The Fifth Elephant 2014

A conference on big data and analytics

Ambuj Singh


Real Time User-Scoring for Bidding in Display Retargeting

Submitted Jul 3, 2014

Retargeting online customers to a retail website via Display Ads has become an incredible avenue to drive traffic back to the website. Especially with the advent of Real Time Bidding (RTB), advertisers now have access to an efficient and transparent mechanism to buy from this huge volume of available ad inventory. It allows an advertiser to optimize their ad spend down to the exact user they are targeting in real time, show visual ads personalized based on the user’s tastes, and strive for a desired Cost per Click / Impression / Conversion goal. In this session, we would like to discuss the various approaches we have tried to model each Walmart user that visits, and target the user via Display Ads.


To participate in an auction, we must come up with a dollar value that we are ready to bid for each user. To do this, we analyze the site-activity of the users in real-time, along with any meta-data we may have. In this session, we walk through how we have broken this problem into smaller pieces, and through optimizations based on CTR, conversion probability and expected revenue, our campaigns are designed towards achieving business goals measured in terms of achieved Return Over Ad Spend (ROAS). We also handle ad-serving, and deciding items to recommend in the ad units, in case of bids won.

Speaker bio

I, Ambuj Singh, graduated in Computer Science from IIT Kanpur in 2012. Since then, I have been working in @WalmartLabs, first in the twitter analysis team, and currently in the Display Ads team.


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

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

{{ errorMsg }}

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

Hosted by

All about data science and machine learning