Feedback Control of Real-Time Bidding Advertising Fatemeh - - PowerPoint PPT Presentation

▶
feedback control of real time bidding advertising
SMART_READER_LITE
LIVE PREVIEW

Feedback Control of Real-Time Bidding Advertising Fatemeh - - PowerPoint PPT Presentation

Apr 12, 2023 254 likes •580 views

Feedback Control of Real-Time Bidding Advertising Fatemeh Gheshlaghpour Advisors: Maryam Babazadeh Amin Nobakhti Sharif University of Technology, EE Department Apr. 2018 Overview Introduction Business Model of the RTB Markets

slide-1
SLIDE 1

Feedback Control of Real-Time Bidding Advertising

Fatemeh Gheshlaghpour Advisors: Maryam Babazadeh Amin Nobakhti

Sharif University of Technology, EE Department

  • Apr. 2018
slide-2
SLIDE 2

Overview

  • Introduction
  • Business Model of the RTB Markets

– Key Roles in RTB Market – The Business Process of RTB Ad Delivery

  • Second-Price Sealed-Bid Auction
  • Key Research Issues in the RTB
  • IPinYou Dataset

– Basic Statistics – User Feedback

  • RTB Feedback Control System

– Bidding Strategy – Logistic Estimator – Actuator

  • Control Issues of the Problem

– Reference and Feedback Signals – Model

  • Results

2/31

slide-3
SLIDE 3

Introduction

  • In the previous generations of the display advertising the advertiser

paid in two different platforms: – CPM (cost per mille) -> do not getting satisfactory numbers of clicks. – CPC (cost per click) -> being subjected to click frauds.

  • Internet users, on the other hand, faced with lots of irrelevant

advertisements on their screens -> Ad-Blockers !

3/31

slide-4
SLIDE 4
  • The Solution was the RTB in which the advertisers should bid

for each impression based on some behavioral and contextual data.

  • The business process, including audience identification,

auction and ad display, will be finished in exactly 10 to 100 milliseconds, and hence it is named "real-time bidding".

  • A basic problem for RTB bidding agents is to figure out how

much to bid for an incoming bid request.

Introduction

4/31

slide-5
SLIDE 5

Business Model of the RTB Markets

  • The key roles in RTB markets

⁻ Advertiser ⁻ Demand side platform (DSP) is a platform that helps advertisers optimize their strategies. ⁻ Ad exchange (AdX) is an ad exchange market that matches the buyers and sellers. ⁻ Supply side platform (SSP) is a platform that helps publishers optimize the strategies. ⁻ Data management platform (DMP) is a platform that analyzes the cookie data of Internet users. ⁻ Publisher

5/31

slide-6
SLIDE 6

Business Model of the RTB Markets

The business process of RTB ad delivery.* *Yuan, Y

., Wang, F ., Li, J., & Qin, R. (2014). A survey on real time bidding advertising. Proceedings of the IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), Qingdao, China (pp. 418-423).

  • The Business Process of RTB Ad Delivery

Myerson has proved that its optimal mechanism is second-price sealed-bid auction.

6/31

slide-7
SLIDE 7

Key Research Issues in the RTB

  • Inventory Pricing and Channel Allocation
  • In RTB markets, publishers and SSPs constitute the supply side
  • f ad resources. Their key decisions, such as inventory pricing

and multi-channel allocation of ad impressions, are major re search topics in literatures.

  • Business Model and Mechanism Design
  • Similarly working like the stock markets, AdX can bridge the

gap in RTB markets by matching advertisers to publishers via real-time auctions. The existing works are focused on the design of the business model and auction mechanisms of AdXs and DSPs.

7/31

slide-8
SLIDE 8

Key Research Issues in the RTB

  • Market Segmentation and Ad Performance Analysis
  • Via designing the audience classification category and attribute

labels, DSPs can divide the Internet users into large amounts of niche markets with different kinds of demographic characteristics or shopping interests, and display best-matched ads accordingly.

  • Bidding Behavior Analysis and Strategy

Optimization

  • In RTB markets, advertisers and DSPs constitute the demand side of

ad resources, seeking to buy best-matched ad impressions via real- time auctioning and bidding. In literatures, bidding behavior analysis and strategy optimization for advertisers and DSPs attract intensive interests.

8/31

slide-9
SLIDE 9

Second-Price Sealed-Bid Auction

9/31

slide-10
SLIDE 10
  • Nash Equilibrium:
  • The only NE which does not need to know other players’

private values is to bid truthfully, i.e. to bid same as the private value.

Second-Price Sealed-Bid Auction

10/31

slide-11
SLIDE 11

IPinYou Dataset

  • Fortunately, a leading Chinese advertising technology company

iPinYou decided to release the dataset used in its global RTB algorithm competition in 2013.

  • The dataset includes logs of ad auctions, bids, impressions, clicks,

and final conversions. These logs reflect the market environment as well as form a complete path of users’ responses from advertisers’ perspective.

11/31

slide-12
SLIDE 12

*Zhang, W., Yuan, S., Wang, J., & Shen X. (2014). Real-time bidding benchmarking with ipinyou dataset.

arXiv:1407.7073.

The iPinYou data format.*

12/31

slide-13
SLIDE 13

Basic Statistics

13/31

slide-14
SLIDE 14

User Feedback

  • Some statistics of user feedback on campaigns 1458 and 3358 are

shown bellow.

14/31

slide-15
SLIDE 15

User Feedback

15/31

slide-16
SLIDE 16

User Feedback

16/31

slide-17
SLIDE 17

The traditional bidding strategy is represented as the bid calculator module in the DSP bidding agent. The controller plays as a role which adjusts the bid price from the bid calculator.

Feedback controller integrated in the RTB system.*

RTB Feedback Control System

*Zhang, W., Yuan, S., & Wang, J. (2014). Optimal real-time bidding for display advertising. Proceedings

  • f the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD), New

York City, NY , USA (pp. 1077-1086).

17/31

slide-18
SLIDE 18
  • Bidding Strategy

( )

t

b t b θ θ =

18/31

slide-19
SLIDE 19

Logistic Estimator

  • Logistic estimator predicts the CTR (a real value between 0 and 1) of

an ad given a set of features.

  • Where fi(ad) is the value of the ith feature for the ad, and wi is the

learned weight for that feature.

19/31

slide-20
SLIDE 20
  • In our experiment, all the features for LR are binary.
  • The weekday and hour feature are extracted from timestamps.
  • The floor price is processed by buckets of 0, [1,10], [11,50], [51,100] and

[101,+∞).

  • We do not include the features of Bid ID, Log Type, iPinYou ID, URL,

Anonymous URL ID, Bidding Price, Paying Price, Key Page URL.

  • In sum, we have 937,748 binary features for LR training and prediction.

Logistic Estimator

20/31

slide-21
SLIDE 21

Logistic Estimator

150 300 450 600 1458 2259 2261 2821 2997 3358 3386 3427 3479 #ectr > 0.5 #ectr < 0.5

Validation of LR for impressions with click=1

175000 350000 525000 700000 1458 2259 2261 2821 2997 3358 3386 3427 3479 #ectr > 0.5 #ectr < 0.5

Validation of LR for impressions with click=0 21/31

slide-22
SLIDE 22
  • Actuator

For example it can be chose to use: For instance in a PID controller we have:

22/31

slide-23
SLIDE 23

Control Issues of the Problem

  • Same as any other control problems we should take care of these:
  • Reference Signal -> What is our controlling goal?
  • Feedback Signal -> Do we have access to this signal?
  • Model -> Can we have a static/dynamic model of the process?

23/31

slide-24
SLIDE 24

Reference and Feedback Signals

  • The advertisers are provided with the data of the impressions. So

we can define a feedback signal.

  • Reference signal is the output of an optimization problem.
  • In order to have smooth budget delivery we should set another

constraint, too.

24/31

slide-25
SLIDE 25

Reference and Feedback Signals

Illustration of different budget pacing schemes with respect to the portion of the budget spent every time interval.* *Lee, Kuang-Chih, Ali Jalali, and Ali Dasdan. "Real time bid optimization with smooth budget delivery in online advertising." Proceedings of the Seventh International Workshop on Data Mining for Online Advertising. ACM, 2013.

25/31

slide-26
SLIDE 26
  • Finally, we should optimize the following goal:

Reference and Feedback Signals

26/31

slide-27
SLIDE 27

Model

  • As the time-constant of the dynamic model is not short enough we

can not have it using the data.

27/31

slide-28
SLIDE 28

Results

  • Here is the AWR signal for the campaign 2998 using impression-based PI controllers.

28/31

slide-29
SLIDE 29
  • Bellow you can see the overall control performance on AWR for the

campaign 2998 using some different methods.

Results

Method ref #Ad #clk total_cost AWR CPC CPM CTR rise-time settling-time rmse-ss awr_rand_pi 0.6 6055 9 200341 0.5896 20034.1 33086.8 0.0015 4 6 0.00196 control_awr_pi 0.6 6167 13 352707 0.5875 25193.3 57192.6 0.0021 252 2016 0.02587 awr_pi_constant 0.6 6053 7 209847 0.5943 26230.8 34668.2 0.0011 4 6 0.00203 awr_pi 0.6 6052 10 226075 0.5999 20552.2 37355.4 0.0017 4 6 0.00199 static_bid_awr_K 0.6 6191 5 142775 0.6136 23795.8 23061.7 0.0008 15 930 0.03102

Performance of different AWR controllers 29/31

slide-30
SLIDE 30
  • Bellow you can see the overall control performance on CPC for the

campaign 2998 using some different methods.

Results

Performance of different CPC controllers

Method ref #Ad #clk total_cost AWR CPC CPM CTR rise-time settling-time rmse-ss control_ecpc_pi 10000 1940 4 54510 0.1939 10902 28097.9 0.00206 5250 5250 0.06144 cpc_constant_pi 10000 153 10057 0.0152 10057 65732.1 134 134 0.00556 cpc_rand_pi 10000 153 10057 0.0153 10057 65732.1 134 134 0.00556

30/31

slide-31
SLIDE 31

Thank you for your time…

31/31