Tag: artificial intelligence

Data-driven machine learning model development is a critical strategy for financial institutions to stay ahead of their competition, and according to IDC, remains a strategic priority for technology buyers.  Improved operational efficiency, increased innovation, enhanced customer experiences and employee productivity are among the primary business objectives for organizations that choose to invest in artificial intelligence (AI) and machine learning (ML), according to IDC’s 2022 CEO survey.   While models have been around for some time, the volume of models and scale at which they are utilized has proliferated in recent years. Models are also now appearing in more regulated aspects of the business, which demand increased scrutiny and transparency.   Implementing an effective model development process is key to achieving business goals and complying with regulatory requirements. While ModelOps, the governance and life cycle management of a wide range of operationalized AI models, is becoming more popular, most organizations are still at relatively low levels of maturity. It's important for key stakeholders to implement best practices and accelerate the model development and deployment lifecycle.   Read the IDC Spotlight Challenges impeding machine learning model development  Model development involves many processes, from wrangling data, analysis, to building a model that is ready for deployment, that all need to be executed in a timely manner to ensure proper outcomes. However, it is challenging to manage all these processes in today’s complex environment.   Modeling challenges include:  Infrastructure: Necessary factors like storage and compute resources incur significant costs, which can keep organizations from evolving their machine learning capabilities.   Organizational: Implementing machine learning applications requires talent, like data scientists and data and machine learning engineers.  Operational: Piece meal approaches to ML tools and technologies can be cumbersome, especially on top of data being housed in different places across an organization, which can make pulling everything together challenging.  Opportunities for improvement are many While there are many places where individuals can focus on improving model development and deployment, there are a few key places where we see individuals experiencing some of the most time-consuming hang-ups.   Data wrangling and preparation   Respondents to IDC's 2022 AI StrategiesView Survey indicated that they spend nearly 22% of their time collecting and preparing data. Pinpointing the right data for the right purpose can be a big challenge. It is important for organizations to understand the entire data universe and effectively link external data sources with their own primary first party data. This way, stakeholders can have enough data that they trust to effectively train and build models.   Model building  While many tools have been developed in recent years to accelerate the actual building of models, the volume of models that often need to be built can be difficult given the many conflicting priorities for data teams within given institutions. Where possible, it is important for organizations to use templates or sophisticated platforms to ease the time to build a model and be able to repurpose elements that may already be working for other models within the business.   Improving Model Velocity Experian’s Ascend ML BuilderTM is an on-demand advanced model development environment optimized to support a specific project. Features include a dedicated environment, innovative compute optimization, pre-built code called ‘Accelerators’ that simply, guide, and speed data wrangling, common analyses and advanced modeling methods with the ability to add integrated deployment.  To learn more about Experian’s Ascend ML Builder, click here.   To read the full Technology Spotlight, download “Accelerating Model Velocity with a Flexible Machine Learning Model Development Environment for Financial Institutions” here.  Download spotlight *This article includes content created by an AI language model and is intended to provide general information. 

From science fiction-worthy image generators to automated underwriting, artificial intelligence (AI), big data sets and advances in computing power are transforming how we play and work. While the focus in the lending space has often been on improving the AI models that analyze data, the data that feeds into the models is just as important. Enter: data-centric AI. What is a data-centric AI? Dr. Andrew Ng, a leader in the AI field, advocates for data-centric AI and is often credited with coining the term. According to Dr. Ng, data-centric AI is, ‘the discipline of systematically engineering the data used to build an AI system.’1 To break down the definition, think of AI systems as a combination of code and data. The code is the model or algorithm that analyzes data to produce a result. The data is the information you use to train the model or later feed into the model to request a result. Traditional approaches to AI focus on the code — the models. Multiple organizations download and use the same data sets to create and improve models. But today, continued focus on model development may offer a limited return in certain industries and use cases. A data-centric AI approach focuses on developing tools and practices that improve the data. You may still need to pay attention to model development but no longer treat the data as constant. Instead, you try to improve a model's performance by increasing data quality. This can be achieved in different ways, such as using more consistent labeling, removing noisy data and collecting additional data.2 Data-centric AI isn't just about improving data quality when you build a model — it's also part of the ongoing iterative process. The data-focused approach should continue during post-deployment model monitoring and maintenance. Data-centric AI in lending Organizations in multiple industries are exploring how a data-centric approach can help them improve model performance, fairness and business outcomes. For example, lenders that take a data-centric approach to underwriting may be able to expand their lending universe, drive growth and fulfill financial inclusion goals without taking on additional risk. Conventional credit scoring models have been trained on consumer credit bureau data for decades. New versions of these models might offer increased performance because they incorporate changes in the economic landscape, consumer behavior and advances in analytics. And some new models are built with a more data-centric approach that considers additional data points from the existing data sets — such as trended data — to score consumers more accurately. However, they still solely rely on credit bureau data. Explainability and transparency are essential components of responsible AI and machine learning (a type of AI) in underwriting. Organizations need to be able to explain how their models come to decisions and ensure they are behaving as expected. Model developers and lenders that use AI to build credit risk models can incorporate new high-quality data to supplement existing data sets. Alternative credit data can include information from alternative financial services, public records, consumer-permissioned data, and buy now, pay later (BNPL) data that lenders can use in compliance with the Fair Credit Reporting Act (FCRA).* The resulting AI-driven models may more accurately predict credit risk — decreasing lenders' losses. The models can also use alternative credit data to score consumers that conventional models can't score. Infographic: From initial strategy to results — with stops at verification, decisioning and approval — see how customers travel across an Automated Loan Underwriting Journey. Business benefit of using data-centric AI models Financial services organizations can benefit from using a data-centric AI approach to create models across the customer lifecycle. That may be why about 70 percent of businesses frequently discuss using advanced analytics and AI within underwriting and collections.3 Many have gone a step further and implemented AI. Underwriting is one of the main applications for machine learning models today, and lenders are using machine learning to:4 More accurately assess credit risk models. Decrease model development, deployment and recalibration timelines. Incorporate more alternative credit data into credit decisioning. AI analytics solutions may also increase customer lifetime value by helping lenders manage credit lines, increase retention, cross-sell products and improve collection efforts. Additionally, data-centric AI can assist with fraud detection and prevention. Case study: Learn how Atlas Credit, a small-dollar lender, used a machine learning model and loan automation to nearly doubled its loan approval rates while decreasing its credit risk losses. How Experian helps clients leverage data-centric AI for better business outcomes During a presentation in 2021, Dr. Ng used the 80-20 rule and cooking as an analogy to explain why the shift to data-centric AI makes sense.5 You might be able to make an okay meal with old or low-quality ingredients. However, if you source and prepare high-quality ingredients, you're already 80% of the way toward making a great meal. Your data is the primary ingredient for your model — do you want to use old and low-quality data? Experian has provided organizations with high-quality consumer and business credit solutions for decades, and our industry-leading data sources, models and analytics allow you to build models and make confident decisions. If you need a sous-chef, Experian offers services and has data professionals who can help you create AI-powered predictive analytics models using bureau data, alternative data and your in-house data. Learn more about our AI analytics solutions and how you can get started today. 1DataCentricAI. (2023). Data-Centric AI.2Exchange.scale (2021). The Data-Centric AI Approach With Andrew Ng.3Experian (2021). Global Insights Report September/October 2021.4FinRegLab (2021). The Use of Machine Learning for Credit Underwriting: Market & Data Science Context. 5YouTube (2021). A Chat with Andrew on MLOps: From Model-Centric to Data-Centric AI *Disclaimer: When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably.

The Fed launched FedNow, a new instant payment service. While it offers advantages, there's concerns that fraudsters may exploit it with fraud schemes.

To drive competitive growth and customer retention, banks must find innovative ways to elevate the banking customer experience.

"Grandma, it’s me, Mike.” Imagine hearing the voice of a loved one (or what sounds like it) informing you they were arrested and in need of bail money. Panicked, a desperate family member may follow instructions to withdraw a large sum of money to provide to a courier. Suspicious, they even make a video call to which they see a blurry image on the other end, but the same voice. When the fight or flight feeling settles, reality hits. Sadly, this is not the scenario of an upcoming Netflix movie. This is fraud – an example of a new grandparent scam/family emergency scam happening at scale across the U.S. While generative AI is driving efficiencies, personalization and improvements in multiple areas, it’s also a technology being adopted by fraudsters. Generative AI can be used to create highly personalized and convincing messages that are tailored to a specific victim. By analyzing publicly available social media profiles and other personal information, scammers can use generative AI to create fake accounts, emails, or phone calls that mimic the voice and mannerisms of a grandchild or family member in distress. The use of this technology can make it particularly difficult to distinguish between real and fake communication, leading to increased vulnerability and susceptibility to fraud. Furthermore, generative AI can also be used to create deepfake videos or audio recordings that show the supposed family member in distress or reinforce the scammer's story. These deepfakes can be incredibly realistic, making it even harder for victims to identify fraudulent activity. What is Generative AI? Generative artificial intelligence (GenAI) describes algorithms that can be used to create new content, including audio, code, images, text, simulations, and videos. Generative AI has the potential to revolutionize many industries by creating new and innovative content, but it also presents a significant risk for financial institutions. Cyber attackers can use generative AI to produce sophisticated malware, phishing schemes, and other fraudulent activities that can cause data breaches, financial losses, and reputational damage. This poses a challenge for financial organizations, as human error remains one of the weakest links in cybersecurity. Fraudsters capitalizing on emotions such as fear, stress, desperation, or inattention can make it difficult to protect against malicious content generated by generative AI, which could be used as a tactic to defraud financial institutions. Four types of Generative AI used for Fraud: Fraud automation at scale Fraudulent activities often involve multiple steps which can be complex and time-consuming. However, GenAI may enable fraudsters to automate each of these steps, thereby establishing a comprehensive framework for fraudulent attacks. The modus operandi of GenAI involves the generation of scripts or code that facilitates the creation of programs capable of autonomously pilfering personal data and breaching accounts. Previously, the development of such codes and programs necessitated the expertise of seasoned programmers, with each stage of the process requiring separate and fragmented development. Nevertheless, with the advent of GenAI, any fraudster can now access an all-encompassing program without the need for specialized knowledge, amplifying the inherent danger it poses. It can be used to accelerate fraudsters techniques such as credential stuffing, card testing and brute force attacks. Text content generation In the past, one could often rely on spotting typos or errors as a means of detecting such fraudulent schemes. However, the emergence of GenAI has introduced a new challenge, as it generates impeccably written scripts that possess an uncanny authenticity, rendering the identification of deceit activities considerably more difficult. But now, GenAI can produce realistic text that sounds as if it were from a familiar person, organization, or business by simply feeding GenAI prompts or content to replicate. Furthermore, the utilization of innovative Language Learning Model (LLM) tools enables scammers to engage in text-based conversations with multiple victims, skillfully manipulating them into carrying out actions that ultimately serve the perpetrators' interests. Image and video manipulation In a matter of seconds, fraudsters, regardless of their level of expertise, are now capable of producing highly authentic videos or images powered by GenAI. This innovative technology leverages deep learning techniques, using vast amounts of collected datasets to train artificial intelligence models. Once these models are trained, they possess the ability to generate visuals that closely resemble the desired target. By seamlessly blending or superimposing these generated images onto specific frames, the original content can be replaced with manipulated visuals. Furthermore, the utilization of AI text-to-image generators, powered by artificial neural networks, allows fraudsters to input prompts in the form of words. These prompts are then processed by the system, resulting in the generation of corresponding images, further enhancing the deceptive capabilities at their disposal. Human voice generation The emergence of AI-generated voices that mimic real people has created new vulnerabilities in voice verification systems. Firms that rely heavily on these systems, such as investment firms, must take extra precautions to ensure the security of their clients' assets. Criminals can also use AI chatbots to build relationships with victims and exploit their emotions to convince them to invest money or share personal information. Pig butchering scams and romance scams are examples of these types of frauds where AI chatbots can be highly effective, as they are friendly, convincing, and can easily follow a script. In particular, synthetic identity fraud has become an increasingly common tactic among cybercriminals. By creating fake personas with plausible social profiles, hackers can avoid detection while conducting financial crimes. It is essential for organizations to remain vigilant and verify the identities of any new contacts or suppliers before engaging with them. Failure to do so could result in significant monetary loss and reputational damage. Leverage AI to fight bad actors In today's digital landscape, businesses face increased fraud risks from advanced chatbots and generative technology. To combat this, businesses must use the same weapons than criminals, and train AI-based tools to detect and prevent fraudulent activities. Fraud prediction: Generative AI can analyze historical data to predict future fraudulent activities. By analyzing patterns in data and identifying potential risk factors, generative AI can help fraud examiners anticipate and prevent fraudulent behavior. Machine learning algorithms can analyze patterns in data to identify suspicious behavior and flag it for further investigation. Fraud Investigation: In addition to preventing fraud, generative AI can assist fraud examiners in investigating suspicious activities by generating scenarios and identifying potential suspects. By analyzing email communications and social media activity, generative AI can uncover hidden connections between suspects and identify potential fraudsters. To confirm the authenticity of users, financial institutions should adopt sophisticated identity verification methods that include liveness detection algorithms and document-centric identity proofing, and predictive analytics models. These measures can help prevent bots from infiltrating their systems and spreading disinformation, while also protecting against scams and cyberattacks. In conclusion, financial institutions must stay vigilant and deploy new tools and technologies to protect against the evolving threat landscape. By adopting advanced identity verification solutions, organizations can safeguard themselves and their customers from potential risks. To learn more about how Experian can help you leverage fraud prevention solutions, visit us online or request a call

Learn how AI analytics helps lenders improve their underwriting.

With predictive custom machine learning models, lenders can target the right audience, score applicants more accurately, and mitigate credit risk.

Lenders are increasingly using artificial intelligence (AI) and machine learning (ML) throughout the customer lifecycle and access to these advanced tools is expanding.

What goals should you set to make financial inclusion a reality? How can success be quantified? This checklist can help you become more inclusive.

Experian’s Ascend Intelligence Service platform has been named “Best Consumer Lending Product” in the sixth annual FinTech Breakthrough Awards.

Download the new global insights report report to learn about consumer desires and business behaviors as we move further through the digital evolution.

Whether looking to increase resources or focus on artificial intelligence and machine learning, growth is the name of the game.

Chatbots, reduction of manual processes and explainability were all hot topics in a recent discussion between two leading data leaders.

Dive into the ways artificial intelligence and digital identity interact and the benefits a clear identity strategy can have for the entire user journey.

Shri Santhanam, Executive VP and GM of Experian's Global Analytics and Artificial Intelligence talks advanced analytics and AI in lending in recent podcast.