Improving the quality and accuracy of chatbots
How to successfully leverage partnerships to the benefit of the client?
Invenica and Volume (with the use of their product QBox) have each been able to advance the digital transformation journey of one of our shared customers (the leading global telecoms operator referred to here). This customers wants to automate 60% of support requests by 2025; with the addition of QBox, this is going to be possible.
Building on Invenica’s work, QBox has been helping optimise the NLP training data (across multiple providers) by:
-
Extracting valuable performance data
-
Offering ongoing monitoring into key metrics of customers’ automations (enabling them to dramatically increase the number of support requests that can be automated)
-
Facilitating enhanced customer support
-
Realising significant operational savings
QBox is a piece of conversational AI middleware. Once a roadmap for the transformation of the customer-support function has been drawn up, QBox helps test, understand and fix NLP training data. It also provides ongoing monitoring support after the automation and AI customer agents have been introduced.
Chatbots, voicebots, chat engines and digital humans all require NLP. Once the conversational AI has been devised and integrated by Invenica, QBox offers incredibly deep and never-seen-before analytics that enhance a customer’s investment into conversational AI. By including QBox or the right customer, Invenica can offer a full-service solution, from inception to optimisation.
When it comes to getting in touch with companies, customers really don’t want to be left hanging on the line. They want a rapid response to their queries - and they’re happy to take their business elsewhere when they don’t get this.
According to research from Hubspot, nine out of ten customers rate an ‘immediate’ response as important when they have a customer service question. This has led to a situation where two-thirds of customers have become ‘serial switchers’, changing brands due to a poor experience – something that’s costing businesses more than $75bn a year.
It’s in this context a Tier 1 bank in the Americas turned to Invenica for help. The firm’s call centre handles millions of customer calls every year. However, until recently, they relied solely on a traditional dual-tone multi-frequency (DTMF) interactive voice response (IVR), a legacy touch-tone system that was having a negative impact on the bank’s customer experience. The system’s menu tree was often difficult to use, causing customers to get lost and even abandon their calls. The bank needed a new system that could improve the customer experience and drive customer retention.
The solution was an AI conversational language platform and customer service virtual agent (VA) able to help customers find answers to their enquiries as quickly as possible – both in free speech and text. The challenge with producing and deploying such a system was that it needed to handle significant levels of complexity. The bank had set high benchmarks for performance in semantic accuracy and task completion. It also required the VA to be capable of serving customers speaking English and local dialect in a mixed-language model – something no contact centre had ever implemented before.
What we did
To develop the solution, Invenica used the technical expertise of its DisruptCX (DCX) practice, which specialises in supplying emerging technology to contact centres. Following a review of the bank’s existing systems, DCX swiftly identified a conversation language platform and VA as the solution best suited to meet the project’s needs.
From there, DCX selected a platform and designed and deployed a VA able to retain context around multiple customer queries in a single conversation. This was supported by the use of machine learning to continuously learn new patterns and improve predictability – allowing the bank to serve customers who are unable to express what they want as clearly as others.
DCX then developed and tested algorithms for dealing with the uncertainty of voice input. So, for example, where the confidence in the intent of the voice input is below 90%, the engine provides up to five inputs that it believes could be accurate. These are sorted by likelihood, with mathematical checks used to confirm which input is the most likely to be correct. Invenica added to this with an application that helped the platform to learn and improve the bank’s self-service conversion rates.
Invenica leveraged its previous R&D project experience – along with its expertise in the development of microservices – to implement the capability for continuous improvement, allowing the platform to be extended in novel ways. In developing a modern microservice ecosystem of functional components, Invenica made it easier for the platform to respond to the bank’s changing requirements while minimising disruption to the customer experience.
What we delivered
With so much complexity and uncertainty involved, the Bank needed a solution based on a scientific and research-driven approach. That’s why Invenica and DCX delivered an AI-powered conversational language platform and VA that could not only handle customer enquiries more efficiently but also learn from each one. Every conversation the platform now has with customers improves future outcomes as it encounters new scenarios and ever-more complex interactions.
The platform meets all of the bank’s KPIs for intent accuracy and task completion rates. It also provides multi-language support for customers speaking English and local dialects. Ultimately, this provides the bank with the best possible platform to improve its customer experience, drive retention rates and cut operational costs by taking the pressure off its existing systems and contact centre agents.
Trading metals can be a time-consuming and expensive process, which is why automation is the key to closing deals quickly and increasing trade volumes.
Concord is a leading global commodities group with a focus on non-ferrous metals and associated raw materials. It supplies metals to a world-wide customer base that includes automotive firms, major manufacturers and national governments. Looking to build on revenues of more than $4bn, Concord was exploring ways to increase its trading volumes – improving its market share and overall profitability. However, the firm faced a few challenges in achieving this aim.
One such issue was the lack of automation in its processes, which meant that closing deals took a more time and effort than was ideal – and made the pursuit of opportunities more difficult in some cases. Also, the time it took for individuals to manually process a deal increased the cost to do so. Increasing trade volumes at pace in this environment was tough as well. In some instances, traders were only able to complete a limited number of deals each year. New buyers were also hard to come by, and Concord was looking for new ways of reaching customers that wouldn’t be time-intensive for its traders.
This was made more challenging by the availability of individuals across the business. With three offices (in China, the UK and the US), clients in different locations didn’t always have as much access to traders as they might have wanted. To address these issues, Concord turned to Invenica to make it easier for traders to connect with new and existing buyers. Concord was confident that, with its track record for delivering digital platforms and its understanding of the industry, Invenica would be able to provide the right solution.
What we did
To begin the project, Invenica held workshops with all the relevant stakeholders within Concord to understand the pain points at every level of the trading process. This ranged from the C-Suite leaders to the traders on the ground. With the knowledge of the challenges, the markets and any restrictions, Invenica got to work on designing a responsive website that would serve as a digital marketplace. The idea was that each trader looking to sell an asset would be able to access that marketplace and publish all the information needed to attract buyers. Once they fill in an e-form about the commodity itself, they publish it and the asset appears on the marketplace.
This worked in a similar way to sites like Amazon. Buyers would access the marketplace to see available products or use the intelligent search function to find what they’re after. They could either bid on, purchase or make an offer on the product – with actions generating a notification for traders to begin engaging with the buyer.
As well as intuitive customer-facing tools, Invenica created a back-office system in the marketplace to offer extra value to Concord and its traders. Users were able to access a dashboard that provided information about trade volume, the types of product available, and all the previous or ongoing deals. To make the trading process simpler and quicker, Invenica provided an interactive form designed to reduce the time taken to share assets with potential buyers. Learning from existing platforms, the developers created an automated process that allowed made it as easy as possible for users to upload forms featuring multiple pages of information.
Another feature Invenica built into the platform was a chatbot that allowed potential buyers to enquire about products not showing as available on the marketplace. It also gave them the ability to ask any questions or leave remarks for traders.
What we delivered
In three months, Invenica delivered a digital marketplace that accelerated Concord’s trading process and allowed it to drive growth in trading volumes. Traders can now upload information and deploy assets to the marketplace in minutes. Engagement with buyers is easy too, with traders getting notifications for orders so they can make decisions quickly and effectively. Then they can start the process of the trade itself – getting deals closed as swiftly as possible. The new platform has also created a new inbound channel for Concord. Finding new customers before meant calling people directly – the firm relied on word-of-mouth sales. With the new marketplace, Concord now attracts traffic it wasn’t previously able to access.
Invenica continues to provide ongoing support and maintenance for the marketplace, making sure it delivers 24/7 uptime.
To be successful, a trading platform must – above all else – make transactions as easy as possible for its users. The challenge with this is that ‘easy’ is an ever-shifting concept that encompasses a wide range of factors.
For example, speed is a key component for traders in volatile markets. They need to be able to action a trade at the touch of a button if they’re to protect profitability against price fluctuations. However, expectations in this area change constantly as performance improves – and platforms need to make sure they can keep up.
This isn’t the only area where customer and market expectations are changing rapidly. The increase in mobile adoption among businesses – along with the cultural weight of smartphone use in everyday life – is driving a move towards mobile trading. In 2018, six out of ten traders were using mobile apps to complete trades – a figure that’s likely to be significantly higher now (especially with remote working becoming the norm). Today, traders are demanding platforms that not only help them make transactions quickly and easily but also allow them to do this on the move. ‘Easy’ in trading has moved away from the mouse and keyboard to embrace mobility. This is the backdrop for LMAX asking Invenica to develop the mobile functionality of its trading platform. Looking to keep up with market expectations, LMAX wanted the ability to provide its clients with an end-to-end mobile solution – all without losing its unique selling point, the speed of its exchange and trading systems.
The idea was to deliver a mobile trading platform that enabled users to easily trade a growing number of complex derivative products. This complexity would be mirrored in the project itself, with the need to meet strict standards in critical areas like financial services compliance and mobile security. The mobile functionality had to recreate the same trading environment as LMAX’s main platform. This meant meeting anti-money laundering (AML) and know your customer (KYC) requirements – a key piece of the puzzle considering that by 2019 a new record of $8.14bn in fines handed out to firms for AML breaches globally.
What we did
Cybersecurity was also a major concern and with the attacks on mobile devices rising dramatically year on year a key requirement. Invenica had to make sure that this new entry point to LMAX’s trading data didn’t create any vulnerabilities for hackers to exploit – especially with no control over the devices being used to access and trade on the platform. The challenge was then providing all of this as part of a high-speed, high-performance platform. Invenica tapped into its considerable experience of complex logic handling over mobile networks, ensuring that this new process was able to match the exchange performance expected by LMAX’s clients. This included the development of protections against any errors caused by mobile networks that might prevent a trade or create conflicting data.
Invenica also worked in tandem with the LMAX development team to track the changes that were continuously altering the architecture and integration services of the main LMAX platform. The new mobile trading environment had to replicate functionality or risk failing to meet users’ needs. Ultimately, the Invenica team planned, designed and executed the delivery of an end-to-end mobile trading platform that retained LMAX’s hallmarks of high speed and high performance. The project took everything that makes LMAX’s desktop platform a leading matching venue for traders and brought it to life in the palm of traders’ hands as part of a simple but effective mobile experience.
What we delivered
The new mobile platform featured full compatibility for iOS and Blackberry devices (even including several models known for presenting a barrier to the implementation of high-performance services).
The completed mobile solution included the following key features:
• Strict Financial Services compliance
• Best-of-breed security using government-approved algorithms
• Protection against errors driven from the mobile network
• Full iOS & Blackberry compatibility
Invenica’s platform was more than able to deliver performance in line with key performance requirements specified by LMAX – succeeding in its aim to make trading as easy as possible for clients.
When investing in bullion, you want to know two critical things: that your wealth is secure, and that you can access it whenever you need to, add to your holdings, or sell it on. These are compelling reasons to keep your investment in a vault, where you know it’ll stay safe and sound. They’re also two major driving forces behind the move toward mobile trading.
BullionVault, the world’s largest online investment gold service, provides private investors with access to the professional bullion market. It also prides itself on its ability to deliver this in a way that’s safer, cheaper and easier than any other firm.
This means that operators who haven’t invested in the tools to improve their service experience (whether customer- or agent-side) become vulnerable to customer attrition. There’s also the likelihood of falling behind competitors when it comes to overall innovation. On the other side of the story, Telcos who already have the technology to deliver a smooth customer experience are freed up to focus on improvements in agility and performance – all of which add to their brand image. It was in this context that the customer service function of a leading global telecoms operator was struggling to deliver the right level of value to customers. As well as causing a high operating cost of costumer care, this situation resulted in a low customer satisfaction scores (NPS, CSAT, FRT, AHT, etc.) and poor reviews on sites like Trustpilot – which, in turn, influenced the company’s brand perception. Offering a wide variety of products and services, the operator required a complex suite of tools to support its customer care teams. It also struggled to make the most of its data. The sheer amount collected and exchanged had created huge sets of information that no one had been able to curate or analyse.
On top of this, the lack of performance data made it difficult to identify the key areas for improvement. It was hard to tell which product support areas were underperforming – and what tools they needed to improve. And this made it near impossible to take a targeted approach to the problem. This is why BullionVault asked Invenica to develop the mobile functionality of its trading platform, with the aim of attracting new investors, increasing trading volumes and improving customer retention rates. The key to this was creating a seamless, integrated and – above all – simple user experience across web and mobile app interfaces.
What we did
Convenience was a critical factor in the mobile platform’s development. BullionVault wanted the lowest possible barrier to entry for users, so Invenica leveraged HTML5 and Bootstrap to create an intuitive interface designed for simplicity – allowing investors and traders to get all the information they needed in the palms of their hands. Using the app would be as simple as the trading process itself.
In addition to this, Invenica made sure that the mobile experience included all the features available to users on the existing web platform. After all, it didn’t matter how easy the app was to use if it didn’t deliver the features that BullionVault’s clients expected.
