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.

Digram depicting the solution architecture of this solution.
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.

GIF showing the responses of the Leafy personal assistant chatbot. This is a mock bot created by the MongoDB team.
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:

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:

← Previous

网易游戏分享游戏场景中MongoDB运行和分析实践

在游戏行业中，数据库的稳定和性能直接影响了游戏质量和用户满意度。在竞争激烈的游戏市场中，一个优秀的数据库产品无疑能为游戏的开发和后期的运营奠定良好的基础。伴随着MongoDB在不同类型游戏场景中的应用越来越广泛，许多知名的游戏公司都在使用MongoDB来处理他们的游戏数据。 网易游戏自成立以来与广大游戏热爱者一同成长。经过20年的快速发展，网易已跻身全球七大游戏公司之一。作为中国领先的游戏开发公司，网易一直处于网络游戏自主研发领域的前端。目前在网易游戏中，包括手游、业务数据中心以及其他内部产品等在内的多项产品都已广泛应用MongoDB。 综合考虑游戏生态、架构、稳定性和成本等因素，网易游戏的数据库架构采用了多类型服务架构，根据游戏在不同的生命周期进行选型适配。MongoDB支持副本集和分片集群模式，可根据需求进行水平扩展，选择合适的分片策略和副本集设置，为网易游戏提供了灵活性和高可用性的帮助。 如何有计划地分析MongoDB数据的过程行为以便产品决策？ 随着游戏行业的不断发展，游戏数据的规模和复杂性也在不断增加。在游戏开发过程中还需要进行大量的数据分析，用以了解玩家行为、优化游戏体验、制定营销策略等。 网易互娱数据库业务负责人郑良榉表示：“我们希望有计划地对MongoDB的过程行为数据进行体系化分析，并应用到常态化管理中，以便在与MongoDB数据库交互的过程中，能够对按需触发的业务进行实时响应。” 灵活的文档模型，让数据分析更从容 MongoDB的灵活文档模型在处理游戏中的复杂数据结构时表现尤为出色。游戏存在不同场景下大量的全量更新和增量更新行为，游戏中包括玩家信息、游戏状态、物品信息等在内的数据结构会频繁发生变化，与此同时，优化占比大的字段还可能带来工作负载的更新。MongoDB采用文档存储的方式，使用JSON格式来存储数据。每个文档可以有不同的字段和结构，这使得它非常适合处理游戏中的复杂数据。通过使用MongoDB，游戏开发人员可以随时添加或修改字段而不需要进行复杂的数据库迁移操作。 当运营需要查证玩家反馈时，比如游戏中出现装备丢失、属性不对、需要查证奖励发放情况等问题，网易游戏内部对文档历史分析提出了时效性(周期性)、可查性(可用性)、对比性(变更差异)和及时性(oplog不带索引）的要求。这是一个既要又要的选择。MongoDB使用副本集来实现数据的冗余和高可用性，而操作日志（oplog）是副本集的核心机制之一。网易游戏能够通过副本集中的oplog实现了与原始文档数据联动管理，在主节点发生故障时，可以根据oplog中的信息快速恢复数据，审计并排查问题。 多场景多应用，也能游刃有余 在一些特定的游戏场景中，历史榜单会保存所有场次的数据，周期性活动的副本战斗需要结算，单一玩家的数据玩法会不断叠加，玩家的装备属性也会越来越复杂……诸如此类的大文档数据会持续增加，从而导致批量更新慢、cache使用异常、队列等待长等问题。网易游戏通过MongoDB的定期、自动巡检，帮助产品及时发现大文档潜在问题，例如数据库负载过高、请求超时、异常错误等，从而采取相应措施，规避线上运营风险。 在游戏运营期间，索引对于服务的访问效率至关重要，无索引行为会导致实例负载变高，严重时会导致整个请求阻塞，影响游戏体验和服务稳定性。依托MongoDB，网易游戏对于人工日常的数据查询行为，在访问入口代码层面实现了实时索引检测与报警，用户可以根据提示是否继续查询行为。同时在系统层面，用户访问可按实例级别配置是否允许无索引查询，以进一步减少非预期内的误操作行为。除了使用索引外，MongoDB还可以通过查询优化来加速热点数据的查询，进一步提升QPS（每秒查询推理响应速度）。 游戏运营中会有一些突发状况，比如高峰期单一玩法异常导致请求突增、某个服务卡住导致整个实例请求阻塞等，此时分析库表级别的访问QPS（非mongostat和mongotop结果）对于找到引起问题的根因点至关重要。借助于 MongoDB 的内置功能，网易游戏实现了实时的库表 QPS 和访问延时采集以帮助产品及时发现瓶颈点。此外，客户端行为的跟踪和分析也能帮助业务发现问题来源，借助MongoDB的CurrentOP功能，网易游戏能够统计业务客户端实时会话情况，并针对当前实例节点操作进行行为检索，还能追踪某个连接操作行为。 与此同时，在数据迁移和数据分布异常的情况下，MongoDB也能有效解决阻碍技术负责人执行的最大障碍——大数据量的数据同步工作及落地后的数据管理，从而提升运维效率。 郑良榉表示，MongoDB的接入只是一个开始，如何更好地贴近业务的使用需要长期的多场景实践、探索与总结，这也是当前持续发展的方向。对MongoDB数据行为的分析能够帮助网易游戏在数据决策方面提供有效参考，从而产生更大的收益和价值。 点击注册，免费开始使用 MongoDB Atlas

