Maximizing Growth: The Power of AI Unleashed in Payments

Boris Bialek and Jack Yallop
February 12, 2024 | Updated: May 13, 2024
#genAI

This post is also available in: Deutsch, Français, Español, Português, Italiano, 한국어, 简体中文.

Artificial Intelligence (AI) technologies are an integral part of the banking industry. In areas such as risk, fraud, and compliance, for example, the use of AI has been commonplace for years and continues to deepen. The success of these initiatives (and others), and the potential to unlock further benefits, is driving further investment in this area in 2024, with Generative AI attracting particular interest.

Financial tech analyst Celent created a report commissioned by MongoDB and Icon Solutions that dives into how AI is currently being used in the banking industry today, as well as some of the key use cases for AI adoption in payments to improve operational agility, automate workflows, and increase developer productivity.





Download Celent’s report: Harnessing the Benefits of AI in Payments to discover how you can make the most of your AI investments and unlock the limitless possibilities that AI holds for the future of payments.

Unlocking a range of workflow and product enhancements

AI technologies are used today to address a wide range of different workflows and customer-facing services from process automation and optimization in the middle and back office, to areas such as real-time risk and liquidity management, cashflow forecasting, and service personalization in the front office. Virtual assistants and bots have also become an important part of the customer support process.

In this blog, we'll cover some of the key findings from Celent’s Harnessing the Benefits of AI in Payments report and what this means for the banking and payments industry.

Advanced analytics, intelligent automation, and AI technologies lead the investment agenda in 2024

Over time, banks have steadily increased their investments in projects to make better and more efficient use of data. In part, this has been driven by the need to respond to rising customer expectations over the speed and quality of digital services, but it also reflects a growing understanding of the true value of account and transaction data. Most important of all, though, has been enabling the technologies required to deliver use cases supported by AI and advanced analytics.

It is no surprise to see that projects supported by data analytics and AI technologies are high on the agenda globally. Advanced analytics and machine learning investments are a leading technology priority for 33% of corporate banks, ranking higher than projects relating to robotics and automation (a focus for 31% of the market). Artificial intelligence and natural language processing (NLP) are not far behind and were highlighted as a priority by 28% of banks.

Many are also exploring Generative AI

While the excitement around genAI is understandable given the obvious potential, the conversation became more nuanced through the latter part of 2023. This is understandable given the complexities of applying large language models (LLMs) to potentially sensitive customer data, as well as broader regulatory concerns over the explainability (and potential auditability) of LLM outputs. That said, there are many areas in which genAI is already being used to support advisors and relationship managers and further innovation in areas such as this is expected. According to the report, 58% of banks are evaluating or testing Generative AI in some capacity while a further 23% have projects using this technology in their roadmap.

Emerging use cases for AI in payments and the potential revenue growth

A lack of developer capacity is one of the biggest challenges for banks when it comes to delivering payment product innovation. Banks believe the product enhancements they could not deliver in the past two years due to resource constraints would have supported a 5.3% growth in payments revenues. With this in mind and the revolutionary transformation with the integration of AI, financial institutions must consider how to free up developer resources to make the most of these opportunities.

As the payments industry continues to evolve, the integration of AI is poised to reshape the landscape, offering innovative solutions that prioritize security, efficiency, and personalized user experience. The emerging use cases for AI in payments are a testament to its transformative potential in shaping the future of financial transactions.

Leveraging modern technologies to make the most of AI adoption

In the rapidly evolving landscape of AI, constant technological advancements and evolving customer needs necessitate strategic investments. To stay competitive, banks and payment providers should not only focus on current product enhancements but also future-proof their capabilities through payment infrastructure modernization. When adopting advanced technologies like AI and ML which require data as the foundation, organizations often grapple with the challenge of integrating these innovations into legacy systems due to their inflexibility and resistance to modification. For example, adding a new payment rail and a new customer access point could be very difficult. Establishing a robust data architecture with a modern data platform that enables banks to enrich the payments experience by consolidating and analyzing data in any format in real-time, driving value-added services and features to consumers. The following recommendations will help ensure financial services organizations can unlock the transformative potential of generative AI at scale while ensuring privacy and security concerns are adequately addressed:

  • Train AI/ML models on the most accurate and up-to-date data, thereby addressing the critical need for adaptability and agility in the face of evolving technologies. By unifying data from backend payment processing to customer interactions, banks can surface insights in real-time to create a seamless, connected, and personalized customer journey.

