Unqork + MongoDB: Use a Single View of the Customer to Enhance the User Experience

Gabriela Preiss
March 8, 2022 | Updated: July 8, 2022
#Partners

To remain competitive in financial services, companies must find new ways to optimize the customer experience as a means to boost loyalty and capture market share. One of the biggest challenges companies of all sizes face is unifying disparate data sources to create a single view of the customer.

Unification enables companies to efficiently surface relevant customer information and data-backed insights to inform strategies, and build personalized customer experiences to delight end-users and optimize processes.

Unfortunately, unification is easier said than done. Many firms struggle with disparate data in siloed systems across the organization. That is where MongoDB and Unqork can be a game changer.

With the combination of Unqork’s industry-first no-code application platform and MongoDB, financial services are able to ingest data from multiple upstream and legacy sources at scale, unify them into one central data platform, and push them downstream to internal applications or specialized third-party services.

Unify your data, enhance the customer experience

With MongoDB, you can build a single view of anything faster with a smaller investment. A single view application aggregates data from multiple sources into a central repository to create a holistic view of anything.

You can integrate data across the enterprise, whether to provide a firm-wide view of asset and counterparty exposure or a single view of your customer for fraud detection and Know Your Customer (KYC) requirements. MongoDB provides:

  • Data agnosticism: MongoDB can incorporate any type of data, no matter the source, while providing all the features needed to build a powerful application.

  • Accelerated development: Your teams move faster with MongoDB because its dynamic schemas let them iterate changes quickly. They spend less time prepping data for storage, and more time pushing the project forward.

  • Improved search and filtering: MongoDB's expressive query language, indexing, and aggregation capabilities make it possible to find and filter the data, no matter how the business needs to access it.

The Unqork platform empowers organizations to rapidly build custom applications in complex, highly regulated industries such as financial services. With Unqork, organizations can:

  • Integrate disparate ecosystems: Seamlessly connect new custom applications with third-party solutions and legacy systems to streamline the entire client experience — from onboarding to transacting — improving risk decisioning while reducing costs by up to 30%.

  • Orchestrate complex business processes: Create, connect, and automate complex, customized workflows to design unified, omnichannel experiences for clients, reducing manual processes by up to 50%. This is particularly apt when it comes to complex, multistep processes such as lending, transactional workflow hubs, onboarding, and KYC.

  • Create branded digital experiences at scale: Today, clients expect Amazon-like, digital-first experiences that are intuitive and easy to navigate. Unqork’s digital portals for retail and institutional clients empower firms to create compelling, on-brand experiences for all end-users, delivering enhanced reporting and self-service capabilities to address the expectations of a new digital age.

By combining the accelerated development of Unqork with the unified single view functionality of MongoDB, companies can effectively use data to enhance user experiences and secure market share.

Success story

Faced with exponential growth, one of the world’s largest crypto-currency exchanges found itself unable to effectively manage demand with its current technology stack. Other legacy solutions were unable to help it optimize the onboarding of new institutional clients, resulting in a queue of nearly 2,000 investors, 200 of whom the company considered VIP.

To effectively address this peak in demand, the exchange tapped into the power of Unqork + MongoDB to reduce its KYC verification process from weeks to days (and in some cases mere hours for low-risk clients). This acceleration was made possible through the automation and orchestration of integrations across multiple vendors and internal systems.

Using the two platforms, the exchange transformed its customer onboarding function complete with:

  • Enhanced digital client experience: Modern, intuitive client portal with integrated chat and video tools to boost collaboration between clients and agents

  • Intelligent workflows: Dynamic workflow engine supporting customized client journeys based on entity type, product, and jurisdiction

  • Improved transparency: Seamless information flow, handoffs, and real-time tracking across internal teams and clients

  • Integrated ecosystem: Integrated ecosystem of best-in-class technologies to prefill/validate data, enabling exception-based processing

  • Risk-based compliance: A risk-based approach to optimize compliance approvals with fully integrated audit trail

Key benefits:

  • Platform integrations: Seamless integration with various KYC/AML vendors into the app

  • Real-time analytics: Any variety of data type analyzed in real time without excessive infrastructure, such as warehouse loads, and auto-scaling to adapt to whatever size (increasing/decreasing) of data the moment demands

  • Speed-of-delivery: Custom KYC verification solution delivered in 16 weeks

  • Flexible compliance: A flexible tech stack to empower the organization to future-proof against evolving regulations and compliance concerns since crypto is vulnerable to misuse and other KYC/AML challenges

And this is just the beginning. With the exchange’s firm-wide customer-first initiative, Unqork + MongoDB will become the central orchestrator across all products and locations to create a unified, end-to-end client onboarding experience.

The potential with MongoDB + Unqork

The potential business value is enormous. When correlating shareholder value with its customer-experience benchmarking, McKinsey found that, between 2009 and 2019, digital leaders delivered 55% higher shareholder returns than customer-experience laggards. Benefits include:

  • Lower administrative costs. The potential to reduce costs via digital self-service is enormous. In addition to driving down costs-per-transaction by up to 99%, Gartner estimates that 40% or more of today’s live-call volume could be handled via self-service channels.

  • Increased customer loyalty and retention. Today’s customers have little patience for slow, opaque processes that require lots of back and forth with intermediaries. The vast majority (67%) of customers prefer self-service, according to a Zendesk study. With MongoDB + Unqork, organizations can rapidly build powerful self-service functionality that provides their customers with 24/7 access to information and services.

  • More granular customer insights. By centralizing customer interactions and the data they produce, firms gain valuable insight into customer behaviors to help improve the client experience, unlock cross-sell and upsell opportunities, and guide future iterations of digital experiences to further enhance customer experiences and, ultimately, retention and customer lifetime value.

With MongoDB + Unqork, financial firms gain the flexibility required to unify client experiences and resulting data to future-proof firms to agilely pivot to address changing client and regulatory needs — at speeds that outpace their competitors.

