Developing Efficient Machine Learning Models for Price Bidding

Curate Mobile operates a demand site platform (DSP), which is an advertising platform responsible for bidding in real time ad placements from various publishers. This process is a blind auction, happening over 50,000 times a second, and during this bidding process we have less then 100ms to determine which of our clients should bid for this ad placement, how much it might be worth to them, and what price we believe we can win this auction for. During this project, we will add machine learning models to our DSP to provide fast decisions in real time to maximize the return on ad spend of our clients’ campaigns. The main goal for this project is to add proof-of-concept machine learning model to Curate Mobile’s DSP, with a pipeline that will continually update the models with new data as it is ingested. We will also design a validation module to monitor and validate the performance of the developed models.

Faculty Supervisor:

Rasha Kashef

Student:

Partner:

Curate Mobile Ltd.

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Toronto Metropolitan University

Program: