What are chatbots?
And how can you combine them with analytics?
In today’s digital world, you’ve probably interacted with a chatbot. Consider some familiar scenarios.
- Thank you for visiting our site. How can I help you today?
Perhaps you’ve been looking at a new pair of shoes and a chat window pops up with a friendly greeting, asking if you need help. Or you’ve asked Siri, Alexa or Google to schedule a meeting, remind you about an upcoming task or set a timer for the cookies in the oven. You may have even used ChatGPT to help craft a letter, brainstorm strategies and concepts, or write computer code for a class project.
Dating back to the 1960s, chatbots have a fascinating history. Today they can be powerful tools for businesses, customers and individuals alike. Technologies like generative artificial intelligence (AI) have made conversations with these "bots" surprisingly human-like, providing answers and solutions in real time.
Defining chatbots
A chatbot is a form of conversational artificial intelligence (AI) designed to simplify human interaction with computers. Using a computer program that simulates human conversation, chatbots can understand and respond to user questions and input through spoken and written language.
Rudimentary chatbots use rules to follow specific paths based on user input. They are commonly used to answer simple questions or route customers to log a ticket. These bots are widespread, so you may encounter them on commercial websites, phone trees, messaging apps – like Facebook Messenger – and other social media platforms.
More sophisticated chatbots use technologies like transformer-based large language models (LLMs) to process customer queries and provide human-like responses. LLMs help the bots understand question intent, despite typos or translation barriers.
As the conversation continues, sophisticated chatbots learn and gather information to adapt to user preferences and provide personalised responses and recommendations – serving as a digital AI assistant. They can engage in complex conversations on everything from technology to the best ingredients for a family dinner.
Some examples of voice assistants include Siri, Alexa and Google Assistant. Examples of chatbots based on generative AI technology include OpenAI ChatGPT, Google Bard, and Meta Llama2.
Learn about generative AI
Explore the core analytics technologies that power chatbots – including generative AI – and learn how to use the technology in a meaningful way.
The value of chatbots – and primary applications
Across industries, businesses use chatbots to respond to customer demands around the clock. Enhance the customer experience. Improve accessibility. And streamline customer service and e-commerce.
There are many ways chatbots can help in interactions with users and customers. Here are just a few:
- Customer service. Many businesses use chatbots as a first contact for customer support. Almost every industry employs them to help customers navigate their websites, answer simple queries and find relevant points of contact.
- E-commerce. Retail companies and telecommunication providers use chatbots as an additional interaction channel for their customers. These bots are designed to lead customer interactions through a linear process flow to complete requests or transactions. When needed, they can initiate human intervention by escalating requests to a customer service representative.
- Virtual assistants. Personal virtual assistants like Alexa have risen in popularity as they’ve become more broadly available and are easily embedded into consumers’ daily lives. People use them to quickly retrieve information, schedule appointments and interact with smart home features. With the rise of generative AI, customers and bots can interact in an increasingly human-like way.
Generative AI chatbots
With generative AI, chatbots go beyond simply answering or predicting answers – they generate new data as their primary output. For example, users can provide a few words to describe an idea, like some basic information they’d like to include in a speech, and the bot can create a full-length script in seconds. It can even go back and forth and provide changes until the speech is perfect.
Chatbots are programmed to simulate human conversation and exhibit intelligent behaviour that is equivalent to that of a human. Mary Beth Moore AI and Language Analytics Strategist SAS
How do chatbots work?
Chatbots communicate through speech or text. Both rely on artificial intelligence technologies like machine learning and natural language processing.
Natural language processing is a branch of artificial intelligence that teaches machines to read, analyse and interpret human language. This technology gives chatbots a baseline for understanding language structure and meaning. NLP, in essence, allows the computer to understand what you are asking and how to appropriately respond.
“Chatbots are programmed to simulate human conversation and exhibit intelligent behaviour that is equivalent to that of a human,” says Moore. “With developments in deep learning and reinforcement learning, chatbots can interpret more complexities in language and improve the dynamic nature of conversation between human and machine.”
Essentially, a chatbot tries to match what you’ve asked to an intent that it understands. The more a chatbot communicates with you, the more it understands and the more it learns to communicate like you and others with similar questions. Your positive responses reinforce its answers, and then it uses those answers again.
