a common red flag to fraud detection systems, because it is an international card purchasing something that is shipped to a foreign address that the card is not registered to. However, if this purchase was made on a device that the customer commonly uses, its device fingerprint would be familiar and the risk to the merchant is significantly reduced. Additional data analysis using algorithmic matching and behavioural analytics also play a very important role to correctly identify a purchaser.

Fighting data breaches with data science

If fraudsters are using algorithms and data science to quickly test and validate stolen card details in bulk, merchants must also use data science and predicative analytics to get ahead of the game.

Intelligent risk management solutions use a combination of transaction data and technology to build intelligent risk profiles designed to identify fraudsters early and remove friction for legitimate customers.

At Adyen we process payments for more than 4,500 merchants across the globe, including some of the world’s largest companies. This comprehensive dataset enables an intelligent assessment of each transaction – so that if a merchant identifies a fraudulent card in use, it can be analysed and treated with caution across the whole network.

With data science and machine learning, we can start to predict fraudulent behaviour and prevent these transactions from taking place. A crucial step to is to look at transactions as more than just stand-alone entities. There is a lot of valuable data that can be clustered with a transaction to get a holistic view of the shopper – such as email address, login credentials and card details. Through our ShopperDNA system, we apply advanced linking algorithms to these clusters, alongside proprietary device fingerprinting and network intelligence, to track devices, networks, and online personas. This enables merchants to track and block fraudsters as they adapt to reduce risk and chargebacks (the process where fraudulent payments are refunded).

Minimising risk while reducing friction

In the age of omni channel, ecommerce and the desire for frictionless payment processes, preventing fraud is not just about keeping bad payments out, but equally about letting the good payments through. Data really is the key – it’s what fraudsters crave in their schemes to extract money, but it’s also the best way to fight fraudulent payments. It enables merchants to reward good customers and provide them with a seamless checkout experience, while at the same time stopping fraudsters – who will try stolen credit cards across multiple devices, networks and email addresses.

The post Using data science to prevent fraud appeared first on Artificial Intelligence.