← Previous

MongoDB.local revient à Paris le 5 avril 2022

Après une interruption de deux ans due à la pandémie, nous sommes heureux d'être enfin de retour à Paris pour MongoDB.local Paris 2022 ! Se déroulant le 5 avril 2022 au 3 Mazarium , l'événement est conçu pour aider les développeurs à découvrir de nouveaux produits et astuces, et sera rempli de contenu éducatif, de témoignages de clients, de démos techniques et de tutoriels pour vous aider à créer facilement des applications basées sur les données. Alors, pourquoi devriez-vous nous rejoindre pendant une journée à MongoDB.local Paris ? Pouvoir se retrouver en personne L'une des raisons d'y assister est simplement qu'il s'agit d'un événement en présentiel, et après les deux dernières années, nous en avons besoin. Nous avons tous fait du télétravail, et la plupart du temps, cela a fonctionné, mais il existe encore des opportunités qui sont tout simplement meilleures en personne. Il n'y a rien de tel que les conversations fortuites avec d'autres participants qui se produisent lors d'événements en présentiel, ou la session à laquelle vous assistez entre les deux qui vous tiennent vraiment à cœur et qui s'avère être exactement ce dont vous aviez besoin. Le tout pour vous donner une toute nouvelle perspective. Si vous pouvez le faire en toute sécurité, nous aimerions passer du temps avec vous à Paris pour comprendre comment vous utilisez MongoDB - ou ce que vous recherchez de MongoDB, et comment nous pouvons mieux travailler ensemble. L'importance de ces retrouvailles a été renforcée récemment lorsqu'un client a mentionné que : "Par rapport à d'autres fournisseurs de technologie, MongoDB a un caractère distinctif en ce qui concerne l'attention personnelle." Laissez-nous vous montrer ce dont il parlait ! Mais aussi virtuellement Là encore, certains des changements que le confinement nous a imposés n'ont pas été tous mauvais. Le télétravail, au moins une partie du temps, a donné à beaucoup d'entre nous plus de flexibilité dans la façon dont nous gérons notre travail et la balance entre le travail et d'autres engagements. Nous en sommes conscients ... C'est pourquoi MongoDB.local Paris 2022 sera également accessible aux participants de façon virtuelle. Vous pourrez même poser des questions à nos experts pendant les sessions. Cette nouvelle approche des événements hybrides ouvre la participation à beaucoup plus de personnes qui n'auraient peut-être pas pu y assister autrement. Les sessions resteront également disponibles en ligne après coup, donc même si vous êtes occupé le jour de l'événement, vous pouvez regarder des sessions enregistrées et toujours bénéficier des mises à jour des dirigeants et des chefs de produit de MongoDB. Updates Produits et les Rapid Releases Avec le lancement de MongoDB 5.0, nous avons introduit des “rapid releases”. C'est notre nouvelle cadence de publication qui nous permet de mettre plus rapidement entre vos mains les dernières innovations et fonctionnalités offertes par la base de données et les pilotes. Avec la version 5.1, nous avons de nouvelles fonctionnalités à discuter au-delà de ce qui a été annoncé l'été dernier, et sans attendre la prochaine version majeure. MongoDB.local Paris 2022 vous donnera l'occasion de passer en revue certaines des principales fonctionnalités introduites avec la version 5.0, telles que la prise en charge des séries chronologiques, et de voir comment ces fonctionnalités ont continué à évoluer avec les rapid releases. Workshops et tutoriels avec les Experts Produits Au-delà des présentations, certaines des sessions les plus utiles sont les workshops et tutoriels où les participants ont la possibilité d'essayer directement les produits MongoDB tels que MongoDB Atlas et MongoDB Atlas Search, et de découvrir la création de clusters et d'applications MongoDB. Ces sessions sont conçues par nos Product Managers et Experts et vous donneront la chance de comprendre les facteurs qui influencent le développement de MongoDB et comment ils s’appliquent à des situations spécifiques. En plus des tutoriels, vous aurez la possibilité de poser toutes vos questions sur les produits MongoDB à notre équipe Produits sur les stands durant toute la durée de l’événement. Témoignages clients et utilisateurs Enfin, la série d’événements MongoDB.local offre la possibilité de découvrir les expériences réelles d'autres utilisateurs. L'événement parisien vous propose les témoignages d’utilisateurs avec les présentations clés de Renault, Cdiscount et Lactalis. Il est toujours extrêmement utile d'entendre comment les clients et les utilisateurs tirent parti des capacités technologiques de MongoDB pour répondre à leurs besoins spécifiques et comment ils gèrent le processus pour atteindre ces objectifs. J’ai hâte de vous y retrouver ! Si vous me voyez vagabonder, n’hésitez pas à venir discuter, j’ai toujours adoré rencontrer les utilisateurs MongoDB et apprendre de vos expériences et découvrir comment vous utilisez notre technologie. Ah et vous pouvez vous inscrire ici avec mon code promo : DominicWellington50 . Cela vous donnera 50% de discount sur votre ticket en présentiel.

March 7, 2022
Next →

Retrieval Augmented Generation for Claim Processing: Combining MongoDB Atlas Vector Search and Large Language Models

