the talk at twente university on 28 july 2014
DESCRIPTION
Predictive Web Analytics is aimed at understanding behavioural patterns of users of various web-based applications: e-commerce, ubiquitous and mobile computing, and computational advertising. Within these applications business decisions often rely on two types of predictions: an overall or particular user segment demand predictions and individualised recommendations for visitors. Visitor behaviour is inherently sensitive to the context, which can be de ned as a collection of external factors. Context-awareness allows integrating external explanatory information into the learning process and adapting user behaviour accordingly. The importance of context-awareness has been recognised by researchers and practitioners in many disciplines, including recommendation systems, information retrieval, personalization, data mining, and marketing. We focus on studying ways of context discovery and its integration into predictive analytics.TRANSCRIPT
Context Mining and Integration into Web Predictive Analytics
Julia Kiseleva
04/10/2023 2
Outline• What is Web Predictive Analytics• Context-Aware Predictive Analytics
framework• Datasets• User Intent Modeling• Contextual Markov Models• Discovering Change in User intent• Conclusions and Further and Ongoing
work
04/10/2023 3
Understanding user needs
04/10/2023 4
Let’s give it a try…
04/10/2023 5
User Intent Modeling: What?
• Next action predictiono Click prediction on display advertisingo Drop out predictiono User Trail prediction
• Information need predictiono Navigational vs. explorative vs. purchaseo Changes in user intent
• Type of product wanted o Personalization based on contexto Personalization based on changed context
04/10/2023 6
User Intent Modeling: Why?
• To understand users and website usageo redesign websiteo diversified search o search recommendations
• To better use advertisement budgeto When serve ads?o What type of ads to serve? o brand awareness CPM or convergence CPC
• To manipulate user – worth giving a promotion?o personalize with intent of converging to a desired
actiono personalized suggestions based on user context
04/10/2023 7
Web Predictive Analytics
• Web predictive analytics - aims to predict individual and aggregated characteristics indicating visitor behavior for purposes of understanding and optimizing web usage
• Application:o Search engines o Recommender Systemo Computational Advertisement
• Predictive web analytics tasks:o Online shop’s recommendationso Users’ next action predictiono Users’ intention predictingo Personalized search result page
04/10/2023 8
User Intent Modeling: How?
Model L
Users web log
Historicaldata
labels
label?
1. training
3. application
X
y
X'
labels
Testingdata
2. testing
Training:y = L (X)Application:use L for an unseen datay' = L (X')
Formulations:① Classification② Regression ③ Clustering④ Scoring
04/10/2023 9
Type of Context• User Context
o User Preferences o User profileso Usage of user history
• Document/Product Contexto Meta-data o Content features
• Task Contexto Current activity o Location and etc.
• Social Contexto Leveraging the social graph
04/10/2023 10
Example of Context: in Diagnostics
• Not predictive alone but a subset of features with the contextual attribute(s) becomes (much) more predictive
Time of the daycontext
No context
04/10/2023 11
Example of Context: in Marketing
P(Purchase|gender=“male”)=P(Purchase|gender=“female”)
ModelMale~f(relevance); ModelFemale~f(perceived value);
Gendercontext
Male
Female
buy
relevance
buy
don’t
don’t
No contextbuy
relevance
don’tgender
04/10/2023 12
History of context definition and discovery
Context YearLocation 1992Taxonomy of explicit context 1999Predictive features vs. contextual
2002
Hidden context: (clustering, mixture models)
2004
Contextual bandits 2007History of previous interaction 2008Independence of predicted class 2011Two level prediction model 2012Focus on Context Discovery 2012 -
Tim
elin
e
04/10/2023 13
Taxonomy for explicit Context
Human Factors
Physical EnvironmentFactors
User CharacteristicsSocial EnvironmentIntent
Conditions
Infrastructure
Location
*Weather*Light*Acceleration*Audio*…
*Temperature*Humidity*…
04/10/2023 14
Strategies for Context Discovery
Definitions/properties/
utilities
[Un] [Semi] Supervised
methods
How to define context
Context mining: how to discover context
• Contextual features• Contextual
categories
• Features not predictive alone, but increasing predictive power of other features
• Descriptors explaining a significant group of instances having some distinct behaviour
• Subgroup discovery• AntiLDA• Uplift modeling• Actionable attributes
Predictive
model(s)
Predictions
Training data
Context Integration
Output correction
if (context == “spring”) select instances(“spring”)
if (context == “spring”) select models (“spring”)
if (context == “spring”) score += 0.1*score
Instance set selectionFeature set selectionFeature set expansion Model
selection/weightingModel adjustment
04/10/2023 15
Strategies for Context Integration
04/10/2023 16
Learning Classifiers and Contexts
04/10/2023 17
Context-Aware Prediction
04/10/2023 18
Context-Aware Systems
Context definition
Context Integration Method
Application
Context-aware system
Recommendationsystems
Computational Advertisement
Information Retrieval
Normalization
Expansion
Classifier Selection
Classification Adjustment
Weighting
Domain Expert
Clustering
Contextual feature identification
04/10/2023 19
Research Questions1. How to define the context (form and maintain
contextual categories) in web analytics?2. How to connect context with the prediction
process in predictive web analytics?3. How to integrate change detection mechanisms
into the prediction process in web analytics?4. How to ensure integration and feedback
mechanisms between change detection and context awareness mechanisms?
