Actions and words are meaningless without a context. It is a common misconception that meaning is contained within words. Nothing could be further from the truth.


Think about the word ‘interest’. It may assume different meanings depending upon the context. In banking, the word ‘interest’ can be used to either refer to money paid at regular intervals for deposits or loans or, to express curiosity to learn about a product or service. Double entendre and other complexities associated with sentence construction muddles up conversations. It is only by remaining in context that anybody can make sense of it.


Similarly, in customer-brand engagements, contextual understanding and shared meanings are necessary to architect meaningful conversations. This is ever so vital in the case of chatbots. Unlike face-to-face interactions, visual cues are unavailable. Text and voice remains the only medium for a chatbot to analyze user sentiments. Hence, contextual awareness should be the root of its intelligence however quixotic that statement might sound!


From General Contextual Awareness to Specific Contextual Awareness A combination of operational factors like industry and geography function act as a premise upon which the product and service related knowledge is built. Basic domain modelling can endow chatbots with general contextual awareness. But that alone is not sufficient in giving a human-like conversational experience.


The difficulty that organisations face in engineering meaningful, intelligent and personalized conversational experiences is partly due to their limited understanding of contextual setting of a conversation. Every time a customer interacts with a brand, it is not an event happening in isolation. It is the residual impact of previous conversations.


Chat history is a crucial factor in shaping the landscape of customer-brand engagements. An enterprise chatbot can’t simply operate with a simplistic, need-based understanding of context. To put it in perspective, let’s analyze the following conversations between a banking chatbot and a customer.


Chat without context . Chat with context
Chat without context Chat with context

The customer experience is far better if the chatbot could remember the previous chat and/or customer’s preferences. Such an approach can enhance customer experience drastically.


How to build a contextual chatbot? Context-aware chatbots look back into history and determine the most accurate response. Usually, the amount of history the bot can search can be configured.


Enterprises can harness customer information from third party systems such as CRM, sharepoints and chat logs to contextualize the conversation and quickly solve issues for an existing customer. In the case of new customer, there exist a plethora of tools that can identify a unique visitor.


Using Natural Language Processing (NLP) and Machine Learning, Chatbots like CogniCor understand what the user is trying to convey and generate precise response on the fly. Such bots do not follow a script/menu and are not keyword-based. With substantial amounts of training data and increase in conversations, contextual bots automatically self-learns what customers are asking and adds context to a bucket that the machine understands.


An enterprise chatbot need not be a super intelligent machine straight out of the science fiction. Rather, it should be an AI-powered system that has meaningful conversations with customers. Empowering chatbots with context awareness is a powerful way to engage customers with human-like responses, provide personalised information and drive higher conversions.


About CogniCor CogniCor is one of the fastest growing providers of cognitive chatbots for the financial services industry. A spin-off from Europe’s top Artificial Intelligence Institute, the company has done deployments across the globe and featured in Forrester, Gartner and IDC reports. Over the last four years, CogniCor has facilitated over 5 million interactions and delivered ROI worth $100m.


Originally published in Medium



Having the right skills are worth their weight in gold, especially when operating within the modern-day market that is known for its agility and operational precision. Perhaps, this is one of the main reasons why the industry is always on the lookout for professionals with dynamic skills, the ones who can reap higher customer satisfaction. But these prized skills, as is the case, are rarely available in the market. This makes the ones available an even more precious commodity.


The challenge that every growing business faces today is to deliver an exceptional customer experience and at the same time utilize the skills of its human resources to its full capacity. AI-driven chatbots are making this dream come true while boosting customer satisfaction and increasing efficiency of operations. How? Let’s find out.


What are artificial intelligence-driven conversational chatbots, and what difference do they make?

Chatbots are applications that can converse through auditory or textual methods. They are designed and trained with use cases relating to customer queries and are aimed at delivering a human-like experience to the end-user. Since people are more inclined to having fluidic conversations, cognitive capabilities, which can simulate how a human brain functions, reasons, and more importantly learns, become pivotal.Users characteristically do not want to get lost in the myriad of details, for example of a home loan or new credit card, while clicking several menus and sub-menus, especially when a simple question can fetch an instant answer. Hence it is natural that chatbots herald the next evolution of digital customer touch points from today’s static web experience.


A traditional chatbot has limited use cases, given that responses have to be defined for every question the bot encounters. The customer experience is therefore, often frustrating and stops abruptly when the bot can no longer understand the conversation. Conversely, AI-driven chatbots constantly build their knowledge through self-learning algorithms and create an extensive database that paves the way for fluidic interactions. They process their interactions with customers and identify and remember slang, grammatical mistakes and other errors. This gives them a considerable edge over traditional chatbots. But something that takes the customer experience to another level is their ability to understand the customer’s intent, analyse what the customer needs and provide tailored recommendations. Such chatbots leverage historic data to come up with apt replies leading to higher rates of conversion.


There are significant potential applications of this technology. For instance, a personalized financial virtual assistant could interact with you, answer your questions, resolve your issues and also advise you on your next investment decisions, based on your current spending and earning data. Your IT Support could be entirely handled at the first level by such virtual agents, before escalating to appropriate human agents. These “bots” will become mainstream interaction channels for enterprises since customers will manage 85% of their relationship with the enterprise without interacting with a human, as predicted by Gartner.


