RecSys Challenge 2016

Fabian Abel
Fabian AbelPost Doc at L3S Research Center
RecSys Challenge 2016
http://recsyschallenge.com - @recsyschallenge
Martha, Róbert, András, Daniel, Fabian
RecSys, Boston, September 2016
Agenda
Proceedings: titanpad.com/recsyschallenge2016
• 09:00-10:30 Welcome + Short presentations
• 10:30-11:00 Coffee break
• 11:00-12:30 Full Papers
• 12:30-14:00 Lunch break
• 14:00-15:30 Full Papers / Top 3
• 15:30-16:00 Coffee break
• 16:00-17:30 Panel Discussion: RecSys Challenge ‘17
2
Job recommendations
Job recommendations
Example: item (job posting)
5
RecSys Challenge
Given a user, the goal is to predict those job postings that the
user will interact with.
6
?
Scala Dev,
Hamburg
job postings
Scala
Engineer
2 months of impressions &
interactions
click
bookmark
Datasets
1. Training data:
• User demographics (jobtitle, discipline, industry, career level, # CV entries,
country, region) [1M]
• Job postings (title, discipline, industry, career level, country region) [1M]
• Interactions (user_id, item_id, interaction_type, timestamp) [10M, 2 months]
• Impressions (user_id, item_id, week) [30M, 2 months]
2. Task files:
• Users (= User IDs for whom recommendations should be computed) [150k]
• Candidate items (= item IDs that are allowed to be recommended) [300k]
3. Solution (secret)
• Interactions (user_id, item_id) [1M, 1 week]
Anonymization (Strings  IDs; users and interactions are enriched with
artitificial noise) 7
Interaction Data
includes interactions that were not performed on recommendations
8
1"
10"
100"
1000"
10000"
100000"
1000000"
1" 10" 100" 1000" 10000" 100000"
number'of'users/items'that'performed/
received'X'interac5ons'
number'of'interac5ons'
items"(train)"
users"(train)"
items"(test)"
users"(test)"
81%$
5%$
2%$
12%$
interac( on*types*
clicks$
replies$
bookmarks$
deletes$
Evaluation Measure
Mixture of…
- Precision@k (k = 2, 4, 6, 20)
= fraction of relevant items in the top k
- Recall@30 = fraction of relevant
items in the top k
- Success@30 = probability that at
least one relevant item was
recommended in the top 30
9
Who participated?
• 119 teams participated (366 teams registered)
• Countries:
 USA (25%)
 Germany (11%)
 China (9%)
 France (7%)
 Hungary (4%)
• Type of organization:
 academia (∼25%)
 industry (∼75%)
 most common industry: Internet & IT
 larger companies such as Yandex, Alibaba, Microsoft or
Amazon as well as start-ups
10
Top score over time
11
0"
100"
200"
300"
400"
500"
600"
700"
0"
500000"
1000000"
1500000"
2000000"
2500000"
0" 5" 10" 15" 20"
Number'of'submissions'during'week'X'
Top'score'at'the'end'of'week'X'
Week'
top"score"(full)"
#submissions"
Number of submissions per team
12
0"
100"
200"
300"
400"
500"
600"
0" 20" 40" 60" 80" 100" 120"
number'of'submissions'
rank'of'team'
Overlap with XING’s recommender
13
0"
2000"
4000"
6000"
8000"
10000"
12000"
0" 5" 10" 15" 20" 25" 30"
number'of'users'
number'of'overlapping'recommenda3ons'
Outlook for 2017
• Current plan:
 Domain: again job recommendations
 Additional perspectives:
 is the user a good candidate for the job?
 Novelty (recommending new jobs)
 New users (recommending jobs to new users)
 Additional features (e.g. clicks from recruiters on profiles)
 Additional tooling:
 Proper API for submitting solutions
 Advanced Baseline implementations (building up on this year’s solutions)
• Goal: offline + online (!!) evaluation
• More details: panel discussion in the afternoon
14
Thank you to PC!
• Alejandro Bellogín, Universidad Autónoma de Madrid, Spain
• Paolo Cremonesi, Politecnico di Milano, Italy
• Simon Dooms, Trackuity, Belgium
• Balasz Hidasi, Gravity R&D, Hungary
• Levente Kocsis, Hungarian Academy of Sciences, Hungary
• Andreas Lommatzsch, TU Berlin, Germany
• Katja Niemann, XING AG, Germany
• Alan Said, University of Skövde, Sweden
• Yue Shi, Yahoo Labs, USA
• Marko Tkalcic, Free University of Bozen-Bolzano, Italy
15
16
Thank you to
RecSys Challenge
participants!
Agenda
• 09:00-10:30 Welcome + Short presentations
• 10:30-11:00 Coffee break
• 11:00-12:30 Full Papers
• 12:30-14:00 Lunch break
• 14:00-15:30 Full Papers / Top 3
• 15:30-16:00 Coffee break
• 16:00-17:30 Panel Discussion: RecSys Challenge ‘17
17
Thank you
@recsyschallenge
http://recsyschallenge.com
www.xing.com
1 of 18