5. What should a reference architecture allowing to plug in new context aware prediction techniques for a collection of web analytics tasks look like?
04/10/2023
• Context-aware ranking of search results
• Drop-out prediction/prevention
• Next action prediction
20
04/10/2023 21
Mastersportal.eu - Homepage
Quick Search
Banner Click
Universities in the spotlight
04/10/2023 22
Mastersportal.eu - Search
Refine Search
Click on Program is Search Result
Click on University
Click on Country
04/10/2023 23
Dataset
DateSource of information
May 2012Mastersportal.eu
#sessions 350.618
#requests 1.775.711
04/10/2023 24
User Trail Prediction
Search Refine Search
PaymentClick Product
ViewClick ?
What is next?
• Does exist any contextual information?• How we can discover it?• How we can utilize it?
04/10/2023 25
Contextual Partitioning
• Approaches to create local models:o Horizontal partitions
Users from Europe
Users from South America
Session 1
Search Refine Search
Click on Banner
Product View
Payment
Session 3
Product View
Payment
Session 3
Search Refine Search
Refine Search
Click on Banner
Session 4
Search Refine Search
Click on Banner
Product View
Payment
Session 5
Product View
Click on Banner
Search
04/10/2023 26
Motivation for Contextual Markov Models
Useful Contexts: E[M] < pc1*E[Mc1] + pc2*E[Mc2]Why should it help?
Explicit contexts (user location) Implicit contexts (inferred from clickstream)
04/10/2023 27
Implicit Context
Discover clusters in the graph using community detection algorithm
c1 = Novice users
c1 = Experience
d users
C = user type
04/10/2023 28
Change of Intent as Context Switch
Timeline
Search Refine Search
PaymentClick Product
ViewSearch Click
Context ``Find information”
Context ``Buy product”
What is next?Change of
intent?
29
Global vs. explicit vs. implicit vs. random contexts
04/10/2023
04/10/2023 30
Temporal Context-Awareness
G H
Temporal Context-Awareness: (G,H,ti)
……
..
G
G
H
H
Web
Sessio
n
S
Contextual features
Contextual Categories
Individual Models
04/10/2023 31
Optimization problem
a b c d abababababcdcdababcdcdcd
The number of true predictions = 0
a b c d
1.0 1.0 1.0
1.0
Hierarchical clustering
a b c d
ab
abababababcdcdababcdcdcd
The number of true predictions = 12
a b c d
1.0
1.0
1.0 1.0
Hierarchical clustering
a b c d
ab
abababababcdcdababcdcdcd
The number of true predictions = 20
a b c d
1.0
1.0
1.0
1.0
cd
Hierarchical clustering
a b c d
ab
abababababcdcdababcdcdcd
The number of true predictions = 20
a b c d
1.0
1.0
1.0
1.0
cd
abcd
Stop as long as no additional prediction benefit of merging
Hierarchical clustering
04/10/2023 36
Mastersportal.eu - Search
Refine Search
Click on Program is Search Result
Click on University
Click on Country
04/10/2023 37
Schema for Hieratical Clustering
Web log
Train:To train
predictive models
Validation:To find Best
clusters
Test:To derive final
accuracy
To find a “Best”
clusters
Calculate final accuracy
To train local predictive
models
04/10/2023 38
Resulted ClustersId Summary Cluster
1 Intensive Search Basic Search, Refine Search, EmptySearch Result
2 Explore informationrelated toprogram
Program impression in search result,Banner click, Program click ,Click on university link
3 Start ofbrowsing
University Spotlight impression,Quick search
4 Explorecountry information
File view, Click on country link
5 Exploresearch result
Program impressions in search results,University impression onnearby universities
6 Explore program Program in landing page, Submitinquiry
7 Outlier Submit question, X-node
04/10/2023 39
Results Temporal Context Discovery
04/10/2023 40
Site Map• Page is represented as set of possible actions
o Example: Homepage is (Quick Search, University Spot light impression, Question Submit)
o Calculate Jaccard similarity between Page and Cluster
04/10/2023 41
Site map
04/10/2023 42
Conclusion• We formulated the context discovery
process as an optimization problem
• Definition of the useful contexts
• Our approach can be used to identify useful contexts for next action prediction
• Experiments on a real dataset provide empirical evidence that our methods are better than baselines
04/10/2023 43
Future works• Testing our method on another datasets
• Introducing a mechanism for detecting context switching within a web-session
• Considering multidimensional contextual features
04/10/2023 44
Thank you!
• Context mining and integration into prediction models
• Accurately predicting users’ desired actions and understanding behavioral patterns of users in various web-applications
• Personalization and adaptation to diverse customer needs and preferences
• Accounting for the practical needs within the considered application areas
04/10/2023 45
Questions?