Evolved, consistent, and available round-the-clock: Human? Chatbots?

To err is human. Therefore, one of the biggest advantages of cognitive capabilities in chatbots is that despite displaying all the characteristics of a human, they do not replicate flaws and disadvantages inherent to our species. Chatbots have an unmatched consistency in operations and do not make errors which are more likely to affect the overall conversion rate. They also have above-benchmark performance when it comes to customer satisfaction, and deliver considerably higher customer acquisition rates as compared to the human workforce.


A pain point that impacts customer experience is that they need to needlessly wait before they are either transferred to a customer agent or a technical expert. At times, especially during peak hours or during a resource crunch, customers have to wait for minutes before their queries are looked into. This includes customers with easily resolvable, non-technical queries, who are left waiting and often disgruntled with the brand. An AI-driven chatbot instantly deflects such interactions, rather than making such customers wait needlessly. This also decreases the total workload on the technical experts, allocating more time for query resolution of customers with complex issues. Chatbots also minimise the operational expenditure of businesses significantly, something that can be further diverted to enhance other elements of the customer experience.


Emerging possibilities: Solving the market conundrum with Intelligence

There used to be a time when AI appeared to be a distant reality. Today, this is not the case. AI and its constituent technologies, such as Machine Learning, are being used for a range of actual market deployments and innovation-driven companies are further increasing the footprint of the technology. This year, OCBC Bank, Singapore, collaborated with a leading AI platform to develop a specialized home and renovation loan chatbot service “Emma”. Emma logged 20,000 conversations within 4 months and more than 10% of these conversations converted into mortgage loan sales prospects, translating into USD 10 Million in home loans. 9 out of 10 customers who interacted with Emma also stated that they were satisfied with the bot’s service.


Originally published in Sundary Guradian Live



I’m in!


The above stated statement can range from an affirmation to an assertive sentence providing the location of the speaker. In plain language, its literal meaning can vary from “I agree” and “I include myself” to “I’m inside (something)” or even “I have logged into my mail”. Here, the context of the entire conversation acts as a premise for the statement and understanding it becomes necessary to deduce to its actual meaning.


Customer service is all about understanding customers and providing a valid and relevant solution to their queries. These queries can be related to raising a complaint, obtaining product information, or seeking a resolution to a complaint. In understanding the user’s requirement, one of the key players is the Natural Language Processing (NLP) capability.


Natural Language Processing and its limitations:

Natural Language Processing, also known as NLP, is the process of applying computational techniques to deduce natural language comprising written text or speech. It is a taxonomy-based approach which identifies keyword and matches them with the taxonomy tree to understand the meaning of a statement. Though it has relatively high accuracy, it cannot identify the statement’s semantic variants which can have a meaning other than the predefined sets.


Thus, NLP alone cannot help the system in understanding a user’s requirements by itself. A majority of ‘chat bots’, as they are called in mass market parleys, are NLP at different scales and do not implement Artificial Intelligence and hence follow the above mentioned approach. The user’s intent in such cases needs to be well understood and the context of the user query needs to be established. This can be achieved only by complementing NLP with machine learning and cognitive capabilities.


But why do you need to be careful?

Implementing customer assistance that leverages NLP alone can, given its limitations, cause an adverse situation for the brand. These services have limited use cases that can be easily identified by the customer during interaction. Once being aware of the fact, a majority of customers tend to lose interest in the conversation – resulting in lower customer satisfaction.


Moreover, this issue resolution methodology by and large follows the ‘brute force’ or ‘canned approach’ technique without issue resolution. In such systems, responses are driven by URLs fetched from indexed queries to answer databases where keyword mapping leads to a set of the most probable or matching answers. These answers lack accuracy and can vary dramatically for a similarly phrased statement. Such a gap in experience hampers the customer experience and creates a negative perception about the brand rather than adding a positive value to it, the goal behind all customer service operations.


So, NLP is ineffective without the assistance of AI sciences including machine learning, deep learning and cognitive sciences.


Advantages of an AI-based system:

One of the key deficiencies of human-driven customer assistance is the lack of consistency in responses. A good agent can give great responses resulting in a happy customer, while on a bad day, the same agent can cause a completely different situation. This problem is addressed with cognitive NLP systems where responses are always standard and consistent. While NLP can be called the science of literal translation of the user’s speech or text, AI acts as the brain that makes it understandable to the system – especially with contrast to the context of discussion, user intent, and its logical implementation – and helps it respond like a cognitive system with human-like answers.


70 to 75 percent closure of customer queries, be it informative or issue resolutions, is a milestone for companies to achieve. This high accuracy and completion rate can easily be attained with the help AI platforms. Also, customer care issues can move to virtual assistants and provide satisfactory results only when such systems are incorporated. With machine learning, the system also improvises consistently and adopts a strategy that is best suited for a case-specific customer. This further increases its effectiveness along with enhancing customer satisfaction, improving conversion rates, and most importantly boosting growth of the business.


Making the system cognitive is imperative to offer well-tailored solutions to customers without affecting the brand perception. Smarter implementations using NLP and AI – especially with cognitive assistance – have proved their viability even across complex industries including banking, insurance, and telecom. As they are now focussing on new market segments, businesses across sectors are expected to experience increased flexibility while also substantially reducing their operational expenses.


Originally published in YourStory