A Probabilistic Multi- Touch Attribution Model for Online - PowerPoint PPT Presentation

A Probabilistic Multi- Touch Attribution Model for Online Advertising Author : Wendi Ji, Xiaoling Wang, Dell Zhang Source : CIKM’ 16 Advisor : Jia-Ling Koh Speaker : Chia-Yi Huang Date : 2017/02/21

Outline ▸ Introduction ▸ Method ▸ Experiment ▸ Conclusion 2

Introduction 3

Introduction ▸ Probabilistic Multi-Touch Attribute ▸ Whether a user will convert ▸ When she will convert 4

Introduction ▸ Survival Analysis ▸ Survival function( ⽣甠存函數 ) ： 
 S(t) = Pr(T>t), T 為⽣甠存時間 , t 為某個時間 ▸ Lifetime distribution function( 衍⽣甠函數 ) ： 
 F(t) = 1 - S(t) = Pr(T <= t) ▸ Hazard function( 危險函數 ) ： 
 λ (t) = F’(t) / S(t) 5

Outline ▸ Introduction ▸ Method ▸ Experiment ▸ Conclusion 6

Method ▸ Weibull Distribution ▸ When α < 1, the hazard rate is a monotonic decreasing function. ▸ When α = 1, the hazard rate is a constant over time 1/ λ ▸ When α > 1, the hazard rate is a monotonic increasing function 7

Method ▸ Weibull Distribution 8

Method ▸ Probabilistic Model ▸ User => {1,…,U} ▸ Advertising Channels => {1,…,K} ▸ Browsing path b u of user u 
 => ▸ l u : length of the ad browsing path b u ▸ : set of features whether conversion occurred when conversion occurred 9

Method ▸ Probabilistic Model ▸ : advertising channel ▸ : timestamp of click / impression ▸ : 1 is conversion has occurred , 0 o.t.w ▸ : last timestamp of the observation window ▸ : = 1, timestamp of the conversion occurred ▸ : 1 is conversion will happen , 0 o.t.w ▸ : conversion delay of an ad exposure ▸ : the elapsed time 10

Method ▸ Probabilistic Model ▸ When Y = 1 11

Method ▸ Probabilistic Model ▸ When Y = 1 Train 12

Method ▸ Probabilistic Model ▸ When Y = 1 Train 13

Method ▸ Probabilistic Model ▸ When Y = 0 14


 
 
 Method ▸ Probabilistic Model ▸ When Y = 0 
 ▸ Y = 1 + Y = 0 15

Method ▸ Parameter Estimation ▸ Multi-Touch Attribution 16

Method ▸ Conversion Prediction 17

Outline ▸ Introduction ▸ Method ▸ Experiment ▸ Conclusion 18

Experiment ▸ DataSet ▸ A large real-world dataset provided by Miaozhen, a leading marketing company in China. ▸ The timestamp, the user ID, the channel ID, the advertising form, the website address, the type of operation system and browser, etc. ▸ 1.24 billion data records ▸ 59 million users(0.01% convert) and 1044 conversions available. ▸ Involved 2498 channels with 40 forms (e.g. iFocus, Button, Social Ad) and 72 websites (e.g. video websites, search engines, social networks) 19

Experiment ▸ Baseline ▸ AdditiveHazard ▸ Simple Probability ▸ Time-aware ▸ Logistic Regression 20

Experiment ▸ Conversion Prediction 21

Experiment ▸ Conversion Prediction included 22

Experiment ▸ Conversion Prediction 23

Experiment ▸ Attribution Analysis 24

Experiment ▸ Attribution Analysis 25

Outline ▸ Introduction ▸ Method ▸ Experiment ▸ Conclusion 26

Conclusion ▸ The PMTA model for conversion attribution which takes into account both the intrinsic conversion rate of a user and the conversion delay. ▸ The PMTA model can be applied to conversion prediction. ▸ The PMTA model is fitted to the observed data (conversion rate and conversion delay) rather than relying on simplistic assumptions. ▸ The PMTA model has been evaluated on a large real-world dataset. 27

THANK YOU