NLP-powered smart bots improve transaction rates between customers

These bots use a combination of natural language processing (NLP), artificial intelligence (AI) and machine learning (ML) technologies to understand natural language in spoken or written forms.

“One of the largest insurance companies saw its workforce shrink by 10% at the start of the COVID-19 pandemic, while customer query volume grew 5x. In terms of handling transactions, their chatbot can successfully close around 78% of their transactions,” says Shekhar Murthy, senior vice president of solutions and professional services at Yellow.AI.

It’s not just niche corporations that are benefiting from bots contributing to actual purchases from customers. Gaurav Singh, Founder & CEO, Automated Chat Platform Verloop.io says, “With Naykaa, we handle around 68% of customer interactions without any human intervention. Most customer requests such as adding or changing items, changing delivery addresses and changing payment methods are fully automated today.”

For another of Singh’s clients, Abu Dhabi Islamic Bank (ADIB), Verloop.io claims to successfully automate 88% of all customer conversations “including acquisition, support, engagement and retention”.

The companies claim that this level of automation is helping businesses simplify transactions and convert queries into purchases successfully. Talking about ease of transaction, Birud Sheth, Co-Founder & CEO, Unicorn Startup Gupshup says, “CreditWise Capital today leveraged automation to reduce two wheeler loan processing time at dealerships to as low as three minutes. Have used – Days instead of Multiple. It also integrates coordination with credit bureaus like Experian to accept customer applications through WhatsApp, allowing them to approve loan purchases within minutes.”

Yellow.ai supports a variety of companies that are receiving transactions directly through the chatbot.

For Bharat Petroleum, Murthy said, Voicebot processed over 500,000 LPG cylinder bookings in just four weeks, and even recognized different bids.

“The Madhya Pradesh Electricity Board uses an NLP-enabled voice bot that deploys five dialects of Hindi to decipher similar words when spoken by different users in their own way. The accuracy in voice questions in Hindi is less than 90s. For languages ​​beyond Hindi, our bots are capable of working at over 80% to understand accuracy,” says Murthy.

Interestingly, voice automation is one area where chatbot providers see growth potential in terms of actual transactions. “Chat was old school, but now the whole logic is that it has to be an AI across multiple channels – be it telephone line bots, chatbots or other things. While the use of chat has increased in India, it is still lagging behind global countries This is mainly because real India does not like to chat in English,” said Ganesh Gopalan, CEO and co-founder of Gnani.ai. He said the voice interface on an app or even a telephone line conversation has allowed the company to handle multiple languages.

Raghu Ravinutala, CEO of Yellow.AI, said his company’s services today process more than 10 million voice automation minutes each month, compared to almost zero voice automation minutes processed a year ago.

Talking about claiming to be the “world’s largest insurer”, Yellow.AI says that its multilingual voice bot automation, in fact, provides 12% higher efficiency in terms of successfully converting user transactions – As against live, human agents. This is an area that India’s “next billion” has the potential to tap into, as experts see it.

Gopalan said an insurance customer that was previously engaged in a one-time use case has now expanded to 27 use cases.

Gargi Dasgupta, Director, IBM Research India and CTO, IBM India-SA, says, “IBM Research India is working with the Center for Indian Language Technology (C-FLIT) at IIT Bombay to help Watson understand Indian languages ​​beyond translation. Today Watson is equipped to understand pronunciation, sentence structure, grammar and other nuances of Hindi in Devanagari and work continues for Watson to understand other Indian languages ​​- both spoken and written.”

It seems everyone agrees that the future of automated conversations isn’t either voice or text, but both. Until the efficiency of voice automation catches on, companies are making the most of chatbot efficiency thanks to natural language processing, to increase actual transactions from customers.