  • Future-proof with a flexible data schema capable of accommodating any data structure, format, or source. This flexibility facilitates seamless integration with different AI/ML platforms, allowing financial institutions to adapt to changes in the AI landscape without extensive modifications to the infrastructure.

  • Address security concerns with built-in security controls across all data. Whether managed in a customer environment or through MongoDB Atlas, a fully managed cloud service, MongoDB ensures robust security with features such as authentication (single sign-on and multi-factor authentication), role-based access controls, and comprehensive data encryption. These security measures act as a safeguard for sensitive financial data, mitigating the risk of unauthorized access from external parties and providing organizations with the confidence to embrace AI and ML technologies.

  • Launch and scale always-on and secure applications by integrating third-party services with APIs. MongoDB's flexible data model and ability to handle various types of data, including structured and unstructured data, is a great fit for orchestrating your open API ecosystem to make data flow between banks, third parties, and consumers possible.

The MongoDB Atlas developer data platform puts powerful AI and analytics capabilities directly in the hands of developers and offers the capabilities to enrich payment experiences by consolidating, ingesting, and acting on any payment data type instantly. MongoDB Atlas is designed to help financial services organizations overcome data challenges. It features a flexible document data model and seamless third-party integration capabilities that are necessary to create composable payment systems that scale effortlessly, and are always-on, secure, and ACID compliant.

Stay ahead of the curve — download Celent’s report now and unlock the limitless possibilities that AI holds for the future of payments. If you prefer a visual exploration, or a discussion featuring Celent, Icon Solutions, and MongoDB, register for our upcoming webinar, Using AI to Unlock New Opportunities in Payments with Celent, Icon Solutions, and MongoDB.

If you would like to discover more about building AI-enriched payment applications with MongoDB, take a look at the following resources:

← Previous

发挥 GenAI 的强大功能需要考虑的 4 个主要因素

人工智能正以前所未有的速度发展，而生成式 AI (GenAI) 处于这场变革的前沿。GenAI 拥有广泛的功能，涵盖文本生成以及音乐和艺术创作。但是，GenAI 的真正独特之处在于它能够深入理解上下文，生成的输出与人类输出极为相似。它不仅仅是与智能聊天机器人对话。GenAI 拥有改变行业的潜力，可提供更丰富的用户体验并解锁新的可能性。 在接下来的数月和数年内，我们将见证那些利用 GenAI 蕴藏的强大能力的应用程序崭露头角，这些应用程序可以提供前所未有的各种功能。与现在广受欢迎的聊天机器人（如 ChatGPT）不同，用户不一定会发现 GenAI 正在后台工作。但在后台，这些新应用程序将结合使用信息检索和文本生成，以实时提供真正个性化且与上下文有关的用户体验。此过程被称为检索增强生成，或简称 RAG。 那么，检索增强生成 (RAG) 是如何运作的，以及数据库在此过程中发挥着什么作用？下面我们将更深入地探讨 GenAI 领域及其数据库要求。 请查看我们的 AI 资源页面，来详细了解如何使用 MongoDB 构建采用 AI 技术的应用程序。 训练 AI 基础模型所面临的挑战 GenAI 面临的主要挑战之一是无法访问私有或专有数据。AI 基础模型（ 大型语言模型 (LLM) 是其子集）通常针对公开可用的数据进行训练，但无法访问机密或专有信息。即使这些数据位于公共域中，也有可能已经过时且不太相关。LLM 在识别最近的事件或很新的知识方面也存在局限性。而且，如果没有适当的指导，LLM 可能会生成错误的信息，这在大多数情况下均不可接受。 数据库在应对这些挑战方面发挥着重要作用。应用程序可以使用数据库来检索相关数据并将其作为上下文包含在提示中，而不是直接向 LLM 发送提示。例如，银行应用程序可以从传统数据库中查询用户的交易数据，将该数据添加到提示中，然后将这一经过设计的提示发送至 LLM。此方法可确保 LLM 生成准确的最新回复，消除了数据丢失、过时以及不准确的问题。 针对 GenAI 应用程序选择数据库时需考虑的 4 个因素 当所有人都可以访问相同的工具和知识库时，企业想要利用 GenAI 实现真正的竞争优势就没那么容易了。相反，实现差异化的关键来自于在由基础模型和 LLM 提供支持的生成式 AI 的基础之上， 对您自己的独特专有数据进行分层 。在选择数据库以充分发挥由 GenAI 提供支持的应用程序的潜力时，组织应重点考虑四个主要因素： 可查询性：数据库需要能够支持丰富的表达式查询和二级索引，以提供实时、上下文感知的用户体验。无论查询的复杂性或数据库中存储的数据大小如何，此功能均可确保在数毫秒内完成数据检索。 灵活的数据模型：GenAI 应用程序通常需要不同类型和格式的数据，称为多模式数据。为了适应这些不断变化的数据集，数据库应具有灵活的数据模型，支持轻松载入新数据，而无需更改模式、修改代码或发布版本。对于关系数据库而言，使用多模式数据可能具有挑战性，因为关系数据库是设计用于按照严格的模式规则来处理结构化数据，其中的信息会被整理到包含行和列的表中。 集成向量搜索：GenAI 应用程序可能需要针对不同类型的数据（如自由形式文本、音频或图像）执行语义查询或相似性查询。向量数据库中的向量嵌入支持语义查询或相似性查询。向量嵌入会捕获数据的语义含义和上下文信息，使其适合用于处理各种任务，如文本分类、机器翻译和情感分析。数据库应提供集成的向量搜索索引，让两个单独的系统保持同步变得简单，并确保开发者使用统一的查询语言。 可扩展性：由于 GenAI 应用程序的用户群和数据规模在增长，数据库必须能够动态地横向扩展，以支持不断增长的数据量和请求率。对横向扩展分片提供原生支持可确保数据库存在的限制不会阻碍业务增长。 理想的数据库解决方案：MongoDB Atlas MongoDB Atlas 是一个功能强大的多用途平台，用于处理 GenAI 的独特需求。MongoDB 使用的强大查询 API 可轻松处理多模式数据，让开发者能够用更少的代码交付更多功能。MongoDB 被开发者评为最受欢迎的文档型数据库。对开发者而言，使用文档既简单又直观，因为文档会映射到面向对象的编程中的对象，与关系数据库中数不尽的行和表相比，开发者更熟悉前者。灵活的模式设计考虑到了数据模型的不断发展以满足 GenAI 用例的需求，这些用例本身就是多模式。通过使用分片，Atlas 可以横向扩展以支持由 GenAI 提供支持的应用程序所导致的数据量和请求量的大幅增长。 MongoDB Atlas Vector Search 能够以原生方式嵌入向量搜索索引，因此无需维护两个不同的系统。Atlas 会不断地使用源数据确保 Vector Search 索引为最新状态。开发者可以使用单个端点和查询语言来构建将常规数据库查询过滤器与向量搜索过滤器结合使用的查询。这样可以消除摩擦，为开发者提供了快速制作原型并交付 GenAI 解决方案的环境。 结语 GenAI 已准备好重塑行业，并为各个行业提供创新的解决方案。借助合适的数据库解决方案，GenAI 应用程序可以蓬勃发展，提供准确、上下文感知和动态的数据驱动型用户体验，来满足当今快节奏的数字环境日益增长的需求。使用 MongoDB Atlas，组织可以在敏捷性、生产力和业务增长方面释放潜能，在快速发展的生成式 AI 领域提供竞争优势。 要了解有关 Atlas 如何帮助组织集成并处理 GenAI 和 LLM 数据的更多信息，请下载我们的白皮书《 借助 MongoDB 将生成式 AI 和高级搜索嵌入到您的应用程序中 》。如果您有兴趣在贵组织中利用生成式 AI，请立即 联系我们 ，了解我们如何帮助您实现数字化转型。

