Cold Start on Online Advertising Platforms: Data-Driven Algorithms and Field Experiments

55 Pages Posted:

See all articles by Zikun Ye

Zikun Ye

University of Illinois at Urbana-Champaign

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School

Heng Zhang

USC Marshall School of Business, DSO Department

Renyu (Philip) Zhang

New York University Shanghai

Xin Chen

University of Illinois at Urbana-Champaign

Zhiwei Xu

affiliation not provided to SSRN

Date Written: October 1, 2020

Abstract

Cold start describes a commonly recognized challenge in online advertising platforms: With limited data, the machine learning system cannot accurately estimate the click-through rates (CTR) nor the conversion rates (CVR) of new ads and in turn cannot efficiently price these new ads or match them with platform users. Unsuccessful cold start of new ads will prompt advertisers to leave the platform and decrease the thickness of the ad marketplace. To address the cold start issue for online advertising platforms, we build a data-driven optimization model that captures the essential trade-off between short-term revenue and long-term market thickness of advertisement. Based on duality theory and bandit algorithms, we develop the Shadow Bidding with Learning (SBL) algorithm with a provable regret upper bound of O(T^{2/3}K^{1/3}(logT)^{1/3}d^{1/2}), where K is the number of ads and d is the effective dimension of the underlying machine learning oracle for predicting CTR and CVR. Furthermore, our proposed algorithm can be straightforwardly implemented in practice with minimal adjustments to a real online advertising system. To demonstrate the practicality of our cold start algorithm, we collaborate with a large-scale online video sharing platform to implement the algorithm online. In this context, the traditional single-sided experiment would result in substantially biased estimates. Therefore, we conduct a novel two-sided randomized field experiment and devise unbiased estimates to examine the effectiveness of the SBL algorithm. Our experimental results show that the proposed algorithm could substantially increase the cold start success rate by 61.62% while only compromising the short-term revenue by 0.717%, and consequently boost the total objective value by 0.147%. Our study bridges the gap between the bandit algorithm theory and the ads cold start practice, and highlights the significant value of well-designed cold start algorithms for online advertising platforms.

Keywords: Cold Start Problem, Online Advertising, Contextual Bandit, Two-Sided Field Experiment

Suggested Citation

Ye, Zikun and Zhang, Dennis and Zhang, Heng and Zhang, Renyu and Chen, Xin and Xu, Zhiwei, Cold Start on Online Advertising Platforms: Data-Driven Algorithms and Field Experiments (October 1, 2020). Available at SSRN: https://ssrn.com/abstract=

Zikun Ye (Contact Author)

University of Illinois at Urbana-Champaign ( email )

601 E John St
Champaign, IL 61820
United States

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Heng Zhang

USC Marshall School of Business, DSO Department ( email )

701 Exposition Blvd
Los Angeles, CA 90089
United States

Renyu Zhang

New York University Shanghai ( email )

1555 Century Avenue
Shanghai, 200122
China
86-21-20595135 (Phone)

HOME PAGE: http://https://rphilipzhang.github.io/rphilipzhang/index.html

Xin Chen

University of Illinois at Urbana-Champaign ( email )

601 E John St
Champaign, IL 61820
United States

Zhiwei Xu

affiliation not provided to SSRN

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
20
Abstract Views
103
PlumX Metrics