CAMPAGNA BRAND 0% 0% 0% 0% 0% 0% 0% 0% 0% 0% 100% 90% 75% 60% 45% 30% 10% Last 30 days CTR RANDOM CLUSTER YIELD 0,085 0,080 0,075 0,070 0,065 0,060 0,055 0,050 0,045 0,040 0,035 0,030 0,025 0,020 0,015 0,010 0,005 0,000 242,5 245,0 247,5 250,0 252,5 255,0 257,5 260,0 262,5 265,0 267,5 270,0 272,5 Last 30 days Ecpm RANDOM CLUSTER YIELD 0,16 0,15 0,14 0,13 0,12 0,11 0,10 0,09 0,08 0,07 0,06 0,05 0,04 0,03 0,02 242,5 245,0 247,5 250,0 252,5 255,0 257,5 260,0 262,5 265,0 267,5 270,0 272,5 Results We ran several tests to compare this methodology with competitors platforms and with non optimized impressions.We delivered the same campaigns on the same publishers and si- multaneously by three different delivery algorithms: 1. Our cluster yield method described in this paper / 2. A random non optimized method / 3. A competitor platform based on standard behavioural techniques We executed this test on different days and with different campaigns.We measured an average increase of conversion rate of 150% by the cluster yield method compared with non op- timized delivery.We measured an average increase of conversion rate of 60% by the cluster yield method compared with competitor platform Data-driven behavioural algorithms for online advertising Users Profiling For each user we are able to have information about advertising campaigns, web pages and search queries of interest. We analyze the top significant keywords as- sociated to the content he visited and we are able to extract those ones which have the highest occurency frequency across the corpus of documents. The User Profiling algorithms is then able to build a profile with selected keywords. Clustering Methods The User Similarity Matrix is used to apply an automatic K-Mean Clustering Algorithm. It would be computatio- nally difficult to cluster the huge amount of user profi- les built over Simply Network. As a consequence we developed the following clustering strategy: 1. We apply the clustering methods just on the most active users where for active we mean the fact that they clicked on advertising campaigns and/or launched search queries. 2. Once the clusters are built , we estimate a set of centroids 3. We then built a classification al- gorithm that estimates the di- stance between an user and the centroids of the different cluster and will assign the user to the best matching cluster 4. We classified all profiled users Cluster 30% Affinity percentage
Poster Simply Targeting (HI DEFINITION)
Jul 13, 2015
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
CAMPAGNA BRAND
0%0%
0%0%0%
0%
0%
0%
0%
0%
100%
90%
75%60%
45%
30%
10%
Last 30 days CTR RANDOM CLUSTER YIELD0,0850,0800,0750,0700,0650,0600,0550,0500,0450,0400,0350,0300,0250,0200,0150,0100,0050,000
242,5 245,0 247,5 250,0 252,5 255,0 257,5 260,0 262,5 265,0 267,5 270,0 272,5
Last 30 days Ecpm RANDOM CLUSTER YIELD
0,160,150,140,130,120,110,100,090,080,070,060,050,040,030,02
242,5 245,0 247,5 250,0 252,5 255,0 257,5 260,0 262,5 265,0 267,5 270,0 272,5
ResultsWe ran several tests to compare this methodology with competitors platforms and with non optimized impressions.We delivered the same campaigns on the same publishers and si-multaneously by three different delivery algorithms:1. Our cluster yield method described in this paper / 2. A random non optimized method / 3. A competitor platform based on standard behavioural techniques
We executed this test on different days and with different campaigns.We measured an average increase of conversion rate of 150% by the cluster yield method compared with non op-timized delivery.We measured an average increase of conversion rate of 60% by the cluster yield method compared with competitor platform
Data-driven behavioural algorithmsfor online advertising
Users ProfilingFor each user we are able to have information about advertising campaigns, web pages and search queries of interest. We analyze the top significant keywords as-sociated to the content he visited and we are able to extract those ones which have the highest occurency frequency across the corpus of documents. The User Profiling algorithms is then able to build a profile with selected keywords.
Clustering MethodsThe User Similarity Matrix is used to apply an automatic K-Mean Clustering Algorithm. It would be computatio-nally difficult to cluster the huge amount of user profi-les built over Simply Network. As a consequence we developed the following clustering strategy:1. We apply the clustering methods just on the most active users where for active we mean the fact that they clicked on advertising campaigns and/or launched
search queries.2. Once the clusters are built , we estimate a set
of centroids3. We then built a classification al-gorithm that estimates the di-stance between an user and the centroids of the different cluster
and will assign the user to the best matching cluster
4. We classified all profiled users
Cluster
30%Affinitypercentage
Related Documents