February 8, 2024
Next →

The MongoDB AI Applications Program: Delivering Customer Value

When people ask me about MongoDB, I tell them that they’ve probably interacted with MongoDB without realizing it. In fact, many of the world’s leading companies—including 70% of the Fortune 100—are powered by MongoDB. Everything we do at MongoDB is about serving our customers, but that often happens in the background, where our work is invisible to many users. In my case, that means building an ecosystem of partners who enable customer innovation. A recent example is how MongoDB teamed up with Amazon Web Services (AWS) and Amazon Bedrock to help Base39 —a Brazilian fintech provider—automate loan analysis, decreasing decision time from three days to one hour, and reducing cost per loan analysis by 96%. And there’s the Indian company IndiaDataHub, which joined the MongoDB AI Applications Program (MAAP) to access AI expertise, in-depth support, and a full spectrum of technologies to enhance AI functionality within IndiaDataHub’s analytics platform. This includes connecting relevant data in MongoDB with Meta's AI models to perform sentiment analysis on text datasets. I could go on and on—after all, tens of thousands of MongoDB’s customers have success stories like these. Enabling customer success is precisely why we launched MAAP last summer, and why the program has evolved since. Customers tell us that they want to take advantage of AI, but they’re unsure how to navigate a fast-moving market, how to control costs, and how to unlock business value from their AI investments. So with MAAP, MongoDB offers customers a full AI stack and an integrated set of professional services to help them keep pace with the latest innovations, identify the best AI use cases, and to help them future-proof AI investments. With today’s announcement , Capgemini, Confluent, IBM, QuantumBlack, AI by McKinsey, and Unstructured have joined the 22 companies that now comprise the MAAP partner network. Which means that the MAAP ecosystem (which was founded with Accenture, Anthropic, Anyscale, Arcee AI, AWS, Cohere, Credal, Fireworks AI, Google Cloud, gravity9, LangChain, LlamaIndex, Microsoft Azure, Nomic, PeerIslands, Pureinsights, and Together AI) offers additional cutting-edge AI integration and solutions to customers—and more ways to set them on the path to AI success. CentralReach: Making an impact on autism with AI More than 150 customers have already gotten involved with MAAP, but I’m particularly excited to share the work of CentralReach . CentralReach provides an AI-powered electronic medical record (EMR) platform that is designed to improve outcomes for children and adults diagnosed with autism and related intellectual and developmental disabilities (IDD). Prior to working with MongoDB and MAAP, CentralReach was looking for an experienced partner to further connect and aggregate its more than 4 billion financial and clinical data points across its suite of solutions. CentralReach leveraged MongoDB’s document model to aggregate the company’s diverse forms of information from assessments to clinical data collection, so the company could build rich AI-assisted solutions on top of its database. Meanwhile, MAAP partners helped CentralReach to design and optimize multiple layers of its comprehensive buildout. All of this will enable CentralReach to support initiatives such as value-based outcome measurement, clinical supervision, and care delivery efficacy. With these new data layers in place, providers will be able to make substantial improvements to their clinical delivery to optimize care for all those they serve. “As a mission-driven organization, CentralReach is always looking to innovate on behalf of the clinical professionals—and the more than 350,000 autism and IDD learners—that we serve globally,” said Chris Sullens, CEO of CentralReach. “So being able to lean on MongoDBs database technology and draw on the collective expertise of the MAAP partner network—in addition to MongoDB’s tech expertise and services—to help us improve outcomes for our customers and their clients worldwide has been invaluable.” Working backward from customer needs The addition of Capgemini, Confluent, IBM, QuantumBlack, AI by McKinsey, and Unstructured to the MAAP partner network offers customers additional technology and AI support options. It also builds on MongoDB’s larger partner ecosystem , which is designed to give customers flexibility and choice. By working closely with our partners on product launches, integrations, and real-world challenges, MongoDB has been able to bring a better understanding of the challenges facing customers—and to give them the resources and confidence to move forward with groundbreaking technology like AI . Examples of support MAAP has offered customers include: Guidance on chunking strategies for an AI-native healthcare provider providing patient recommendations based on complex data sources Collaboration on advanced retrieval techniques to improve response accuracies for a large consultancy to automate manual research Evaluation of embedding models for multi-modal data stores for a well-known automaker developing diagnostic applications Guidance on architectures for complex agentic workflows for a mature enterprise technology provider augmenting customer service workflows One way we offer this support is through the MAAP Center of Excellence (CoE). The MAAP CoE comprises AI technical experts from across MongoDB and the MAAP partner ecosystem who collaborate with customers to understand their challenges, technical requirements, and timelines. The MAAP CoE can then recommend custom full-stack architectures and implementation best practices, optimized for the customer’s specific use case and requirements. Indeed, customization is intrinsic to MAAP: MongoDB and our MAAP partners will meet customers wherever they are to help them achieve their goals. For example, if an organization wants to fully own its AI application development, MongoDB and partners can provide guidance and expertise. And in cases where customers want hands-on support, we can help speed projects with professional services. Ultimately, we want MAAP customers—and anyone who works with MongoDB’s partner ecosystem at large—to feel empowered to own their application development, and to transform challenges into opportunities. Let’s build the next big thing together! To learn more about building AI-powered apps with MongoDB, see MongoDB’s AI Resources Hub , the Partner Ecosystem Catalog , or visit the MAAP page . And check out our partner Confluent’s own blog post about MAAP!

December 2, 2024