Following up on our previous blog, AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases , we’ll pick up the conversation right where we left it. We discussed extensively how Atlas Vector Search can benefit the claim process in insurance and briefly covered Retrieval Augmented Generation (RAG) and Large Language Models (LLMs). MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More One of the biggest challenges for claim adjusters is pulling and aggregating information from disparate systems and diverse data formats. PDFs of policy guidelines might be stored in a content-sharing platform, customer information locked in a legacy CRM, and claim-related pictures and voice reports in yet another tool. All of this data is not just fragmented across siloed sources and hard to find but also in formats that have been historically nearly impossible to index with traditional methods. Over the years, insurance companies have accumulated terabytes of unstructured data in their data stores but have failed to capitalize on the possibility of accessing and leveraging it to uncover business insights, deliver better customer experiences, and streamline operations. Some of our customers even admit they’re not fully aware of all the data in their archives. There’s a tremendous opportunity to leverage this unstructured data to benefit the insurer and its customers. Our image search post covered part of the solution to these challenges, opening the door to working more easily with unstructured data. RAG takes it a step further, integrating Atlas Vector Search and LLMs, thus allowing insurers to go beyond the limitations of baseline foundational models, making them context-aware by feeding them proprietary data. Figure 1 shows how the interaction works in practice: through a chat prompt, we can ask questions to the system, and the LLM returns answers to the user and shows what references it used to retrieve the information contained in the response. Great! We’ve got a nice UI, but how can we build an RAG application? Let’s open the hood and see what’s in it! Figure 1: UI of the claim adjuster RAG-powered chatbot Architecture and flow Before we start building our application, we need to ensure that our data is easily accessible and in one secure place. Operational Data Layers (ODLs) are the recommended pattern for wrangling data to create single views. This post walks the reader through the process of modernizing insurance data models with Relational Migrator, helping insurers migrate off legacy systems to create ODLs. Once the data is organized in our MongoDB collections and ready to be consumed, we can start architecting our solution. Building upon the schema developed in the image search post , we augment our documents by adding a few fields that will allow adjusters to ask more complex questions about the data and solve harder business challenges, such as resolving a claim in a fraction of the time with increased accuracy. Figure 2 shows the resulting document with two highlighted fields, “claimDescription” and its vector representation, “claimDescriptionEmbedding” . We can now create a Vector Search index on this array, a key step to facilitate retrieving the information fed to the LLM. Figure 2: document schema of the claim collection, the highlighted fields are used to retrieve the data that will be passed as context to the LLM Having prepared our data, building the RAG interaction is straightforward; refer to this GitHub repository for the implementation details. Here, we’ll just discuss the high-level architecture and the data flow, as shown in Figure 3 below: The user enters the prompt, a question in natural language. The prompt is vectorized and sent to Atlas Vector Search; similar documents are retrieved. The prompt and the retrieved documents are passed to the LLM as context. The LLM produces an answer to the user (in natural language), considering the context and the prompt. Figure 3: RAG architecture and interaction flow It is important to note how the semantics of the question are preserved throughout the different steps. The reference to “adverse weather” related accidents in the prompt is captured and passed to Atlas Vector Search, which surfaces claim documents whose claim description relates to similar concepts (e.g., rain) without needing to mention them explicitly. Finally, the LLM consumes the relevant documents to produce a context-aware question referencing rain, hail, and fire, as we’d expect based on the user's initial question. So what? To sum it all up, what’s the benefit of combining Atlas Vector Search and LLMs in a Claim Processing RAG application? Speed and accuracy: Having the data centrally organized and ready to be consumed by LLMs, adjusters can find all the necessary information in a fraction of the time. Flexibility: LLMs can answer a wide spectrum of questions, meaning applications require less upfront system design. There is no need to build custom APIs for each piece of information you’re trying to retrieve; just ask the LLM to do it for you. Natural interaction: Applications can be interrogated in plain English without programming skills or system training. Data accessibility: Insurers can finally leverage and explore unstructured data that was previously hard to access. Not just claim processing The same data model and architecture can serve additional personas and use cases within the organization: Customer Service: Operators can quickly pull customer data and answer complex questions without navigating different systems. For example, “Summarize this customer's past interactions,” “What coverages does this customer have?” or “What coverages can I recommend to this customer?” Customer self-service: Simplify your members’ experience by enabling them to ask questions themselves. For example, “My apartment is flooded. Am I covered?” or “How long do windshield repairs take on average?” Underwriting: Underwriters can quickly aggregate and summarize information, providing quotes in a fraction of the time. For example, “Summarize this customer claim history.” “I Am renewing a customer policy. What are the customer's current coverages? Pull everything related to the policy entity/customer. I need to get baseline info. Find relevant underwriting guidelines.” If you would like to discover more about Converged AI and Application Data Stores with MongoDB, take a look at the following resources: RAG for claim processing GitHub repository From Relational Databases to AI: An Insurance Data Modernization Journey Modernize your insurance data models with MongoDB and Relational Migrator

April 18, 2024