Auto-bidding in Online Advertising: Campaign Management and Fairness
A Google TechTalk, presented by Jason Liang, 2023-02-14
ABSTRACT: In digital advertising, advertisers procure ad impressions simultaneously on multiple platforms, or so-called channels. Advertisers communicate their procurement goals to channels, where the channels then consequently run automated bidding algorithms to participate in ad auctions on their behalf.
In the first part of this talk, we address a single advertiser’s conversion (e.g. ad clicks) maximization problem while satisfying aggregate return-on-investment (ROI) and budget constraints across all channels. In practice, an advertiser does not have control over, and thus cannot globally optimize, which individual ad auctions she participates in for each channel. Instead, the advertiser authorizes each channel to procure impressions on her behalf: the advertiser can only utilize two levers on each channel, namely setting a per-channel budget and per-channel target ROI. We analyze the effectiveness of each of these levers for solving the advertiser’s global multi-channel problem. Further, we present an efficient learning algorithm to optimize over per-channel levers to approximate the global optimal conversion.
In the second part of this talk, we address a single channel’s problem to improve individual fairness for auction outcomes. Channels have commonly focused on maximizing total advertiser value (or welfare) to attract advertiser traffic and spend, and have resorted to machine learning predictions on advertiser values (also known as machine-learned advice) to improve ad auction designs. Yet, such improvements could come at the cost of individual bidders’ welfare, consequently eroding fairness of a channel, and do not shed light on how particular bidding strategies impact individual fairness. Motivated by this, we present a novel fairness metric that measures an individual bidder’s welfare loss, and also uncovers how advertiser strategies relate to such losses. Under this metric, we then study how channels can utilize ML advice to improve welfare guarantees and fairness on the individual bidder level. We motivate a simple approach that directly sets such advice as personalized reserve prices, and present individual welfare guarantees for classic VCG, GSP and GFP auctions under such ML-advice-based reserves.
Bio: Jason Liang is a 5th year PhD at the MIT Operations Research Center, advised by Negin Golrezaei and Patrick Jaillet. He graduated summa cum laude from Columbia University with a B.S. in Operations Research. Jason’s research interests include online learning, mechanism design, and revenue management for online marketplaces. Jason was also a student researcher in the Market Algorithms Group at Google hosted by Vahab Mirrokni and Yuan Deng during 2022 winter.
A Google Research Algorithms Seminar.
1 view
0
0
6 months ago 00:35:52 1
Free CCNA | Interfaces and Cables | Day 2 | CCNA 200-301 Complete Course
6 months ago 00:20:37 1
FlippyDrive FIRST LOOK! Solderless Modchip For GameCube!
6 months ago 00:14:04 1
Der größte Betrug der E-Auto-Industrie
6 months ago 00:01:02 3
The Ripsaw EV3 F4 Is An 800 Horsepower Luxury Tank You Can Buy
6 months ago 00:04:43 1
Typogram Review: Instant Human-Like Content Across Platforms with Automated Typing Technology!
7 months ago 00:01:13 1
Breaking Bad meets GTA IV
7 months ago 00:00:32 1
[OPEN] Fahrradsattel YCH animation MEME
7 months ago 00:15:25 1
Building a new Game Boy in 2023 | Introducing the Super DMG DIY board!
7 months ago 00:01:33 1
Literally me in GTA V
7 months ago 00:21:46 2
The Subaru XT Is Probably the Weirdest Subaru Ever Made
8 months ago 00:26:49 1
Why You Need To Put A Raspberry Pi CM4 Inside Your PSP Right Now!
9 months ago 00:01:24 1
Ryan Gosling in GTA V
9 months ago 00:17:50 1
I DISASSEMBLE The New EON XBHD HDMI Adaptor To See If It’s Worth $190
9 months ago 00:01:44 1
1969 JAGUAR XJ6 4.2 AUTO SERIES I
9 months ago 00:20:57 1
Making the Steam Deck Even Better With This CRAZY Screen Upgrade
9 months ago 00:39:32 1
Shocking White House Report HUMILIATES Biden: AMERICA IN PERIL! | Officer Tatum Exclusive
9 months ago 00:01:39 3
Ryan Gosling in GTA 5
10 months ago 00:16:51 1
Making The Super Nintendo Even More Super
10 months ago 00:28:34 1
This HDMI Mod Makes The PlayStation 2 Look Gorgeous! | PixelFX RetroGEM
11 months ago 00:29:52 1
First Wash In 5 Years: Abandoned Ford GT Disaster Detail with Doug DeMuro!
11 months ago 00:29:59 1
Bidding And Buying A Crashed 2020 Mclaren GT
12 months ago 00:00:57 109
Dying Light 2 Parkour Comparison | 2021 vs 2023 (Good Night Good Luck Update)
12 months ago 00:09:46 1
Electric Rolls Royce Phantom? Classic Cars New Lease Of Life With Lunaz