Saved in:
Bibliographic Details
Main Authors: Soboleva, Anastasiia, Pudovikov, Andrey, Snetkov, Roman, Babenko, Alina, Samosvat, Egor, Dorn, Yuriy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.01867
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929696948617216
author Soboleva, Anastasiia
Pudovikov, Andrey
Snetkov, Roman
Babenko, Alina
Samosvat, Egor
Dorn, Yuriy
author_facet Soboleva, Anastasiia
Pudovikov, Andrey
Snetkov, Roman
Babenko, Alina
Samosvat, Egor
Dorn, Yuriy
contents Online advertising platforms often face a common challenge: the cold start problem. Insufficient behavioral data (clicks) makes accurate click-through rate (CTR) forecasting of new ads challenging. CTR for "old" items can also be significantly underestimated due to their early performance influencing their long-term behavior on the platform. The cold start problem has far-reaching implications for businesses, including missed long-term revenue opportunities. To mitigate this issue, we developed a UCB-like algorithm under multi-armed bandit (MAB) setting for positional-based model (PBM), specifically tailored to auction pay-per-click systems. Our proposed algorithm successfully combines theory and practice: we obtain theoretical upper estimates of budget regret, and conduct a series of experiments on synthetic and real-world data that confirm the applicability of the method on the real platform. In addition to increasing the platform's long-term profitability, we also propose a mechanism for maintaining short-term profits through controlled exploration and exploitation of items.
format Preprint
id arxiv_https___arxiv_org_abs_2502_01867
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics
Soboleva, Anastasiia
Pudovikov, Andrey
Snetkov, Roman
Babenko, Alina
Samosvat, Egor
Dorn, Yuriy
Machine Learning
Online advertising platforms often face a common challenge: the cold start problem. Insufficient behavioral data (clicks) makes accurate click-through rate (CTR) forecasting of new ads challenging. CTR for "old" items can also be significantly underestimated due to their early performance influencing their long-term behavior on the platform. The cold start problem has far-reaching implications for businesses, including missed long-term revenue opportunities. To mitigate this issue, we developed a UCB-like algorithm under multi-armed bandit (MAB) setting for positional-based model (PBM), specifically tailored to auction pay-per-click systems. Our proposed algorithm successfully combines theory and practice: we obtain theoretical upper estimates of budget regret, and conduct a series of experiments on synthetic and real-world data that confirm the applicability of the method on the real platform. In addition to increasing the platform's long-term profitability, we also propose a mechanism for maintaining short-term profits through controlled exploration and exploitation of items.
title Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics
topic Machine Learning
url https://arxiv.org/abs/2502.01867