Chatbot applications in analytics
Personal assistants like Siri and Alexa are a complex type of chatbot designed to respond to a wide range of scenarios and queries, from current weather and news updates to personal calendars, music selections and random questions. Chatbots with a specific purpose, like routing customer complaints or inquiries, are designed with a more limited scope of potential answers and replies.
At SAS, we’re developing different ways to incorporate chatbots into business dashboards or analytics platforms. These capabilities have the potential to expand the audience for analytics results and attract new and less technical users.
“Chatbots are a key technology that could allow people to consume analytics without realising that’s what they’re doing,” says Oliver Schabenberger, SAS Executive Vice President, Chief Operating Officer and Chief Technology Officer. “Chatbots create a humanlike interaction that makes results accessible to all.”
Introducing chatbot functionality into analytics solutions provides a number of capabilities that marry analytics with conversational capabilities:
- The chatbot can automatically query and describe large corporate or public data sets.
- Users can request summarised or analysed results verbally by saying, for instance, “Which marketing campaigns are generating the most leads this quarter?”
- The chatbot can provide the answer and then offer additional information or suggest a related report to view based on patterns in the data and in previous related queries.
- You can ask the chatbot to share the results with others, and that will happen automatically.
You can even combine chatbots with specialised analytics solutions to perform explicit tasks within the application.
Enhancing marketers’ creativity and efficiency: An example
AI-powered assistants in SAS® Customer Intelligence 360 provide tools to help modern digital marketers with their efforts across the entire customer engagement journey.
Using generative AI technologies, the assistant interfaces with a customer’s chosen LLM to understand customer behaviour and marketing trends. Not only can it help brainstorm customer audiences and journeys, it also helps marketers craft compelling and channel-specific creatives as well as engaging content tailored to different platforms.
The results of generative AI, at their core, are a reflection of us, humans. ... Consumers must continue to apply critical thinking whenever interacting with conversational AI and avoid automation bias (the belief that a technical system is more likely to be accurate and true than a human). Reggie Townsend Vice President, Data Ethics Practice SAS
Talking to solar panels
A facility manager at a large solar farm needed a tool to monitor and control solar panels when away from the computer. A chatbot was designed using SAS® for facility management that analyses live streaming data from the solar panels.
The facility manager can now ask the chatbot directly about equipment status and each panel’s energy generation, then receive a summary of the energy output by day, month or season. A mobile chat interface extends the capabilities to technicians so they can query the application when they’re outside restarting a panel or monitoring the condition of panels in extreme weather conditions.
More time to fight fraud
One financial services nonprofit combined a chatbot with analytics to help reduce identity theft. The chatbot interacts with victims online or in phone calls to coach them through the proper protective steps, depending on their situation. It identifies cyberattacks, scams, frauds and privacy issues and the actual loss, ranging from wallets to passwords.
Based on this analysis, the chatbot asks specific questions to collect required information and recommends next steps to the victim. This streamlined approach gives humans in the call centre more time to focus on case resolution.
It’s all about communication
Both of these bots use natural language processing to anticipate conversational topics and manage a typical conversational flow. They respond by giving answers or advice based on results calculated with analytics or AI algorithms.
“Chatbot technology makes AI accessible to all of us, and it uses AI to do it,” says Schabenberger.
All kinds of organisations are starting to see exciting possibilities from combining chatbots with AI analytics. But even though the technology – NLP, AI, deep learning – seems complicated, it all goes back to one simple concept: communication.
Recommended reading
- How data visualisation helps crack down on crimeAcross the world, law enforcement agencies are making more intensive use of data visualisation technologies. They gain a real-time view of locations, layered with crime, traffic, geospatial, weather and other data. This means decisions are based on solid, robust data and resources allocated to guide intervention and crime prevention. Data visualisation can make this possible for you too.
- Model risk management: Vital to regulatory and business sustainabilitySloppy model risk management can lead to failure to gain regulatory approval for capital plans, financial loss, damage to a bank's reputation and loss of shareholder value. Learn how to improve model risk management by establishing controls and guidelines to measure and address model risk at every stage of the life cycle.
- frtb: a wait and see strategy could be riskyFRTB, fundamental review of the trading book, is a regulation that changes how banks analyse market risk in the trading book to address systemic challenges.