By Wayne Thompson
A chatbot is a computer program that uses natural language processing (NLP) and artificial intelligence to simulate human conversation and derive a response. Essentially, it’s a machine that can chat with you or respond to your chatter.
Chatbots can save time and money when used to handle simple, automated tasks. Need a few examples? Chatbots can:
- Send you notifications about family birthdays.
- Order your favorite Chinese food with a simple command.
- Help book your next vacation getaway.
- Update you on your account balance and when your next payment is due.
How hot are chatbots?
Bots were hot in 2017 but many bots are still primitive. 2018 will be the year of the next generation bot, often called the intelligent virtual assistant (IVA). These assistants incorporate more sophisticated NLP and deeper AI to infer a better response.
They can understand emotion through deep learning facial recognition models that detect happiness, anger, surprise and sadness. They recognize location and use opt-in historical data about your transactions to foster a more human interaction. Plus, these assistants learn continuously over time through machine learning.
Some of the smartest chatbots even consider what I like to call the now moment – analyzing the temporal state of what you are doing now to better understand and assist you. This type of relevance and intelligence will lead to a much higher adoption rate.
When meeting with customers, I’m beginning to see a lot of interest in intelligent virtual assistants from financial service companies. And incorporating AI into these assistants is a top priority. One bank is building a personal investment advisor that uses supervised learning to predict and suggest what securities or funds a client should buy.
The advisor bot also considers market sentiment of stocks as part of the stock pick. Sentiment is calculated by applying text analytics on articles and posts about the stock. The bank wants its financial advisor bot to answer tough questions like, “What the is the impact of interest rates on crude commodities prices?”
Another insurer is computing sentiment for clients from the call center in real time. A key data point for that bot is the polarity score, which measures the emotion expressed in a sentence. This score can be used as another predictor for cross-sell and up-sell models. The polarity can be positive, negative or neutral.
At SAS, we’re building a fraud surveillance bot to better detect fraud, especially anti-money laundering fraud. Since fraud is a rare event, it’s naturally hard to detect. An important goal in this area is to minimize the false positive rate, so the fraud detection bot doesn’t classify legitimate transactions as fraud.
Sometimes an investigator can triage a false positive in just a few minutes but often it can take 8 hours or more – which isn’t a good use of time. By contrast, the bot summarizes variables for classifying fraud and automatically selects a probability threshold cutoff to minimize the false positive rate.
Since the fraud investigative process is labor intensive, banks are hiring more and more investigators to meet demand. A bot that deploys powerful machine learning pipelines to accurately detect fraud can help focus investigative resources where they are really needed.
The bot can adapt to new fraud approaches and attacks through continuous machine learning. Natural language generation provides narrative summaries about why a transaction or set of transactions if fraudulent or not. This speeds the investigative process and helps with compliance.
How to build your own bots
Another goal at SAS is also to build open, extensible software for customers who aspire to build their own bots or virtual assistants. We plan to deliver a natural language interaction (NLI) service that converts keyed or spoken natural language text into application-specific, executable code.
In other words, it automatically maps a user’s command to the correct action, like: “summarize sales” or “score a truncation for fraud.” We’ll also include a natural language generation (NLG) service for developing narrative summaries and templated reports. The goal is to reason on input with the NLI service and explain on output with the NLG service.
This article was republished with permission from SAS.