Optimization of Real-time Bidding System via Automatic Detection of Performance-related Defects

Design an efficient way to store and organize the large amounts of data required by our real time bidding application. Data such as campaign information, campaign assets (images, links, html) campaign targeting settings, and campaign optimization data could be arranged for fast access and processing inside the RTB application. Efficient storage and processing methods are required in order to allow the bidder to store in excess of 1000 campaigns and yet still be able to bid in impressions in the order of milliseconds. Possible storage and optimization methods involve using bit strings to store campaign information in a way that allows logic operations (eg AND/OR/XOR) to process many campaign simultaneously with little compute power.

Faculty Supervisor:

Andriy Miranskyy

Student:

Partner:

Addictive Mobility

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Toronto Metropolitan University

Program: