Engineering Blog

13 Oct 2014
Apu-blog-avatar

Parameter Optimization with DAPS!

Consider a situation where you have a dial to tweak, and this dial setting may influence a reward of some kind. For example, the dial may be a weight used in a personalization algorithm, and the reward may be clickthrough or revenue. The problem is, we don't know beforehand how the dial affects the reward,... View Article

Read More

11 Jun 2014
Sergey Feldman

Personalization with Contextual Bandits

This is the third in a series of three blog posts about bandits for recommendation systems. In the first and second blog posts we covered the bandit problem, and some ways to solve it.  But in doing so, we ignored two critical challenges to dishing out recommendations in the real world. They are: 1. What if you... View Article

Read More

05 Jun 2014
Jeremy York

Content Selection Optimization in Data Driven Marketing

A common problem in data driven marketing systems can be summarized as follows: 1. We have a set of possible content that we could show 2. We have information about the shopper and the context for the content 3. We want to choose content that has the best chance to get a response from the shopper 4. We want... View Article

Read More

05 Jun 2014
Sergey Feldman

Recommendations with Thompson Sampling

This is the second in a series of three blog posts on bandits for recommendation systems. If you read the last blog post, you should now have a good idea of the challenges in building a good algorithm for dishing out recommendations in the bandit setting.  The most important challenge is to balance exploitation with... View Article

Read More

02 Jun 2014
Sergey Feldman

Bandits for Recommendation Systems

This is the first in a series of three blog posts on bandits for recommendation systems.  In this blog post, we will discuss the bandit problem and how it relates to online recommender systems.  Then, we'll cover some classic algorithms and see how well they do in simulation. A common problem for internet-based companies is:... View Article

Read More