November 26, 2024
Next →

AI-Powered Call Centers: A New Era of Customer Service

Customer satisfaction is critical for insurance companies. Studies have shown that companies with superior customer experiences consistently outperform their peers. In fact, McKinsey found that life and property/casualty insurers with superior customer experiences saw a significant 20% and 65% increase in Total Shareholder Return , respectively, over five years. A satisfied customer is a loyal customer. They are 80% more likely to renew their policies, directly contributing to sustainable growth. However, one major challenge faced by many insurance companies is the inefficiency of their call centers. Agents often struggle to quickly locate and deliver accurate information to customers, leading to frustration and dissatisfaction. This article explores how Dataworkz and MongoDB can transform call center operations. By converting call recordings into searchable vectors (numerical representations of data points in a multi-dimensional space), businesses can quickly access relevant information and improve customer service. We'll dig into how the integration of Amazon Transcribe, Cohere, and MongoDB Atlas Vector Search—as well as Dataworkz's RAG-as-a-service platform— is achieving this transformation. From call recordings to vectors: A data-driven approach Customer service interactions are goldmines of valuable insights. By analyzing call recordings, we can identify successful resolution strategies and uncover frequently asked questions. In turn, by making this information—which is often buried in audio files— accessible to agents, they can give customers faster and more accurate assistance. However, the vast volume and unstructured nature of these audio files make it challenging to extract actionable information efficiently. To address this challenge, we propose a pipeline that leverages AI and analytics to transform raw audio recordings into vectors as shown in Figure 1: Storage of raw audio files: Past call recordings are stored in their original audio format Processing of the audio files with AI and analytics services (such as Amazon Transcribe Call Analytics ): speech-to-text conversion, summarization of content, and vectorization Storage of vectors and metadata: The generated vectors and associated metadata (e.g., call timestamps, agent information) are stored in an operational data store Figure 1: Customer service call insight extraction and vectorization flow Once the data is stored in vector format within the operational data store, it becomes accessible for real-time applications. This data can be consumed directly through vector search or integrated into a retrieval-augmented generation (RAG) architecture, a technique that combines the capabilities of large language models (LLMs) with external knowledge sources to generate more accurate and informative outputs. Introducing Dataworkz: Simplifying RAG implementation Building RAG pipelines can be cumbersome and time-consuming for developers who must learn yet another stack of technologies. Especially in this initial phase, where companies want to experiment and move fast, it is essential to leverage tools that allow us to abstract complexity and don’t require deep knowledge of each component in order to experiment with and realize the benefits of RAG quickly. Dataworkz offers a powerful and composable RAG-as-a-service platform that streamlines the process of building RAG applications for enterprises. To operationalize RAG effectively, organizations need to master five key capabilities: ETL for LLMs: Dataworkz connects with diverse data sources and formats, transforming the data to make it ready for consumption by generative AI applications. Indexing: The platform breaks down data into smaller chunks and creates embeddings that capture semantics, storing them in a vector database. Retrieval: Dataworkz ensures the retrieval of accurate information in response to user queries, a critical part of the RAG process. Synthesis: The retrieved information is then used to build the context for a foundational model, generating responses grounded in reality. Monitoring: With many moving parts in the RAG system, Dataworkz provides robust monitoring capabilities essential for production use cases. Dataworkz's intuitive point-and-click interface (as seen in Video 1) simplifies RAG implementation, allowing enterprises to quickly operationalize AI applications. The platform offers flexibility and choice in data connectors, embedding models, vector stores, and language models. Additionally, tools like A/B testing ensure the quality and reliability of generated responses. This combination of ease of use, optionality, and quality assurance is a key tenet of Dataworkz's "RAG as a Service" offering. Diving deeper: System architecture and functionalities Now that we’ve looked at the components of the pre-processing pipeline, let’s explore the proposed real-time system architecture in detail. It comprises the following modules and functions (see Figure 2): Amazon Transcribe , which receives the audio coming from the customer’s phone and converts it into text. Cohere ’s embedding model, served through Amazon Bedrock , vectorizes the text coming from Transcribe. MongoDB Atlas Vector Search receives the query vector and returns a document that contains the most semantically similar FAQ in the database. Figure 2: System architecture and modules Here are a couple of FAQs we used for the demo: Q: “Can you explain the different types of coverage available for my home insurance?” A: “Home insurance typically includes coverage for the structure of your home, your personal belongings, liability protection, and additional living expenses in case you need to temporarily relocate. I can provide more detailed information on each type if you'd like.” Q: “What is the process for adding a new driver to my auto insurance policy?" A: “To add a new driver to your auto insurance policy, I'll need some details about the driver, such as their name, date of birth, and driver's license number. We can add them to your policy over the phone, or you can do it through our online portal.” Note that the question is reported just for reference, and it’s not used for retrieval. The actual question is provided by the user through the voice interface and then matched in real-time with the answers in the database using Vector Search. This information is finally presented to the customer service operator in text form (see Fig. 3). The proposed architecture is simple but very powerful, easy to implement, and effective. Moreover, it can serve as a foundation for more advanced use cases that require complex interactions, such as agentic workflows , and iterative and multi-step processes that combine LLMs and hybrid search to complete sophisticated tasks. Figure 3: App interface, displaying what has been asked by the customer (left) and how the information is presented to the customer service operator (right) This solution not only impacts human operator workflows but can also underpin chatbots and voicebots, enabling them to provide more relevant and contextual customer responses. Building a better future for customer service By seamlessly integrating analytical and operational data streams, insurance companies can significantly enhance both operational efficiency and customer satisfaction. Our system empowers businesses to optimize staffing, accelerate inquiry resolution, and deliver superior customer service through data-driven, real-time insights. To embark on your own customer service transformation, explore our GitHub repository and take advantage of the Dataworkz free tier .

November 27, 2024