Submissions for MLOps November edition

On ML workflows, tools, automation and running ML in production

Sayed Adil Hussain

@adil9627

Search Driven Analytics: Enabled through a Conversational Bot

Submitted Jul 6, 2021

To deliver insights at the speed of thought, instead of requiring the need through dashboards, applying filters / or asking analysts - We at Mahindra & Mahindra, have developed Genie for Analytics, a voice-enabled analytics conversational assistant.
This Engine has been a first-of-its-kind, cutting edge work in Mahindra. It integrates natural language processing, query processing and natural language generation in a single interface to provide answers to analytics questions asked in simple English (text , voice) - in form of charts, tables and voice. The back end architecture, is sitting on bed rock of AI based Deep Learning Natural language & Search algorithms talking to internal databases.

The engine has been built on three principles:
• Personalization - Personalized In-sights basis user behaviors & Role
• Search Engine - Single source for analytics
• Maturing Analytics - including moving into exceptions, predictive & prescriptive

It empowers front-line HR employees, to deep dive in their data, make multiple data points talk to each other - by only asking questions in simple English - and in process uncover In-sights & get those delivered to them in seconds.

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures