Sep 23–26, 2019

Migrating millions of users from voice and email based customer support to a chatbot

Madhu Gopinathan (MakeMyTrip), Sanjay Mohan (MakeMyTrip)
3:45pm4:25pm Thursday, September 26, 2019
Location: 1E 12/13
Secondary topics:  Text and Language processing and analysis, Transportation and Logistics

Who is this presentation for?

Data Scientists, Machine Learning Engineers, Architects, Product Managers

Level

Beginner

Description

At MakeMyTrip, a large number of customer care agents were dedicated to handle customer support issues over voice and email. Given the popularity of Whatsapp in India, conversational interfaces have become mainstream for the Indian consumer. MakeMytrip decided to capitalize on this trend and revamped customer support channels using a chatbot named Myra. Myra is adept at handling the languages of the Indian consumer including English, Hindi and a mix of the two popularly known as Hinglish.

Myra handles user input using a natural language understanding framework that solves problems such as intent classification and slot extraction using the latest advances in deep learning. In the intent classification problem, an utterance “please cancel my ticket” should be mapped to a label “Full Cancellation”. The intent classification model supports over 120 intents and is sophisticated to distinguish between fine grained intents such as full cancellation, partial cancellation and flight cancellation by airlines. In the slot extraction problem, from the utterance “please cancel my ticket to new york”, the value “new york” should be extracted to fill the destination slot.

For curating the data required for training deep learning models, we employed multiple methods such as manual tagging, creating language models from existing email conversations, progressive refinement of the models and natural language generation. In this case study, we will discuss our learnings from developing deep learning models to power Myra revamping of agent tools and processes to support Myra and the ensuing business impact.

Prerequisite knowledge

None

What you'll learn

This session will cover learnings from deploying a conversational bot and associated agent systems to improve post sale service. The details covered include architecture, strategies for data curation to train deep learning models and business impact from deploying a chatbot based on these models.
Photo of Madhu Gopinathan

Madhu Gopinathan

MakeMyTrip

Madhu Gopinathan is currently Vice President, Data Science at MakeMyTrip, India’s leading online travel company. He started his career in the San Francisco Bay area developing large scale software systems in the telecom industry. After spending about 10 years in the industry at companies such as Covad Communications and Microsoft, he completed his PhD in computer science from Indian Institute of Science, working on mathematical modelling of software systems. He then came back to the industry, starting with building a machine learning at team at Infosys product incubation group followed by couple of startups before his current stint at MakeMyTrip. He has collaborated with researchers at Microsoft Research, General Motors and Indian Institute of Science leading to publications in prominent computer science conferences. He holds an MS in computer science from the University of Florida, Gainesville, USA. He has extensive experience developing large scale systems using machine learning & natural language processing and has been granted multiple US patents.

Photo of Sanjay Mohan

Sanjay Mohan

MakeMyTrip

Sanjay is the Group Chief Technology Officer MakeMyTrip Ltd. He leads overall technology for MakeMyTrip, GoIbibo and Redbus. Prior to the merger with the Ibibo Group, he was the CTO of MakeMyTrip.

Sanjay is responsible for developing and executing global technology strategy for the combined entity, and planning ongoing technology innovations for the company’s continued success. Sanjay has brought on-board an extensive product leadership and management experience in marquee companies like Yahoo, IBM, Infosys, Oracle, and Netscape in the US and in India.

With an overall experience of 25+ years, Sanjay brings along significant expertise in product and platform engineering, including architecture, user experience, site operations, product management and product strategy.

Sanjay has Masters in Computer Science from University of Louisiana and completed his Bachelors’ degree in Engineering from the Birla Institute of Technology Mesra – Ranchi.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

confreg@oreilly.com

For conference registration information and customer service

partners@oreilly.com

For more information on community discounts and trade opportunities with O’Reilly conferences

strataconf@oreilly.com

For information on exhibiting or sponsoring a conference

Contact list

View a complete list of Strata Data Conference contacts