Recommended

Avito recsys-challenge-2016RecSys Challenge 2016: Job Recommendation Based on... by
Avito recsys-challenge-2016RecSys Challenge 2016: Job Recommendation Based on...Avito recsys-challenge-2016RecSys Challenge 2016: Job Recommendation Based on...
Avito recsys-challenge-2016RecSys Challenge 2016: Job Recommendation Based on...Vasily Leksin
1.2K views23 slides
A Combination of Simple Models by Forward Predictor Selection for Job Recomme... by
A Combination of Simple Models by Forward Predictor Selection for Job Recomme...A Combination of Simple Models by Forward Predictor Selection for Job Recomme...
A Combination of Simple Models by Forward Predictor Selection for Job Recomme...David Zibriczky
2K views22 slides
DoWhy Python library for causal inference: An End-to-End tool by
DoWhy Python library for causal inference: An End-to-End toolDoWhy Python library for causal inference: An End-to-End tool
DoWhy Python library for causal inference: An End-to-End toolAmit Sharma
1K views23 slides
LinkedIn talk at Netflix ML Platform meetup Sep 2019 by
LinkedIn talk at Netflix ML Platform meetup Sep 2019LinkedIn talk at Netflix ML Platform meetup Sep 2019
LinkedIn talk at Netflix ML Platform meetup Sep 2019Faisal Siddiqi
3.2K views32 slides
Replication of Recommender Systems Research by
Replication of Recommender Systems ResearchReplication of Recommender Systems Research
Replication of Recommender Systems ResearchAlan Said
1.9K views130 slides
Artwork Personalization at Netflix by
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at NetflixJustin Basilico
28.1K views83 slides

More Related Content

What's hot

Measuring effectiveness of machine learning systems by
Measuring effectiveness of machine learning systemsMeasuring effectiveness of machine learning systems
Measuring effectiveness of machine learning systemsAmit Sharma
874 views65 slides
Rinse and Repeat : The Spiral of Applied Machine Learning by
Rinse and Repeat : The Spiral of Applied Machine LearningRinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine LearningAnna Chaney
60 views29 slides
Managing machine learning by
Managing machine learningManaging machine learning
Managing machine learningDavid Murgatroyd
1.6K views38 slides
Barga Data Science lecture 9 by
Barga Data Science lecture 9Barga Data Science lecture 9
Barga Data Science lecture 9Roger Barga
202 views127 slides
Barga Data Science lecture 1 by
Barga Data Science lecture 1Barga Data Science lecture 1
Barga Data Science lecture 1Roger Barga
263 views95 slides

What's hot(20)

