Scalable Audience Reach Estimation in Real-time Online Advertising

TL;DR

This paper presents a distributed, fault-tolerant system for real-time online advertising reach estimation, balancing speed and accuracy by using stratified sampling on representative data samples across multiple machines.

Contribution

It introduces a novel distributed sampling-based forecasting system that improves accuracy and speed over existing industry methods for online ad reach estimation.

Findings

Significant accuracy improvements over uniform sampling.

Faster estimation suitable for real-time applications.

Effective handling of minority groups through fuzzy fallback.

Abstract

Online advertising has been introduced as one of the most efficient methods of advertising throughout the recent years. Yet, advertisers are concerned about the efficiency of their online advertising campaigns and consequently, would like to restrict their ad impressions to certain websites and/or certain groups of audience. These restrictions, known as targeting criteria, limit the reachability for better performance. This trade-off between reachability and performance illustrates a need for a forecasting system that can quickly predict/estimate (with good accuracy) this trade-off. Designing such a system is challenging due to (a) the huge amount of data to process, and, (b) the need for fast and accurate estimates. In this paper, we propose a distributed fault tolerant system that can generate such estimates fast with good accuracy. The main idea is to keep a small representative sample in memory across multiple machines and formulate the forecasting problem as queries against the sample. The key challenge is to find the best strata across the past data, perform multivariate stratified sampling while ensuring fuzzy fall-back to cover the small minorities. Our results show a significant improvement over the uniform and simple stratified sampling strategies which are currently widely used in the industry.