SlideShare une entreprise Scribd logo
1  sur  15
Télécharger pour lire hors ligne
1
Internal mesh optimization
Semantic linking and siloing
Big data
DUPREY Stefan
Cdiscount
ISWAG Deauville, 3 June 2015
Plan 2
Plan
1. Heuristic
2. Metaheuristics
3. Shrinking our universe with siloing and semantic similarity
4. Same problem with an e-commerce flavor
5. Prototyping example
6. Big data implementation : Neo4j and Spark GraphX
7. Video and paper link
ISWAG Deauville, 3 June 2015
Heuristic 3
1. Heuristic
Some notations
Let N ∈ N be the number of nodes in our mesh.
Let (Xi)i∈{1,...,N} be the vertices (URLs) of our oriented graph.
Let (Gij) ∈ {0, 1}
N×N
be the adjacency matrix of our oriented graph.
Let here define f, a given data per URL, which gives a potentiality metrics
for our vertices.
f : (Xi)i∈{1,...,N} → R+
x → f(x)
(1)
ISWAG Deauville, 3 June 2015
Heuristic 4
In-rank
We restrain the universe to our site where we compute the standard
page-rank.
Initialization :
∀u PR (u) =
1
N
(2)
Iterative computation :
PR (u) =
(1 − c)
N
+ c ×
v→u
PR (v)
card ({v → u})
(3)
ISWAG Deauville, 3 June 2015
Heuristic 5
Our heuristic
We want here to optimize the adequacy of our mesh (Xi) to our potentiality
vector f. We here postulate the following heuristic to assess the relevance of
a mesh :
max
(Gij )∈{0,1}N×N
N
i=1
trafic (Xi) × pageRank(Xi) (4)
ISWAG Deauville, 3 June 2015
Metaheuristics 6
2. Metaheuristics
Exhaustive brute force doesn’t work
For a N = 106
millions URLs web site, we have 2N2
with a 2048 bits
mantissa, 256 bits exponent
21062
=
9.5762442314927432848050594956989483747127095675192905698213128517073583274396016675898
714705184143146468453752442806484690561169975498415015777492655947375270159476651418975
300707658547568802353384879419803574730952480197774380552040662758127609571333683703207
910070247048194459504686986124786492353387550318495241621572271925127288273993787778380
450774809611395810191417363401889038757182279484019203870177413318113073911418463615759
647977538478560166958988721048687854280187283661925937530017243461145905573802314471888
491758757162677684017424597014433418179115289463552630751896559312213624470617453325056
5836008e+301029995663
ISWAG Deauville, 3 June 2015
Metaheuristics 7
Picturing our smallest store : jewelery
ISWAG Deauville, 3 June 2015
Metaheuristics 8
Metaheuristics
We here have to maximize over all possible graphs. We have to find a clever
global optimization methodology : metaheuristics such as global search,
multistart, particle swarm, simulated annealing or genetic algorithm are all
good candidates.
What is a genetic algorithm
• Genetic algorithm mimics evolutionary biology to find approximate solutions to optimization problems
• Start with an initial generation of candidate solutions that are tested against the objecive function (fitness
of the individual)
• Subsequent generations evolve from the first through selection, crossover and mutation
• The individual that best minimizes the given objective is returned as the ideal solution
Why a genetic algorithm
• Lots of local minima to avoid
• Non continuous universe, constraints and objective
• Problem with noise and non-smooth data
ISWAG Deauville, 3 June 2015
Metaheuristics 9
Cleverly evolving through our universe
Child spawning from 2 parents crossover
Mutation of an individual
ISWAG Deauville, 3 June 2015
Shrinking our universe with siloing and semantic similarity 10
3. Shrinking our universe with siloing and semantic similarity
Siloing and links categorizing
ISWAG Deauville, 3 June 2015
Shrinking our universe with siloing and semantic similarity 11
Semantic similarity
We slack our universe by allowing links only between semantically similar
URLs :
max
(Gij )∈{0,1}N×N
Gij =0 if CS(ij)≤t
N
i=1
f (Xi) × PR(Xi) (5)
where CS(ij) is a semantic distance between the two linked pages i and j.
CS(ij) can be defined very easily as the scalar product of the tf/idf vectors
of the product descriptions whose weight are defined by the well known
formula :
wik =
tfik log N
nk
t
k=1(tfik)2 log N
nk
2 (6)
ISWAG Deauville, 3 June 2015
Same problem with an e-commerce flavor 12
4. Same problem with an e-commerce flavor
i∈Keywords
SV (i) × CTR (position (i)) × CR (i) × P (i) (7)
where position (i) is the estimated position in search engine results coming
from the modification of our new mesh,
SV (i) is the search volume for the keywords i estimated by the search
engine.
and CTR (i) is the click through rate for an URL at the position place in the
search engine results.
ISWAG Deauville, 3 June 2015
Prototyping example 13
5. Prototyping example
(Xi) =’home’,’metalist1’,’metalist2’,’list1’,’list2’,’list3’,’list4’,’product1’,’product2’,...,’product32’;
f (Xi)=[ 100, 80, 55, 40, 35, 25, 20, 4, 5,...,3 ] ;
Results
ISWAG Deauville, 3 June 2015
Big data implementation : Neo4j and Spark GraphX 14
6. Big data implementation : Neo4j and Spark GraphX
ISWAG Deauville, 3 June 2015
Video and paper link 15
7. Video and paper link
http ://sduprey.github.io/page_rank_optimization_video.html
http ://sduprey.github.io/article_sduprey_iswag_02_06_2015.pdf
http ://sduprey.github.io/PRESENTATION_ISWAG.pdf
ISWAG Deauville, 3 June 2015

Contenu connexe

Tendances (10)

F4 01 Standard Form
F4 01 Standard FormF4 01 Standard Form
F4 01 Standard Form
 
An algorithm for generating new mandelbrot and julia sets
An algorithm for generating new mandelbrot and julia setsAn algorithm for generating new mandelbrot and julia sets
An algorithm for generating new mandelbrot and julia sets
 
Combined operation
Combined operationCombined operation
Combined operation
 
F4 c1 functions__new__1_
F4 c1 functions__new__1_F4 c1 functions__new__1_
F4 c1 functions__new__1_
 
MLconf NYC Edo Liberty
MLconf NYC Edo LibertyMLconf NYC Edo Liberty
MLconf NYC Edo Liberty
 
Worksheet 3 addition & subtraction
Worksheet 3 addition & subtractionWorksheet 3 addition & subtraction
Worksheet 3 addition & subtraction
 
Vedic Mathematics- Combined operation Sum and Product of Numbers
Vedic Mathematics- Combined operation Sum and Product of NumbersVedic Mathematics- Combined operation Sum and Product of Numbers
Vedic Mathematics- Combined operation Sum and Product of Numbers
 
Lesson 5.3 honors
Lesson 5.3 honorsLesson 5.3 honors
Lesson 5.3 honors
 
Logarithm Bases IA
Logarithm Bases IALogarithm Bases IA
Logarithm Bases IA
 
Ppt fiske daels mei drisa desain media komputer
Ppt fiske daels mei drisa desain media komputerPpt fiske daels mei drisa desain media komputer
Ppt fiske daels mei drisa desain media komputer
 

En vedette

Word wall words (pass)
Word wall words (pass)Word wall words (pass)
Word wall words (pass)
sherrywyche
 
99p stores interview questions and answers
99p stores interview questions and answers99p stores interview questions and answers
99p stores interview questions and answers
anbersmith384
 
Khuyến học - Yuichi Fukuzawa
Khuyến học - Yuichi FukuzawaKhuyến học - Yuichi Fukuzawa
Khuyến học - Yuichi Fukuzawa
Son Cao
 
My little stories, Vietnam & Experimental High Energy Physics
My little stories, Vietnam & Experimental High Energy PhysicsMy little stories, Vietnam & Experimental High Energy Physics
My little stories, Vietnam & Experimental High Energy Physics
Son Cao
 
Penggolongan bahan galian
Penggolongan bahan galianPenggolongan bahan galian
Penggolongan bahan galian
ismono widodo
 
Pembangunan Perumahan yang berpusat pada manusia
Pembangunan Perumahan yang berpusat pada manusiaPembangunan Perumahan yang berpusat pada manusia
Pembangunan Perumahan yang berpusat pada manusia
Rissalwan Lubis
 

En vedette (19)

Drive Profit with Google Shopping Campaigns
Drive Profit with Google Shopping CampaignsDrive Profit with Google Shopping Campaigns
Drive Profit with Google Shopping Campaigns
 
Word wall words (pass)
Word wall words (pass)Word wall words (pass)
Word wall words (pass)
 
Ppt01 1
Ppt01 1Ppt01 1
Ppt01 1
 
ученый совет 22 мая 2014 -Выборы декана
ученый совет 22 мая 2014 -Выборы деканаученый совет 22 мая 2014 -Выборы декана
ученый совет 22 мая 2014 -Выборы декана
 
99p stores interview questions and answers
99p stores interview questions and answers99p stores interview questions and answers
99p stores interview questions and answers
 
CompanionAble
CompanionAbleCompanionAble
CompanionAble
 
Khuyến học - Yuichi Fukuzawa
Khuyến học - Yuichi FukuzawaKhuyến học - Yuichi Fukuzawa
Khuyến học - Yuichi Fukuzawa
 
وانةى دةيةم
وانةى دةيةموانةى دةيةم
وانةى دةيةم
 
Edita Kaye: Overcoming Writer's Block
Edita Kaye: Overcoming Writer's BlockEdita Kaye: Overcoming Writer's Block
Edita Kaye: Overcoming Writer's Block
 
dinCloud 2014 year in review
dinCloud 2014 year in reviewdinCloud 2014 year in review
dinCloud 2014 year in review
 
iPad accessibility features for Pasifika students with disabilities
iPad accessibility features for Pasifika students with disabilitiesiPad accessibility features for Pasifika students with disabilities
iPad accessibility features for Pasifika students with disabilities
 
My little stories, Vietnam & Experimental High Energy Physics
My little stories, Vietnam & Experimental High Energy PhysicsMy little stories, Vietnam & Experimental High Energy Physics
My little stories, Vietnam & Experimental High Energy Physics
 
Final report on RoRP project evaluation - Islamic Relief
Final report on RoRP project evaluation - Islamic ReliefFinal report on RoRP project evaluation - Islamic Relief
Final report on RoRP project evaluation - Islamic Relief
 
Edita Kaye: Celebrating Cooking With Coconut
Edita Kaye: Celebrating Cooking With CoconutEdita Kaye: Celebrating Cooking With Coconut
Edita Kaye: Celebrating Cooking With Coconut
 
(Group 18) pck
(Group 18) pck(Group 18) pck
(Group 18) pck
 
Edita Kaye: 4 Items all Writers Should Have on Their Desk
Edita Kaye: 4 Items all Writers Should Have on Their DeskEdita Kaye: 4 Items all Writers Should Have on Their Desk
Edita Kaye: 4 Items all Writers Should Have on Their Desk
 
Penggolongan bahan galian
Penggolongan bahan galianPenggolongan bahan galian
Penggolongan bahan galian
 
وانةى يازدةم
وانةى يازدةموانةى يازدةم
وانةى يازدةم
 
Pembangunan Perumahan yang berpusat pada manusia
Pembangunan Perumahan yang berpusat pada manusiaPembangunan Perumahan yang berpusat pada manusia
Pembangunan Perumahan yang berpusat pada manusia
 

Similaire à Page rank optimization to push successful URLs or products for e-commerce

Operational Intelligence with WSO2 BAM
Operational Intelligence with WSO2 BAM Operational Intelligence with WSO2 BAM
Operational Intelligence with WSO2 BAM
WSO2
 

Similaire à Page rank optimization to push successful URLs or products for e-commerce (20)

Semantic Labeling for Quantitative Data using Wikidata
Semantic Labeling for Quantitative Data using WikidataSemantic Labeling for Quantitative Data using Wikidata
Semantic Labeling for Quantitative Data using Wikidata
 
DevSpace 2018 - Practical Computer Science: What You Need To Know Without Th...
 DevSpace 2018 - Practical Computer Science: What You Need To Know Without Th... DevSpace 2018 - Practical Computer Science: What You Need To Know Without Th...
DevSpace 2018 - Practical Computer Science: What You Need To Know Without Th...
 
Empowering the quantum revolution with Q#
Empowering the quantum revolution with Q#Empowering the quantum revolution with Q#
Empowering the quantum revolution with Q#
 
Inferring Complementary Products from Baskets and Browsing Sessions
Inferring Complementary Products from Baskets and Browsing SessionsInferring Complementary Products from Baskets and Browsing Sessions
Inferring Complementary Products from Baskets and Browsing Sessions
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
 
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdfNeo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
 
Geospatial Data Analysis and Visualization in Python
Geospatial Data Analysis and Visualization in PythonGeospatial Data Analysis and Visualization in Python
Geospatial Data Analysis and Visualization in Python
 
PyData Paris 2015 - Track 1.2 Gilles Louppe
PyData Paris 2015 - Track 1.2 Gilles LouppePyData Paris 2015 - Track 1.2 Gilles Louppe
PyData Paris 2015 - Track 1.2 Gilles Louppe
 
Discover deep insights with Salesforce Einstein Analytics and Discovery
Discover deep insights with Salesforce Einstein Analytics and DiscoveryDiscover deep insights with Salesforce Einstein Analytics and Discovery
Discover deep insights with Salesforce Einstein Analytics and Discovery
 
Simulation Watch Window Part I.pdf
Simulation Watch Window Part I.pdfSimulation Watch Window Part I.pdf
Simulation Watch Window Part I.pdf
 
A Picture is Worth a Thousand Words
A Picture is Worth a Thousand WordsA Picture is Worth a Thousand Words
A Picture is Worth a Thousand Words
 
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
 
Using PyPy instead of Python for speed
Using PyPy instead of Python for speedUsing PyPy instead of Python for speed
Using PyPy instead of Python for speed
 
pattern_evaluaiton_methods.ppt
pattern_evaluaiton_methods.pptpattern_evaluaiton_methods.ppt
pattern_evaluaiton_methods.ppt
 
Operational Intelligence with WSO2 BAM
Operational Intelligence with WSO2 BAM Operational Intelligence with WSO2 BAM
Operational Intelligence with WSO2 BAM
 
Landmark Retrieval & Recognition
Landmark Retrieval & RecognitionLandmark Retrieval & Recognition
Landmark Retrieval & Recognition
 
Enabling GenAI Breakthroughs with Knowledge Graphs
Enabling GenAI Breakthroughs with Knowledge GraphsEnabling GenAI Breakthroughs with Knowledge Graphs
Enabling GenAI Breakthroughs with Knowledge Graphs
 
ELAVARASAN.pdf
ELAVARASAN.pdfELAVARASAN.pdf
ELAVARASAN.pdf
 

Plus de Stefan Duprey

Plus de Stefan Duprey (16)

Dynamical smart liquidity on decentralized exchanges for lucrative market making
Dynamical smart liquidity on decentralized exchanges for lucrative market makingDynamical smart liquidity on decentralized exchanges for lucrative market making
Dynamical smart liquidity on decentralized exchanges for lucrative market making
 
Smart systematic short strangle
Smart systematic short strangleSmart systematic short strangle
Smart systematic short strangle
 
Short Term Intraday Long Only Crypto Strategies
Short Term Intraday Long Only Crypto StrategiesShort Term Intraday Long Only Crypto Strategies
Short Term Intraday Long Only Crypto Strategies
 
On Chain Weekly Rebal Low Expo Strategy
On Chain Weekly Rebal Low Expo StrategyOn Chain Weekly Rebal Low Expo Strategy
On Chain Weekly Rebal Low Expo Strategy
 
Stable_pool_optimal_allocation.pdf
Stable_pool_optimal_allocation.pdfStable_pool_optimal_allocation.pdf
Stable_pool_optimal_allocation.pdf
 
Curve_fairness_IOUs.pdf
Curve_fairness_IOUs.pdfCurve_fairness_IOUs.pdf
Curve_fairness_IOUs.pdf
 
Financial quantitative strategies using artificial intelligence
Financial quantitative strategies using artificial intelligenceFinancial quantitative strategies using artificial intelligence
Financial quantitative strategies using artificial intelligence
 
Intraday news event_study
Intraday news event_studyIntraday news event_study
Intraday news event_study
 
Multi risk factor model
Multi risk factor model Multi risk factor model
Multi risk factor model
 
Impact best bid/ask limit order execution
Impact best bid/ask limit order executionImpact best bid/ask limit order execution
Impact best bid/ask limit order execution
 
Optimal order execution
Optimal order executionOptimal order execution
Optimal order execution
 
A new axisymmetric finite element
A new axisymmetric finite elementA new axisymmetric finite element
A new axisymmetric finite element
 
Compounded autoregressive processes for Credit Risk modelling
Compounded autoregressive processes for Credit Risk modellingCompounded autoregressive processes for Credit Risk modelling
Compounded autoregressive processes for Credit Risk modelling
 
Thesis presentation
Thesis presentationThesis presentation
Thesis presentation
 
Algorithmic trading
Algorithmic tradingAlgorithmic trading
Algorithmic trading
 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_finance
 

Dernier

Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Sheetaleventcompany
 
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
@Chandigarh #call #Girls 9053900678 @Call #Girls in @Punjab 9053900678
 
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
Diya Sharma
 
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
soniya singh
 
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
soniya singh
 
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
Chandigarh Call girls 9053900678 Call girls in Chandigarh
 

Dernier (20)

Moving Beyond Twitter/X and Facebook - Social Media for local news providers
Moving Beyond Twitter/X and Facebook - Social Media for local news providersMoving Beyond Twitter/X and Facebook - Social Media for local news providers
Moving Beyond Twitter/X and Facebook - Social Media for local news providers
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirt
 
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
 
On Starlink, presented by Geoff Huston at NZNOG 2024
On Starlink, presented by Geoff Huston at NZNOG 2024On Starlink, presented by Geoff Huston at NZNOG 2024
On Starlink, presented by Geoff Huston at NZNOG 2024
 
Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Rani Bagh Escort Service Delhi N.C.R.
 
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
 
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort ServiceEnjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 3 Gurgaon >༒8448380779 Escort Service
 
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
 
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
 
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Prashant Vihar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
 
GDG Cloud Southlake 32: Kyle Hettinger: Demystifying the Dark Web
GDG Cloud Southlake 32: Kyle Hettinger: Demystifying the Dark WebGDG Cloud Southlake 32: Kyle Hettinger: Demystifying the Dark Web
GDG Cloud Southlake 32: Kyle Hettinger: Demystifying the Dark Web
 
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
 
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night StandHot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
Hot Call Girls |Delhi |Hauz Khas ☎ 9711199171 Book Your One night Stand
 
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Pratap Nagar Delhi 💯Call Us 🔝8264348440🔝
 
𓀤Call On 7877925207 𓀤 Ahmedguda Call Girls Hot Model With Sexy Bhabi Ready Fo...
𓀤Call On 7877925207 𓀤 Ahmedguda Call Girls Hot Model With Sexy Bhabi Ready Fo...𓀤Call On 7877925207 𓀤 Ahmedguda Call Girls Hot Model With Sexy Bhabi Ready Fo...
𓀤Call On 7877925207 𓀤 Ahmedguda Call Girls Hot Model With Sexy Bhabi Ready Fo...
 
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
Russian Call Girls in %(+971524965298  )#  Call Girls in DubaiRussian Call Girls in %(+971524965298  )#  Call Girls in Dubai
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
 
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Model Towh Delhi 💯Call Us 🔝8264348440🔝
 
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
Low Sexy Call Girls In Mohali 9053900678 🥵Have Save And Good Place 🥵
 

Page rank optimization to push successful URLs or products for e-commerce

  • 1. 1 Internal mesh optimization Semantic linking and siloing Big data DUPREY Stefan Cdiscount ISWAG Deauville, 3 June 2015
  • 2. Plan 2 Plan 1. Heuristic 2. Metaheuristics 3. Shrinking our universe with siloing and semantic similarity 4. Same problem with an e-commerce flavor 5. Prototyping example 6. Big data implementation : Neo4j and Spark GraphX 7. Video and paper link ISWAG Deauville, 3 June 2015
  • 3. Heuristic 3 1. Heuristic Some notations Let N ∈ N be the number of nodes in our mesh. Let (Xi)i∈{1,...,N} be the vertices (URLs) of our oriented graph. Let (Gij) ∈ {0, 1} N×N be the adjacency matrix of our oriented graph. Let here define f, a given data per URL, which gives a potentiality metrics for our vertices. f : (Xi)i∈{1,...,N} → R+ x → f(x) (1) ISWAG Deauville, 3 June 2015
  • 4. Heuristic 4 In-rank We restrain the universe to our site where we compute the standard page-rank. Initialization : ∀u PR (u) = 1 N (2) Iterative computation : PR (u) = (1 − c) N + c × v→u PR (v) card ({v → u}) (3) ISWAG Deauville, 3 June 2015
  • 5. Heuristic 5 Our heuristic We want here to optimize the adequacy of our mesh (Xi) to our potentiality vector f. We here postulate the following heuristic to assess the relevance of a mesh : max (Gij )∈{0,1}N×N N i=1 trafic (Xi) × pageRank(Xi) (4) ISWAG Deauville, 3 June 2015
  • 6. Metaheuristics 6 2. Metaheuristics Exhaustive brute force doesn’t work For a N = 106 millions URLs web site, we have 2N2 with a 2048 bits mantissa, 256 bits exponent 21062 = 9.5762442314927432848050594956989483747127095675192905698213128517073583274396016675898 714705184143146468453752442806484690561169975498415015777492655947375270159476651418975 300707658547568802353384879419803574730952480197774380552040662758127609571333683703207 910070247048194459504686986124786492353387550318495241621572271925127288273993787778380 450774809611395810191417363401889038757182279484019203870177413318113073911418463615759 647977538478560166958988721048687854280187283661925937530017243461145905573802314471888 491758757162677684017424597014433418179115289463552630751896559312213624470617453325056 5836008e+301029995663 ISWAG Deauville, 3 June 2015
  • 7. Metaheuristics 7 Picturing our smallest store : jewelery ISWAG Deauville, 3 June 2015
  • 8. Metaheuristics 8 Metaheuristics We here have to maximize over all possible graphs. We have to find a clever global optimization methodology : metaheuristics such as global search, multistart, particle swarm, simulated annealing or genetic algorithm are all good candidates. What is a genetic algorithm • Genetic algorithm mimics evolutionary biology to find approximate solutions to optimization problems • Start with an initial generation of candidate solutions that are tested against the objecive function (fitness of the individual) • Subsequent generations evolve from the first through selection, crossover and mutation • The individual that best minimizes the given objective is returned as the ideal solution Why a genetic algorithm • Lots of local minima to avoid • Non continuous universe, constraints and objective • Problem with noise and non-smooth data ISWAG Deauville, 3 June 2015
  • 9. Metaheuristics 9 Cleverly evolving through our universe Child spawning from 2 parents crossover Mutation of an individual ISWAG Deauville, 3 June 2015
  • 10. Shrinking our universe with siloing and semantic similarity 10 3. Shrinking our universe with siloing and semantic similarity Siloing and links categorizing ISWAG Deauville, 3 June 2015
  • 11. Shrinking our universe with siloing and semantic similarity 11 Semantic similarity We slack our universe by allowing links only between semantically similar URLs : max (Gij )∈{0,1}N×N Gij =0 if CS(ij)≤t N i=1 f (Xi) × PR(Xi) (5) where CS(ij) is a semantic distance between the two linked pages i and j. CS(ij) can be defined very easily as the scalar product of the tf/idf vectors of the product descriptions whose weight are defined by the well known formula : wik = tfik log N nk t k=1(tfik)2 log N nk 2 (6) ISWAG Deauville, 3 June 2015
  • 12. Same problem with an e-commerce flavor 12 4. Same problem with an e-commerce flavor i∈Keywords SV (i) × CTR (position (i)) × CR (i) × P (i) (7) where position (i) is the estimated position in search engine results coming from the modification of our new mesh, SV (i) is the search volume for the keywords i estimated by the search engine. and CTR (i) is the click through rate for an URL at the position place in the search engine results. ISWAG Deauville, 3 June 2015
  • 13. Prototyping example 13 5. Prototyping example (Xi) =’home’,’metalist1’,’metalist2’,’list1’,’list2’,’list3’,’list4’,’product1’,’product2’,...,’product32’; f (Xi)=[ 100, 80, 55, 40, 35, 25, 20, 4, 5,...,3 ] ; Results ISWAG Deauville, 3 June 2015
  • 14. Big data implementation : Neo4j and Spark GraphX 14 6. Big data implementation : Neo4j and Spark GraphX ISWAG Deauville, 3 June 2015
  • 15. Video and paper link 15 7. Video and paper link http ://sduprey.github.io/page_rank_optimization_video.html http ://sduprey.github.io/article_sduprey_iswag_02_06_2015.pdf http ://sduprey.github.io/PRESENTATION_ISWAG.pdf ISWAG Deauville, 3 June 2015