Measuring effectiveness of machine learning systems by Amit Sharma
Measuring effectiveness of machine learning systemsMeasuring effectiveness of machine learning systems
Measuring effectiveness of machine learning systems
Amit Sharma874 views
Rinse and Repeat : The Spiral of Applied Machine Learning by Anna Chaney
Rinse and Repeat : The Spiral of Applied Machine LearningRinse and Repeat : The Spiral of Applied Machine Learning
Rinse and Repeat : The Spiral of Applied Machine Learning
Anna Chaney60 views
Barga Data Science lecture 9 by Roger Barga
Barga Data Science lecture 9Barga Data Science lecture 9
Barga Data Science lecture 9
Roger Barga202 views
Barga Data Science lecture 1 by Roger Barga
Barga Data Science lecture 1Barga Data Science lecture 1
Barga Data Science lecture 1
Roger Barga263 views
Crafting Recommenders: the Shallow and the Deep of it! by Sudeep Das, Ph.D.
Crafting Recommenders: the Shallow and the Deep of it! Crafting Recommenders: the Shallow and the Deep of it!
Crafting Recommenders: the Shallow and the Deep of it!
Sudeep Das, Ph.D.1.8K views
H2O World - Top 10 Data Science Pitfalls - Mark Landry by Sri Ambati
H2O World - Top 10 Data Science Pitfalls - Mark LandryH2O World - Top 10 Data Science Pitfalls - Mark Landry
H2O World - Top 10 Data Science Pitfalls - Mark Landry
Sri Ambati5K views
Intro to machine learning by Tamir Taha
Intro to machine learningIntro to machine learning
Intro to machine learning
Tamir Taha343 views
Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Rec... by Evgeny Frolov
Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Rec...Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Rec...
Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Rec...
Evgeny Frolov428 views
Building a Predictive Model by DKALab
Building a Predictive ModelBuilding a Predictive Model
Building a Predictive Model
DKALab15.7K views
Machine learning the next revolution or just another hype by Jorge Ferrer
Machine learning   the next revolution or just another hypeMachine learning   the next revolution or just another hype
Machine learning the next revolution or just another hype
Jorge Ferrer1.4K views
My Three Ex’s: A Data Science Approach for Applied Machine Learning by Daniel Tunkelang
My Three Ex’s: A Data Science Approach for Applied Machine LearningMy Three Ex’s: A Data Science Approach for Applied Machine Learning
My Three Ex’s: A Data Science Approach for Applied Machine Learning
Daniel Tunkelang15.9K views
Machine Learning 101 by Setu Chokshi
Machine Learning 101Machine Learning 101
Machine Learning 101
Setu Chokshi2.6K views
End-to-End Machine Learning Project by Eng Teong Cheah
End-to-End Machine Learning ProjectEnd-to-End Machine Learning Project
End-to-End Machine Learning Project
Eng Teong Cheah2.5K views
Data Science: A Mindset for Productivity by Daniel Tunkelang
Data Science: A Mindset for ProductivityData Science: A Mindset for Productivity
Data Science: A Mindset for Productivity
Daniel Tunkelang11.9K views
Barga DIDC'14 Invited Talk by Roger Barga
Barga DIDC'14 Invited TalkBarga DIDC'14 Invited Talk
Barga DIDC'14 Invited Talk
Roger Barga223 views
Beyond Churn Prediction : An Introduction to uplift modeling by Pierre Gutierrez
Beyond Churn Prediction : An Introduction to uplift modelingBeyond Churn Prediction : An Introduction to uplift modeling
Beyond Churn Prediction : An Introduction to uplift modeling
Pierre Gutierrez5.4K views
Implementing and analyzing online experiments by Sean Taylor
Implementing and analyzing online experimentsImplementing and analyzing online experiments
Implementing and analyzing online experiments
Sean Taylor3.9K views

Similar to RecSys Challenge 2016

Sutton presentationnasig2017 by
Sutton presentationnasig2017Sutton presentationnasig2017
Sutton presentationnasig2017Sarah Sutton
271 views31 slides
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters by
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing RecruitersHRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing RecruitersJohnny Campbell
1.6K views40 slides
HR Trends 2017 by
HR Trends 2017HR Trends 2017
HR Trends 2017Andrey Kulikov
5.1K views15 slides
Recommendations and Statistics with Graph Databases by
Recommendations and Statistics with Graph DatabasesRecommendations and Statistics with Graph Databases
Recommendations and Statistics with Graph DatabasesCalin Constantinov
58 views50 slides
Xinthe VASOWT Strategy by
Xinthe VASOWT StrategyXinthe VASOWT Strategy
Xinthe VASOWT StrategySrikant Jakilinki
421 views10 slides
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016 by
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016Calin Constantinov
57 views38 slides

Similar to RecSys Challenge 2016(20)

Sutton presentationnasig2017 by Sarah Sutton
Sutton presentationnasig2017Sutton presentationnasig2017
Sutton presentationnasig2017
Sarah Sutton271 views
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters by Johnny Campbell
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing RecruitersHRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters
HRdergi Istanbul 2015 Good to Great: The 6 traits of High Performing Recruiters
Johnny Campbell1.6K views
Recommendations and Statistics with Graph Databases by Calin Constantinov
Recommendations and Statistics with Graph DatabasesRecommendations and Statistics with Graph Databases
Recommendations and Statistics with Graph Databases
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016 by Calin Constantinov
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016
Calin Constantinov - Neo4j - Keyboards and Mice - Craiova 2016
What's wrong with Recruiter-John? A non-trivial recommender challenge. by Fabian Abel
What's wrong with Recruiter-John? A non-trivial recommender challenge.What's wrong with Recruiter-John? A non-trivial recommender challenge.
What's wrong with Recruiter-John? A non-trivial recommender challenge.
Fabian Abel576 views
Webinar: Schema Design by MongoDB
Webinar: Schema DesignWebinar: Schema Design
Webinar: Schema Design
MongoDB3.7K views
KM World Enterprise Social Networking 2007 by Christian Gray
KM World Enterprise Social Networking 2007KM World Enterprise Social Networking 2007
KM World Enterprise Social Networking 2007
Christian Gray456 views
Search Analytics for Fun and Profit by Louis Rosenfeld
Search Analytics for Fun and ProfitSearch Analytics for Fun and Profit
Search Analytics for Fun and Profit
Louis Rosenfeld2.7K views
The People Model & Cloud Transformation - Transformation Day Public Sector Lo... by Amazon Web Services
The People Model & Cloud Transformation - Transformation Day Public Sector Lo...The People Model & Cloud Transformation - Transformation Day Public Sector Lo...
The People Model & Cloud Transformation - Transformation Day Public Sector Lo...
Amazon Web Services1.7K views
AWS re:Invent 2016: Building the Future of DevOps with Amazon Web Services (D... by Amazon Web Services
AWS re:Invent 2016: Building the Future of DevOps with Amazon Web Services (D...AWS re:Invent 2016: Building the Future of DevOps with Amazon Web Services (D...
AWS re:Invent 2016: Building the Future of DevOps with Amazon Web Services (D...
Amazon Web Services1.4K views
The Connected Data Imperative: Why Graphs at GraphDay LA by Neo4j
The Connected Data Imperative: Why Graphs at GraphDay LAThe Connected Data Imperative: Why Graphs at GraphDay LA
The Connected Data Imperative: Why Graphs at GraphDay LA
Neo4j177 views
Tell Your Library's Story with Infographics: Tips From an Accidental Graphic ... by library_research_service
Tell Your Library's Story with Infographics: Tips From an Accidental Graphic ...Tell Your Library's Story with Infographics: Tips From an Accidental Graphic ...
Tell Your Library's Story with Infographics: Tips From an Accidental Graphic ...

Recently uploaded

PRINCIPLES-OF ASSESSMENT by
PRINCIPLES-OF ASSESSMENTPRINCIPLES-OF ASSESSMENT
PRINCIPLES-OF ASSESSMENTrbalmagro
12 views12 slides
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl... by
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...GIFT KIISI NKIN
26 views31 slides
ELECTRON TRANSPORT CHAIN by
ELECTRON TRANSPORT CHAINELECTRON TRANSPORT CHAIN
ELECTRON TRANSPORT CHAINDEEKSHA RANI
7 views16 slides
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdf by
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdfMODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdf
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdfKerryNuez1
25 views5 slides
DATABASE MANAGEMENT SYSTEM by
DATABASE MANAGEMENT SYSTEMDATABASE MANAGEMENT SYSTEM
DATABASE MANAGEMENT SYSTEMDr. GOPINATH D
7 views50 slides
How to be(come) a successful PhD student by
How to be(come) a successful PhD studentHow to be(come) a successful PhD student
How to be(come) a successful PhD studentTom Mens
491 views62 slides

Recently uploaded(20)

PRINCIPLES-OF ASSESSMENT by rbalmagro
PRINCIPLES-OF ASSESSMENTPRINCIPLES-OF ASSESSMENT
PRINCIPLES-OF ASSESSMENT
rbalmagro12 views
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl... by GIFT KIISI NKIN
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...
Synthesis and Characterization of Magnetite-Magnesium Sulphate-Sodium Dodecyl...
GIFT KIISI NKIN26 views
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdf by KerryNuez1
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdfMODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdf
MODULE-9-Biotechnology, Genetically Modified Organisms, and Gene Therapy.pdf
KerryNuez125 views
How to be(come) a successful PhD student by Tom Mens
How to be(come) a successful PhD studentHow to be(come) a successful PhD student
How to be(come) a successful PhD student
Tom Mens491 views
Light Pollution for LVIS students by CWBarthlmew
Light Pollution for LVIS studentsLight Pollution for LVIS students
Light Pollution for LVIS students
CWBarthlmew7 views
별헤는 사람들 2023년 12월호 전명원 교수 자료 by sciencepeople
별헤는 사람들 2023년 12월호 전명원 교수 자료별헤는 사람들 2023년 12월호 전명원 교수 자료
별헤는 사람들 2023년 12월호 전명원 교수 자료
sciencepeople41 views
Conventional and non-conventional methods for improvement of cucurbits.pptx by gandhi976
Conventional and non-conventional methods for improvement of cucurbits.pptxConventional and non-conventional methods for improvement of cucurbits.pptx
Conventional and non-conventional methods for improvement of cucurbits.pptx
gandhi97619 views
"How can I develop my learning path in bioinformatics? by Bioinformy
"How can I develop my learning path in bioinformatics?"How can I develop my learning path in bioinformatics?
"How can I develop my learning path in bioinformatics?
Bioinformy24 views
Pollination By Nagapradheesh.M.pptx by MNAGAPRADHEESH
Pollination By Nagapradheesh.M.pptxPollination By Nagapradheesh.M.pptx
Pollination By Nagapradheesh.M.pptx
MNAGAPRADHEESH16 views
Metatheoretical Panda-Samaneh Borji.pdf by samanehborji
Metatheoretical Panda-Samaneh Borji.pdfMetatheoretical Panda-Samaneh Borji.pdf
Metatheoretical Panda-Samaneh Borji.pdf
samanehborji16 views
Nitrosamine & NDSRI.pptx by NileshBonde4
Nitrosamine & NDSRI.pptxNitrosamine & NDSRI.pptx
Nitrosamine & NDSRI.pptx
NileshBonde417 views
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ... by ILRI
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...
ILRI5 views

RecSys Challenge 2016

  • 1. RecSys Challenge 2016 http://recsyschallenge.com - @recsyschallenge Martha, Róbert, András, Daniel, Fabian RecSys, Boston, September 2016
  • 2. Agenda Proceedings: titanpad.com/recsyschallenge2016 • 09:00-10:30 Welcome + Short presentations • 10:30-11:00 Coffee break • 11:00-12:30 Full Papers • 12:30-14:00 Lunch break • 14:00-15:30 Full Papers / Top 3 • 15:30-16:00 Coffee break • 16:00-17:30 Panel Discussion: RecSys Challenge ‘17 2
  • 5. Example: item (job posting) 5
  • 6. RecSys Challenge Given a user, the goal is to predict those job postings that the user will interact with. 6 ? Scala Dev, Hamburg job postings Scala Engineer 2 months of impressions & interactions click bookmark
  • 7. Datasets 1. Training data: • User demographics (jobtitle, discipline, industry, career level, # CV entries, country, region) [1M] • Job postings (title, discipline, industry, career level, country region) [1M] • Interactions (user_id, item_id, interaction_type, timestamp) [10M, 2 months] • Impressions (user_id, item_id, week) [30M, 2 months] 2. Task files: • Users (= User IDs for whom recommendations should be computed) [150k] • Candidate items (= item IDs that are allowed to be recommended) [300k] 3. Solution (secret) • Interactions (user_id, item_id) [1M, 1 week] Anonymization (Strings  IDs; users and interactions are enriched with artitificial noise) 7
  • 8. Interaction Data includes interactions that were not performed on recommendations 8 1" 10" 100" 1000" 10000" 100000" 1000000" 1" 10" 100" 1000" 10000" 100000" number'of'users/items'that'performed/ received'X'interac5ons' number'of'interac5ons' items"(train)" users"(train)" items"(test)" users"(test)" 81%$ 5%$ 2%$ 12%$ interac( on*types* clicks$ replies$ bookmarks$ deletes$
  • 9. Evaluation Measure Mixture of… - Precision@k (k = 2, 4, 6, 20) = fraction of relevant items in the top k - Recall@30 = fraction of relevant items in the top k - Success@30 = probability that at least one relevant item was recommended in the top 30 9
  • 10. Who participated? • 119 teams participated (366 teams registered) • Countries:  USA (25%)  Germany (11%)  China (9%)  France (7%)  Hungary (4%) • Type of organization:  academia (∼25%)  industry (∼75%)  most common industry: Internet & IT  larger companies such as Yandex, Alibaba, Microsoft or Amazon as well as start-ups 10
  • 11. Top score over time 11 0" 100" 200" 300" 400" 500" 600" 700" 0" 500000" 1000000" 1500000" 2000000" 2500000" 0" 5" 10" 15" 20" Number'of'submissions'during'week'X' Top'score'at'the'end'of'week'X' Week' top"score"(full)" #submissions"
  • 12. Number of submissions per team 12 0" 100" 200" 300" 400" 500" 600" 0" 20" 40" 60" 80" 100" 120" number'of'submissions' rank'of'team'
  • 13. Overlap with XING’s recommender 13 0" 2000" 4000" 6000" 8000" 10000" 12000" 0" 5" 10" 15" 20" 25" 30" number'of'users' number'of'overlapping'recommenda3ons'
  • 14. Outlook for 2017 • Current plan:  Domain: again job recommendations  Additional perspectives:  is the user a good candidate for the job?  Novelty (recommending new jobs)  New users (recommending jobs to new users)  Additional features (e.g. clicks from recruiters on profiles)  Additional tooling:  Proper API for submitting solutions  Advanced Baseline implementations (building up on this year’s solutions) • Goal: offline + online (!!) evaluation • More details: panel discussion in the afternoon 14
  • 15. Thank you to PC! • Alejandro Bellogín, Universidad Autónoma de Madrid, Spain • Paolo Cremonesi, Politecnico di Milano, Italy • Simon Dooms, Trackuity, Belgium • Balasz Hidasi, Gravity R&D, Hungary • Levente Kocsis, Hungarian Academy of Sciences, Hungary • Andreas Lommatzsch, TU Berlin, Germany • Katja Niemann, XING AG, Germany • Alan Said, University of Skövde, Sweden • Yue Shi, Yahoo Labs, USA • Marko Tkalcic, Free University of Bozen-Bolzano, Italy 15
  • 16. 16 Thank you to RecSys Challenge participants!
  • 17. Agenda • 09:00-10:30 Welcome + Short presentations • 10:30-11:00 Coffee break • 11:00-12:30 Full Papers • 12:30-14:00 Lunch break • 14:00-15:30 Full Papers / Top 3 • 15:30-16:00 Coffee break • 16:00-17:30 Panel Discussion: RecSys Challenge ‘17 17