Pedro Bereilh

2 results

Better Digital Banking Experiences with AI and MongoDB

Interactive banking represents a new era in financial services where customers engage with digital platforms that anticipate, understand, and meet their needs in real-time. This approach encompasses AI-driven technologies such as chatbots, virtual assistants, and predictive analytics that allow banks to enhance digital self-service while delivering personalized, context-aware interactions. According to Accenture’s 2023 consumer banking study , 44% of consumers aged 18-44 reported difficulty accessing human support when needed, underscoring the demand for more responsive digital solutions that help bridge this gap between customers and financial services. Generative AI technologies like chatbots and virtual assistants can fill this need by instantly addressing inquiries, providing tailored financial advice, and anticipating future needs. This shift has tremendous growth potential; the global chatbot market is expected to grow at a CAGR of 23.3% from 2023 to 2030 , with the financial sector experiencing the fastest growth rate of 24.0%. This shift is more than just a convenience; it aims to create a smarter, more engaging, and intuitive banking journey for every user. Simplifying self-service banking with AI Navigating daily banking activities like transfers, payments, and withdrawals can often raise immediate questions for customers: “Can I overdraft my account?” “What will the penalties be?” or “How can I avoid these fees?” While the answers usually lie within the bank’s terms and conditions, these documents are often dense, complex, and overwhelming for the average user. At the same time, customers value their independence and want to handle their banking needs through self-service channels, but wading through extensive fine print isn't what they signed up for. By integrating AI-driven advisors into the digital banking experience, banks can provide a seamless, in-app solution that delivers instant, relevant answers. This removes the need for customers to leave the app to sift through pages of bank documentation in search of answers, or worse, endure the inconvenience of calling customer service. The result is a smoother and user-friendly interaction, where customers feel supported in their self-service journey, free from the frustration of navigating traditional, cumbersome information sources. The entire experience remains within the application, enhancing convenience and efficiency. Solution overview This AI-driven solution enhances the self-service experience in digital banking by applying Retrieval-Augmented Generation (RAG) principles, which combine the power of generative AI with reliable information retrieval, ensuring that the chatbot provides accurate, contextually relevant responses. The approach begins by processing dense, text-heavy documents, like terms and conditions, often the source of customer inquiries. These documents are divided into smaller, manageable chunks vectorized to create searchable data representations. Storing these vectorized chunks in MongoDB Atlas allows for efficient querying using MongoDB Atlas Vector Search , making it possible to instantly retrieve relevant information based on the customer’s question. Figure 1: Detailed solution architecture When a customer inputs a question in the banking app, the system quickly identifies and retrieves the most relevant chunks using semantic search. The AI then uses this information to generate clear, contextually relevant answers within the app, enabling a smooth, frustration-free experience without requiring customers to sift through dense documents or contact support. Figure 2: Leafy Bank mock-up chatbot in action How MongoDB supports AI-driven banking solutions MongoDB offers unique capabilities that empower financial institutions to build and scale AI-driven applications. Unified data model for flexibility: MongoDB’s flexible document model unifies structured and unstructured data, creating a consistent dataset that enhances the AI’s ability to understand and respond to complex queries. This model enables financial institutions to store and manage customer data, transaction history, and document content within a single system, streamlining interactions and making AI responses more contextually relevant. Vector search for enhanced querying: MongoDB Atlas Vector Search makes it easy to perform semantic searches on vectorized document chunks, quickly retrieving the most relevant information to answer user questions. This capability allows the AI to find precise answers within dense documents, enhancing the self-service experience for customers. Scalable integration with AI models: MongoDB is designed to work seamlessly with leading AI frameworks, allowing banks to integrate and scale AI applications quickly and efficiently. By aligning MongoDB Atlas with cloud-based LLM providers, banks can use the best tools available to interpret and respond to customer queries accurately, meeting demand with responsive, real-time answers. High performance and cost efficiency: MongoDB’s multi-cloud, developer-friendly platform allows financial institutions to innovate without costly infrastructure changes. It’s built to scale as data and AI needs to grow, ensuring banks can continually improve the customer experience with minimal disruptions. MongoDB’s built-in scalability allows banks to expand their AI capabilities effortlessly, offering a future-proof foundation for digital banking. Building future-proof applications Implementing generative AI presents several advantages, not only for end-users of the interactive banking applications but also for financial institutions: Enhanced user experience encourages customer satisfaction, ensures retention, boosts reputation, and reduces customer turnover while unlocking new opportunities for cross-selling and up-selling to increase revenue, drive growth and elevate customer value. Moreover, adopting AI-driven initiatives prepares the groundwork for businesses to develop innovative, creative, and future-proof applications to address customer needs and upgrade business applications with features that are shaping the industry and will continue to do so, here are some examples: Summarize and categorize transactional information by powering applications with MongoDB’s Real-Time Analytics . Understand and find trends based on customer behavior that could positively impact and leverage fraud prevention , anti-money laundering (AML) , and credit card application (just to mention a few). Offering investing, budgeting, and loan assessments through AI-powered conversational banking experience. In today’s data-driven world, companies face increasing pressure to stay ahead of rapid technological advancements and ever-evolving customer demands. Now more than ever, businesses must deliver intuitive, robust, and high-performing services through their applications to remain competitive and meet user expectations. Luckily, MongoDB provides businesses with comprehensive reference architectures for building generative AI applications, an end-to-end technology stack that includes integrations with leading technology providers, professional services, and a coordinated support system through the MongoDB AI Applications Program (MAAP) . By building AI-enriched applications with the leading multi-cloud developer data platform, companies can leverage low-cost, efficient solutions through MongoDB’s flexible and scalable document model which empowers businesses to unify real-time, operational, unstructured, and AI-related data, extending and customizing their applications to seize upcoming technological opportunities. Check out these additional resources to get started on your AI journey with MongoDB: How Leading Industries are Transforming with AI and MongoDB Atlas - E-book Our Solutions Library is where you can learn about different use cases for gen AI and other interesting topics that are applied to financial services and many other industries.