It was also vital for the new system to integrate with the web platform. The syncing of orders and access to market data are seen as the two most important capabilities for any trading app to provide, which would affect the ability for BullionVault to attract new investors. Invenica saw to it that users were able to see the same information across iOS, Android, mobile web and desktop.
Despite the need for simplicity, security was another key concern. This was no surprise given users were technically able to access bullion vaults from wherever they were in the world. Creating new access points to BullionVault’s platform increased the risk of vulnerability and attack, so Invenica built effective security features into the app – making it as safe as the vaults themselves.
What we delivered
Overall, the Invenica team was able to deliver a new, convenient, and secure mobile experience for trading commodities. It also helped BullionVault to create a new channel opportunity to acquire new customers and differentiate its offering against competitors.
Developing an intuitive interface that offered easy access to BullionVault’s trading platform for new and existing users alike, Invenica was able to:
- Reduce the number of support requests
- Increase trading volumes using the app
- Drive higher existing customer retention rates
Thanks to Invenica, BullionVault users were now able to access the professional bullion market from mobile devices, enjoying a seamless and integrated experience that made their trading activities safer, easier and cheaper.
Good news travels, but bad news travels quicker – and further. Three-quarters of people tell at least one person about a poor customer service experience. And, now, with the reach and immediacy of social media, how firms respond to and manage issues plays a huge role in building brand image and perception.
In a recent survey, 56% of customers said the most important thing in customer service is that their issue is resolved satisfactorily. It’s no surprise then that the same survey found that eight out of ten customers spend more with companies that give them a good customer experience.
This means that operators who haven’t invested in the tools to improve their service experience (whether customer- or agent-side) become vulnerable to customer attrition. There’s also the likelihood of falling behind competitors when it comes to overall innovation. On the other side of the story, Telcos who already have the technology to deliver a smooth customer experience are freed up to focus on improvements in agility and performance – all of which add to their brand image.
It was in this context that the customer service function of a leading global telecoms operator was struggling to deliver the right level of value to customers. As well as causing a high operating cost of costumer care, this situation resulted in a low customer satisfaction scores (NPS, CSAT, FRT, AHT, etc.) and poor reviews on sites like Trustpilot – which, in turn, influenced the company’s brand perception.
Offering a wide variety of products and services, the operator required a complex suite of tools to support its customer care teams. It also struggled to make the most of its data. The sheer amount collected and exchanged had created huge sets of information that no one had been able to curate or analyse.
On top of this, the lack of performance data made it difficult to identify the key areas for improvement. It was hard to tell which product support areas were underperforming – and what tools they needed to improve. And this made it near impossible to take a targeted approach to the problem.
What we did
For Invenica, the first step to solving the problem was to identify the core challenges across the relevant teams – including customer care teams onshore and offshore and those dedicated to specific markets. This was achieved by surveying the relevant stakeholders: customer agents, sales representatives, managers, product owners and customers. The survey was important for gathering insights, determining actual performance and setting targets for a healthy customer satisfaction index.
Invenica then designed a roadmap for the transformation of the company’s customer support function – featuring steps like the rationalisation of tools, plus the introduction of automation and AI customer agents. The next step was to carry out a rationalisation of the firm’s customer care tools. This process involved the creation of new customer journeys and the streamlining of data – making it easier for agents to respond to queries effectively and efficiently. Invenica designed and developed the missing components and assembled the customer care platform, taking care to integrate it with existing legacy systems to provide functions such as identity, billing and supply chain management.
What we delivered
The changes and additions made by Invenica removed some huge barriers to performance (such as slow information discovery, a lack of insight from customer history and defragmented sets of tools for different products and services). They also increased the capacity to resolve customer queries through the automation of support tasks. All in all, the process reduced handling times, increased the number of solved tickets and delivered a better overall quality of service.
Taking an agile approach, Invenica transformed the tools incrementally, introducing time and cost savings to go with the improved customer experience. It also integrated new tools with the right systems where required – allowing agents to seamlessly discover and access the data and information they need.
This transformation extended into a review and reform of operating models. It also featured the creation of adequate training and documentation materials to help users get to grips with new features, including:
• An intelligent search engine
• Integration with telephony
• Identity management
• Chat engines (text/voice)
The team implemented QBox to continuously monitor and improve the accuracy of chatbot, you can learn more about this here.
With the tools in place, Invenica set new KPIs to match user expectations. The teams are now constantly measuring the customer satisfaction index to make sure their results reflect the vision and targets set by their leadership.