ICICI Lombard, India’s one of the leading private sector general insurance company, has transformed its customer engagement using Microsoft Azure Cognitive Services. The company has leveraged Azure Speech Services and Natural Language Processing (NLP) to simplify the insurance requirements of its customers, including purchase of new policies, renewal of existing policies, and settlement of claims. The deployment of Azure AI tools has enabled ICICI Lombard to increase the accuracy of Quality Audit (QA) during its calls – from 50% to over 80%. It has also enhanced the efficiency of its internal audit process by reducing latency from 12 hours to two hours, apart from increasing productivity of its call center agents.
The ICICI Lombard digital team currently makes over 1,000 outbound customer calls daily through its call center. While the company screened and audited calls randomly to check compliance levels and quality of its tele-customer service, the high call volume was affecting efficacy of audits. It is important to evaluate adherence to approved scripts and use of appropriate tonality by agents during customer calls, as is reporting non-compliance within 24 hours. Multiplicity of language is another challenge, with customers often switching between English and Hindi during calls. Moreover, owing to the diversity of dialects across the country, ensuring clarity of accent is a concern as well.
To address these issues, ICICI Lombard’s data scientists collaborated with Microsoft’s AI team to implement Azure Speech Services and create a customized NLP algorithm. This has allowed the insurance provider to screen 100% of its calls now as against 20% earlier. It was also able to automate its Quality Assurance process to remove human bias from customer calls, resulting in improved customer outreach, increased productivity and consistency across the audit system. Further, the tools easily process customer queries in Hindi and English and detect insurance-specific keywords easily.
Girish Nayak, Chief of Customer Service, Operations and Technology, ICICI Lombard, said “Given the diversity of our customer ecosystem and dynamic requirements, it was important to facilitate a seamless policy buying and claim experience. Today, customer engagement requires a focused, customized and agile approach to address queries and issues. This is where AI is empowering us to unlock human ingenuity – with Azure AI tools and services; we are also enabling our agents to enhance their customer engagement and efficiency levels. Through our partnership with Microsoft, we aim to take our customer experience to the next level.”
Azure Speech Services provide a wide range of speech recognition and generation capabilities including speech transcription, text-to-speech, speech translation, and speaker recognition. ICICI Lombard is converting Speech to Text leading to 90% accuracy on important key phrases such as Registration Number.
Sashi Sreedharan, Managing Director, Microsoft India, said, “To be successful in today’s dynamic business environment, organizations need to be a fast adopter of best-in-class technology; and secondly, they need to build their own unique digital capabilities. We are excited about enabling ICICI Lombard, a forerunner in digital acceleration; to enhance their customer experience significantly using Microsoft’s unified cognitive speech services.”
With Azure Speech Services businesses across industries, can build smart apps and services that speak to users naturally with the Text to Speech service. It converts text to audio in near real time, tailored to change the speed of speech, pitch, volume and more.
Azure Language Understanding, is an AI service that allows users to interact with applications, bots and IoT devices by using natural language. Using machine teaching technology and Microsoft’s visual user interface, developers and subject matter experts can build custom machine-learned language models that interprets user goals and extracts key information from conversational phrases—all without any machine learning experience. Azure Text Analysis is an AI service that uncovers insights such as sentiment, entities, relations, and key phrases in unstructured text. It discovers insights in unstructured text using natural language processing (NLP)—no machine learning expertise required. It helps in identifying key phrases and entities such as people, places, and organizations to understand common topics and trends. Users can gain a deeper understanding of customer opinions with sentiment analysis and evaluate text in a wide range of languages