November 26, 2024

Unlock PDF Search in Insurance with MongoDB & Superduper.io

As industries go, the insurance industry is particularly document-driven. Insurance professionals, including claim adjusters and underwriters, spend considerable time handling documentation with a significant portion of their workday consumed by paperwork and administrative tasks. This makes solutions that speed up the process of reviewing documents all the more important. Retrieval-augmented generation (RAG) applications are a game-changer for insurance companies, enabling them to harness the power of unstructured data while promoting accessibility and flexibility. This is especially true for PDFs, which despite their prevalence are difficult to search, leading claim adjusters and underwriters to spend hours reviewing contracts, claims, and guidelines in this common format. By combining MongoDB and Superduper.io you can build a RAG-powered system for PDF search, thus bringing efficiency and accuracy to this cumbersome task. With a PDF search application, users can simply type a question in natural language and the app will sift through company data, provide an answer, summarize the content of the documents, and indicate the source of the information, including the page and paragraph where it was found. In this blog, we will dive into the architecture of how this PDF search application can be created and what it looks like in practice. Why should insurance companies care about PDF Search? Insurance firms rely heavily on data processing. To make investment decisions or handle claims, they leverage vast amounts of data, mostly unstructured. As previously mentioned, underwriters and claim adjusters need to comb through numerous pages of guidelines, contracts, and reports, typically in PDF format. Manually finding and reviewing every piece of information is time-consuming and can easily lead to expensive mistakes, such as incorrect risk estimations. Quickly finding and accessing relevant content is key. Combining Atlas Vector Search and LLMs to build RAG apps can directly impact the bottom line of an insurance company. Behind the scenes: System architecture and flow As mentioned, MongoDB and Superduper.io underpin our information retrieval system. Let’s break down the process of building it: The user adds the PDFs that need to be searched. A script scans them, creates the chunks, and vectorizes them (see Figure 1). The chunking step is carried out using a sliding window methodology, which ensures that potentially important transitional data between chunks is not lost, helping to preserve continuity of context. Vectors and chunk metadata are stored in MongoDB, and an Atlas Vector Search index is created (see Figure 3). The PDFs are now ready to be queried. The user selects a customer, asks a question, and the system returns an answer, where it was found and highlights the section with a red frame (see Figure 3). Figure 1: PDF chunking, embedding creation, and storage orchestrated with Superduper.io Each customer has a guidelines PDF associated with their account based on their residency. When the user selects a customer and asks a question, the system runs a Vector Search query on that particular document, seamlessly filtering out the non-relevant ones. This is made possible by the pre-filtering field included in the search query. Atlas Vector Search also takes advantage of MongoDB’s new Search Nodes dedicated architecture, enabling better optimization for the right level of resourcing for specific workload needs. Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads, allowing you to optimize your compute resources and fully scale your search needs independent of the database. Search Nodes provide better performance at scale, delivering workload isolation, higher availability, and the ability to optimize resource usage. Figure 2: PDF querying flow, orchestrated with Superduper.io Superduper.io Superduper.io is an open-source Python framework for integrating AI models and workflows directly with and across major databases for more flexible and scalable custom enterprise AI solutions. It enables developers to build, deploy, and manage AI on their existing data infrastructure and data, while using their preferred tools, eliminating data migration and duplication. With Superduper.io, developers can: Bring AI to their databases, eliminate data pipelines and moving data, and minimize engineering efforts, time to production, and computation resources. Implement AI workflows with any open and closed source AI models and APIs, on any type of data, with any AI and Python framework, package, class or function. Safeguard their data by switching from APIs to hosting and fine-tuning your own models, on your own existing infrastructure, whether on-premises or in the cloud. Easily switch between embedding models and LLMs, to other API providers as well as hosting your own models, on HuggingFace, or elsewhere just by changing a small configuration. Build next-generation AI apps on your existing database Superduper.io provides an array of sample use cases and notebooks that developers can use to get started, including vector search with MongoDB, embedding generation, multimodal search, retrieval-augmented generation (RAG), transfer learning, and many more. The demo showcased in this post is adapted from an app previously developed by Superduper.io. Let's put it into practice To show you how this could work in practice, let’s look at, an underwriter handling a specific case. The underwriter is seeking to identify the risk control measures as shown in Figure 3 below but needs to look through documentation. Analyzing the guidelines PDF associated with a specific customer helps determine the loss in the event of an accident or the new premium in the case of a policy renewal. The app assists by answering questions and displaying relevant sections of the document. Figure 3: Screenshot of the UI of the application, showing the question asked, the LLM’s answer, and the reference document where the information is found By integrating MongoDB and Superduper.io, you can create a RAG-powered system for efficient and accurate PDF search. This application allows users to type questions in natural language, enabling the app to search through company data, provide answers, summarize document content, and pinpoint the exact source of the information, including the specific page and paragraph. If you would like to learn more about Vector Search powered apps and Superduper.io, visit the following resources: PDF Search in Insurance Github repository Search PDFs at Scale with MongoDB and Nomic Superduper.io Github, includes notebooks and examples

June 24, 2024