Anthill Inside For members

Anthill Inside 2019

A conference on AI and Deep Learning

Make a submission

Accepting submissions till 01 Nov 2019, 04:20 PM

Taj M G Road, Bangalore, Bangalore

Tickets

Loading…

##About the 2019 edition:

The schedule for the 2019 edition is published here: https://hasgeek.com/anthillinside/2019/schedule

The conference has three tracks:

  1. Talks in the main conference hall track
  2. Poster sessions featuring novel ideas and projects in the poster session track
  3. Birds of Feather (BOF) sessions for practitioners who want to use the Anthill Inside forum to discuss:
  • Myths and realities of labelling datasets for Deep Learning.
  • Practical experience with using Knowledge Graphs for different use cases.
  • Interpretability and its application in different contexts; challenges with GDPR and intepreting datasets.
  • Pros and cons of using custom and open source tooling for AI/DL/ML.

#Who should attend Anthill Inside:

Anthill Inside is a platform for:

  1. Data scientists
  2. AI, DL and ML engineers
  3. Cloud providers
  4. Companies which make tooling for AI, ML and Deep Learning
  5. Companies working with NLP and Computer Vision who want to share their work and learnings with the community

For inquiries about tickets and sponsorships, call Anthill Inside on 7676332020 or write to sales@hasgeek.com


#Sponsors:

Sponsorship slots for Anthill Inside 2019 are open. Click here to view the sponsorship deck.


Anthill Inside 2019 sponsors:


#Bronze Sponsor

iMerit Impetus

#Community Sponsor

GO-JEK iPropal
LightSpeed Semantics3
Google Tact.AI
Amex

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more

Priyanshu Chandra

@priyanshu_chandra

Building a Recommendation Engine for diverse content and user behaviors

Submitted Sep 8, 2019

Good recommendation systems, as we all know, are a great way to acquire users, creating a delightful user experience for user engagement while driving incremental revenue. There is a lot of innovation and research in making recommendations systems understand the user preferences and hence personalise better.

At Hotstar, India’s largest premium streaming and entertainment platform, we have a scale of more than 200 million monthly active downloads of diverse demography and a variety of content catalog in terms of category, genre, ingestion rate, and liveliness-requirement (live video streaming). Due to each of these factors, we face this unique challenge of user behavior cycle varying according to each content type, because of which our recommendation systems demand to be smarter. For example we have entertainment content like movies and TV shows which get binge-watch kind of behavior, contrary to news channels which have daily cyclic watch patterns and live sports which have random and concentrated watch behavior. Coupled with this, our typical peak scale for a single online recommendation service is 2 million RPM!

In this talk, I am going to cover how do we take these diversity factors into consideration in designing our personalisation models at scale, to cater to different UI features collating and surfacing mixed variety of content. Will focus on how we use ensemble modelling for ranking and designing online and offline sub-models for different content types.

Outline

  • Introduction
  • Key take-away
  • Personalisation @Hotstar
  • Unique Challenges we face.
  • Brief about varying user behavior for various content types
  • Brief about varying ingestion rate of new content for various content types
  • Case study - Building a deep recommender system for limited catalogue
  • Case study - Building a recommender system for catalogue of various content types
  • Case Study - Building a recommender system for infinite feed of fast generating new content.
  • Q&A

Requirements

Basic ML knowledge.
Preferred : Basic techniques of recommendation systems like collaborative filtering.

Speaker bio

Currently Working as a Machine Learning Engineer in Personalisation team at Hotstar building models to serve millions of diverse users and helping drive engagement. Undergraduate in Mathematics and Computing from IIT Guwahati. Geek by nature, like formulating and solving algorithmic and data science problems. New found interest in applying ML practically to solve real world problems, drive them to production and thus leaving a significant impact. Currently more intrigued by personalisation industry, as you get to analyse user behavior trends at large and solve problems accordingly.
On personal front, I am a couch potato always wanting to work out soon. (:

Slides

https://docs.google.com/presentation/d/1Eqn_ZI3Kms6RoFWA5L5eNTKxwREvcajiL65XKQtcfuk/edit?usp=sharing

Comments

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

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

{{ errorMsg }}

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

Make a submission

Accepting submissions till 01 Nov 2019, 04:20 PM

Taj M G Road, Bangalore, Bangalore

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more