SlideShare a Scribd company logo
Recsys 2018
Conference Overview and Highlights
Recsys Overview
- Deep learning is “omnipresent” now (no more specialized workshop or DL-specific track)
- Reinforcement Learning gaining popularity (industry mostly)
- User-centric papers (calibration, diversity…)
- Evaluation and Metrics
- Recsys Challenge (Spotify) - LTR
- Tutorials (material & slides here)
- Mixed Methods (Spotify)
- Sequence-aware RS (Politecnico di Milano + Pandora)
- OpenRec (open-source and modular library for NN algo’s)
- Deep Learning (Flipkart)
- Emotions and Personality in Recommender Systems
- Many authors are making their code available
Reinforcement Learning
Traditionally used in robotics, games (AlphaGo), self-driving cars...
Why RL in RS? RS have 2 competing goals:
● Recommend items with the highest user predicted engagement (exploit)
● Recommend items with uncertain predicted user engagement to gather more
information (explore)
=> Traditional RS focus on exploiting only.
Exploration is important in settings with new users, new items and dynamic user
preferences.
RS problem framed as a RL problem
RL: Sequential decision making problem
At step t, an agent must perform an action at
in an uncertain environment which
presents the agent with a new reward r(t+1)
and a new state s(t+1).
Example:
● action: recommend a product
● reward: click or no click (binary)
The goal of the agent is to learn a policy indicating the action that maximises the
total reward collected: greedy, epsilon-greedy, upper confidence bound (UCD),
Thompson sampling...
Netflix: Artwork recommendation using RL
Personalise artwork of movie titles so users can better decide whether to watch
something or not
Netflix: Artwork recommendation using RL
Netflix: Artwork recommendation using RL
Choose an
action
uniformly at
random with
probability
epsilon.
RL @ Recsys 2018
- REVEAL: workshop on Offline Evaluation for Recommender Systems
- BEARS (Insight, Athena): Evaluation framework to test bandit-based RS
- Netflix: Artwork recommendation using RL
- Pandora: Rank modules to show to users (i.e. “friday mood”, ...)
- Spotify: Jointly learn what items and explanations to show to users
- Criteo: Causal Embeddings (best paper)
- Deal with data confounded by the recommender by combining a large sample of biased
feedback data with a small sample of unbiased feedback data.
However...
Deep Reinforcement Learning Doesn't Work Yet (Feb 2018)
Reinforcement Learning never worked, and 'deep' only helped a bit (Feb 2018)
RL Researchers
Improving user
experience
Calibrated Recommendations (Steck)
- Nominated paper by Harald Steck (Netflix)
- RS trained on accuracy tend to focus on user’s main interests (unbalanced
recommendations)
- E.g. user’s items 70% romance and 30% action → an uncalibrated algorithm
would recommend most items in the romance category
- The work proposes
a calibration metric
and performs an
evaluation on
MovieLens
Calibration Metric
Calibration Metric
CKL
(p, q) = 0 → p(g | u) = q(g | u) (perfect calibration)
Calibration Method
Goal: Find the optimal set I* of items to recommend
Maximum marginal relevance:
Calibration vs Diversity
If we have 2 genres, romance and action, the most diverse list would contain 50%
romance and 50% action movies.
But it does not consider the accuracy - diversity tradeoff for each user (some
users may not want diverse recommendations) -> ~ personalized diversity
Extension taking into account diversity (introduce a new param beta that controls
the calibration-diversity tradeoff):
Diversity-
promoting
prior
Calibration
target
Results
calibration - accuracy tradeoff (controlled by lambda)
Reciprocal Recommender Systems (Kleinerman et al)
Reciprocal -> online dating, jobs… (recommending people), marketplaces (items)
For each user receiving a recommendation, the system finds the optimal balance
of:
● Likelihood of the user accepting the recommendation
● Likelihood of the recommended user positively responding
Evaluation on an online dating site (app)
marketplaces,
Reciprocal Recommender Systems (Kleinerman et al)
Approach based on combining:
● Collaborative filtering -> score for each user pair CF(x,y)
● AdaBoost classifier that predicts the probability that a user will respond to
another user based on features from the sender and the receiver (content +
popularity features) -> PR(y,x)
Classifier AUC = 0.83
Baseline = CF (on its own)
Learn a weight that balances CF and PR
Recsys Challenge
Automatic Playlist Continuation
Given a playlist, what songs should be played after?
Input: A user-created playlist, represented by:
● Playlist metadata
● A list of the K tracks in the playlist, K = [0, 1, 5, 10, 25, or 100]
Output: A list of 500 recommended tracks, ordered by relevance
Top 3 Teams:
1st place: Two-stage model:
● 1st: WRMF + CNN + user-user + item-Item neighborhood models.
● 2nd: gradient boosting model used to re-rank the retrieved songs
2nd place: Multimodal CF that uses an autoencoder and a character-level CBB
3rd place: Two-stage model:
● 1st: LightFM
● 2nd: gradient boosting
Winning Team Model Architecture
Two-stage Model for Automatic Playlist Continuation at Scale [Volkovs et al]
Winning Team Model Architecture
First Stage: Linear weighted ensemble method:
Second Stage: Learning to rank using gradient boosting trees (GBT)
● first stage scores (s_blend, s_wrmf…) + other engineered features
● pairwise ranking loss
● 150 trees; depth = 10 (XGBoost library)
Cold-start handled as a separate problem
Main Findings
● Blending (1st stage) already produced high performance (high recall of 90% 20K
candidate songs - 60% in the top 1K).
● Neighbourhood based approaches outperformed CNN and WRMF (CNN was
the worst performing)
● Re-scaling similarity scores using inverse popularity [Verstrepen et al]
significantly improved the accuracy of the 2 neighbourhood-based approaches
● First few trees of GBM (2nd stage) already beat performance of blending (1st
stage) because GBM uses output of blender (scores of the different models)
as input
2nd place: Multimodal Collaborative Filtering
Multimodal approach that uses:
1. an autoencoder using the playlist
and its categorical contents
2. a character-level CNN that only
uses the playlist title
MMCF: Multimodal Collaborative Filtering for
Automatic Playlist Continuation. [Yang et al.]
2nd place: Multimodal Collaborative Filtering
Combine the two models using a linear combination of output vectors witem
& wtitle
The autoencoder can capture the characteristics of a given playlist more precisely
as the number of input items increases → give more weight to witem
when number
of items is higher
N([p; ap
]): number of items I(Tp
): importance of the playlist title
3rd place: hybrid two-stage recommender
1st stage: LightFM used for generating candidates
2nd stage:
● LightFM features (features produced by LightFM (score(p, t) but also bp
,bt
,
< qp
,qt
>) -- p=playlist, t=track
● Co-occurrence features related to playlist p and candidate track t
● e.g. number of playlists containing tracks t_i and t… → calculate it for each track in the playlist
t_i and candidate track t. Use mean, min, max, and median statistics over the tracks in the
playlist)
A hybrid two-stage recommender system for automatic playlist continuation
Evaluation
and
Metrics
On the Robustness and Discriminative Power
of IR Metrics for Top-N Recommendation (Valcarce et al)
● Studies the robustness and discriminative power of several ranking metrics
(originally used in IR) when applied to the top-N recommendation task.
● A desirable metric for recommendation should be robust to incompleteness in
the test set.
● Assess robustness by simulating sparsity and popularity bias in the test set
(removing at random or removing top popular) and recalculating the metrics.
● Compare rankings of the test sets with Kendall’s correlation
On the Robustness and Discriminative Power
of IR Metrics for Top-N Recommendation (Valcarce et al)
3 datasets and 21 recommendation algorithms (All Items methodology)
● Precision is very robust to sparsity and popularity biases
● NDCG → high robustness to the sparsity bias and moderate robustness to
the popularity bias.
● MRR: performs poorly in RS evaluation.
Interesting approach to evaluate the robustness of our metrics for our own
datasets
Judging Similarity: A user-centric study of related
item recommendations (Yao et al.)
Evaluate item similarity Evaluate recommendation quality
Judging Similarity: A user-centric study of related
item recommendations (Yao et al.)
● User-centric evaluation of 6 related item algorithms: random,
content- based (tag genome), content-based (user reviews), svd,
item2vec, arm
● 700 participants (Movielens users invited by email)
● 2 research questions:
○ Which related item algorithms best match user perceptions of relatedness and
recommendation quality?
○ How should related item algorithms be designed to improve the user experience?
● Survey and responses are publicly available
Stratified sampling strategy
● 100 source items sampled from the top 2500 most popular items
○ Easier for people to know about the movies
○ 2500 most popular account for 80% of user ratings
● Stratified -> split 2500 into 10 groups, pick 10 random movies from each
● For each algorithm, retrieve top 10 neighbours
● Top 10,000 items considered as target items
High correlation
between similarity
and recom. Quality
(0.80 Spearman
rank-order
correlation)
CB approaches outperform CF-based ones in terms of user
expectations for similarity and recommendation quality
Results and Conclusions of the Study
- Content-based approaches item-similarity matches the most with user
expectations compared to CF approaches
- Perceived recommendation quality is also better.
- Users said they want something in between “similar to their interests” and “not
obvious”
- Based on the user’s feedback the authors suggest that related item
recommendations should combine item similarity with other factors such as
diversity and serendipity.
Interpreting User Inaction (Zhao et al.)
Most work focuses on user’s interactions with items. This work focuses on
studying the lack of interaction / inaction through a live user survey on MovieLens.
Inaction doesn’t always mean negative feedback. E.g. “explore later” type of
inaction is a positive user feedback.
Research questions:
● What causes inaction?
● Can inaction reason be predicted?
● Can we improve recommender systems using an inaction model?
Interpreting User Inaction (Zhao et al.)
7 categories of inaction:
● Not Noticed / Lack of attention (38.6%)
● Not Now (18.2%)
● Already Watched (14.6%)
● Others Better Titles (9.5%)
● Explore Later / Need more info to make a decision (6.9%)
● Would Not Enjoy / Not matching user’s taste (5.8%)
● Already Decided To Watch (5.8%)
User’s lack of attention → UI design should try to optimize user attention
Interpreting User Inaction (Zhao et al.)
Used a multinomial regression model to predict the type / category of user
inaction.
Main Findings:
=> Reason for inaction is hard to predict → overall poor classification performance
but some categories have high accuracy.
=> Predicted probability of “Not Now” could be used when to “skip” showing a
recommendation and wait for a future session to show it.
Mixed Methods
(Tutorial)
Mixed Methods (Discovery Weekly @ Spotify)
Qualitative
Quantitative
Mixed Methods (Discovery Weekly @ Spotify)
Qualitative:
How to do interviews and surveys (best practices)
E.g. scales shouldn’t have numbers, should have words
Quantitative:
How to collect data: attention, interaction, task-success
Recsys 2019
See you in Copenhagen

More Related Content

What's hot

Recommender Systems, Matrices and Graphs
Recommender Systems, Matrices and GraphsRecommender Systems, Matrices and Graphs
Recommender Systems, Matrices and Graphs
Roelof Pieters
 
Matrix Factorization Technique for Recommender Systems
Matrix Factorization Technique for Recommender SystemsMatrix Factorization Technique for Recommender Systems
Matrix Factorization Technique for Recommender Systems
Aladejubelo Oluwashina
 
Recommender Systems from A to Z – The Right Dataset
Recommender Systems from A to Z – The Right DatasetRecommender Systems from A to Z – The Right Dataset
Recommender Systems from A to Z – The Right Dataset
Crossing Minds
 
Building Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyBuilding Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at Spotify
Vidhya Murali
 
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
Arjen de Vries
 
Summary of a Recommender Systems Survey paper
Summary of a Recommender Systems Survey paperSummary of a Recommender Systems Survey paper
Summary of a Recommender Systems Survey paper
Changsung Moon
 
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
Iván Palomares Carrascosa
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
YONG ZHENG
 
Item Based Collaborative Filtering Recommendation Algorithms
Item Based Collaborative Filtering Recommendation AlgorithmsItem Based Collaborative Filtering Recommendation Algorithms
Item Based Collaborative Filtering Recommendation Algorithmsnextlib
 
Recommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model TrainingRecommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model Training
Crossing Minds
 
Recommender systems
Recommender systemsRecommender systems
Recommender systems
Tamer Rezk
 
CF Models for Music Recommendations At Spotify
CF Models for Music Recommendations At SpotifyCF Models for Music Recommendations At Spotify
CF Models for Music Recommendations At Spotify
Vidhya Murali
 
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
YONG ZHENG
 
Collaborative Filtering
Collaborative FilteringCollaborative Filtering
Collaborative Filtering
Tayfun Sen
 
Scala Data Pipelines for Music Recommendations
Scala Data Pipelines for Music RecommendationsScala Data Pipelines for Music Recommendations
Scala Data Pipelines for Music Recommendations
Chris Johnson
 
Next directions in Mahout's recommenders
Next directions in Mahout's recommendersNext directions in Mahout's recommenders
Next directions in Mahout's recommenders
sscdotopen
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Ernesto Mislej
 
Collaborative filtering
Collaborative filteringCollaborative filtering
Collaborative filtering
Kishor Datta Gupta
 
Filtering content bbased crs
Filtering content bbased crsFiltering content bbased crs
Filtering content bbased crs
Aravindharamanan S
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender Systems
YONG ZHENG
 

What's hot (20)

Recommender Systems, Matrices and Graphs
Recommender Systems, Matrices and GraphsRecommender Systems, Matrices and Graphs
Recommender Systems, Matrices and Graphs
 
Matrix Factorization Technique for Recommender Systems
Matrix Factorization Technique for Recommender SystemsMatrix Factorization Technique for Recommender Systems
Matrix Factorization Technique for Recommender Systems
 
Recommender Systems from A to Z – The Right Dataset
Recommender Systems from A to Z – The Right DatasetRecommender Systems from A to Z – The Right Dataset
Recommender Systems from A to Z – The Right Dataset
 
Building Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyBuilding Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at Spotify
 
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
Similarity & Recommendation - CWI Scientific Meeting - Sep 27th, 2013
 
Summary of a Recommender Systems Survey paper
Summary of a Recommender Systems Survey paperSummary of a Recommender Systems Survey paper
Summary of a Recommender Systems Survey paper
 
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
ACM SIGIR 2020 Tutorial - Reciprocal Recommendation: matching users with the ...
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
 
Item Based Collaborative Filtering Recommendation Algorithms
Item Based Collaborative Filtering Recommendation AlgorithmsItem Based Collaborative Filtering Recommendation Algorithms
Item Based Collaborative Filtering Recommendation Algorithms
 
Recommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model TrainingRecommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model Training
 
Recommender systems
Recommender systemsRecommender systems
Recommender systems
 
CF Models for Music Recommendations At Spotify
CF Models for Music Recommendations At SpotifyCF Models for Music Recommendations At Spotify
CF Models for Music Recommendations At Spotify
 
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
 
Collaborative Filtering
Collaborative FilteringCollaborative Filtering
Collaborative Filtering
 
Scala Data Pipelines for Music Recommendations
Scala Data Pipelines for Music RecommendationsScala Data Pipelines for Music Recommendations
Scala Data Pipelines for Music Recommendations
 
Next directions in Mahout's recommenders
Next directions in Mahout's recommendersNext directions in Mahout's recommenders
Next directions in Mahout's recommenders
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011
 
Collaborative filtering
Collaborative filteringCollaborative filtering
Collaborative filtering
 
Filtering content bbased crs
Filtering content bbased crsFiltering content bbased crs
Filtering content bbased crs
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender Systems
 

Similar to Recsys 2018 overview and highlights

Recommendation Systems
Recommendation SystemsRecommendation Systems
Recommendation Systems
Robin Reni
 
Rokach-GomaxSlides (1).pptx
Rokach-GomaxSlides (1).pptxRokach-GomaxSlides (1).pptx
Rokach-GomaxSlides (1).pptx
Jadna Almeida
 
Rokach-GomaxSlides.pptx
Rokach-GomaxSlides.pptxRokach-GomaxSlides.pptx
Rokach-GomaxSlides.pptx
Jadna Almeida
 
Search Quality Evaluation to Help Reproducibility: An Open-source Approach
Search Quality Evaluation to Help Reproducibility: An Open-source ApproachSearch Quality Evaluation to Help Reproducibility: An Open-source Approach
Search Quality Evaluation to Help Reproducibility: An Open-source Approach
Alessandro Benedetti
 
IntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdfIntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdf
AlphaIssaghaDiallo
 
Buidling large scale recommendation engine
Buidling large scale recommendation engineBuidling large scale recommendation engine
Buidling large scale recommendation engine
Keeyong Han
 
acmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptxacmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptx
dongchangim30
 
Search Quality Evaluation to Help Reproducibility : an Open Source Approach
Search Quality Evaluation to Help Reproducibility : an Open Source ApproachSearch Quality Evaluation to Help Reproducibility : an Open Source Approach
Search Quality Evaluation to Help Reproducibility : an Open Source Approach
Alessandro Benedetti
 
Recommender Systems and Linked Open Data
Recommender Systems and Linked Open DataRecommender Systems and Linked Open Data
Recommender Systems and Linked Open Data
Polytechnic University of Bari
 
Sistemas de Recomendação sem Enrolação
Sistemas de Recomendação sem Enrolação Sistemas de Recomendação sem Enrolação
Sistemas de Recomendação sem Enrolação
Gabriel Moreira
 
Summer internship 2014 report by Rishabh Misra, Thapar University
Summer internship 2014 report by Rishabh Misra, Thapar UniversitySummer internship 2014 report by Rishabh Misra, Thapar University
Summer internship 2014 report by Rishabh Misra, Thapar UniversityRishabh Misra
 
Item basedcollaborativefilteringrecommendationalgorithms
Item basedcollaborativefilteringrecommendationalgorithmsItem basedcollaborativefilteringrecommendationalgorithms
Item basedcollaborativefilteringrecommendationalgorithms
Aravindharamanan S
 
Recsys2016 Tutorial by Xavier and Deepak
Recsys2016 Tutorial by Xavier and DeepakRecsys2016 Tutorial by Xavier and Deepak
Recsys2016 Tutorial by Xavier and Deepak
Deepak Agarwal
 
CSTalks-Quaternary Semantics Recomandation System-24 Aug
CSTalks-Quaternary Semantics Recomandation System-24 AugCSTalks-Quaternary Semantics Recomandation System-24 Aug
CSTalks-Quaternary Semantics Recomandation System-24 Augcstalks
 
Collaborative Filtering Recommendation System
Collaborative Filtering Recommendation SystemCollaborative Filtering Recommendation System
Collaborative Filtering Recommendation System
Milind Gokhale
 
Overview of recommender system
Overview of recommender systemOverview of recommender system
Overview of recommender system
Stanley Wang
 
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
OpenSource Connections
 
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Alessandro Benedetti
 
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Sease
 
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by HadoopRecommendation Engine Powered by Hadoop
Recommendation Engine Powered by HadoopPranab Ghosh
 

Similar to Recsys 2018 overview and highlights (20)

Recommendation Systems
Recommendation SystemsRecommendation Systems
Recommendation Systems
 
Rokach-GomaxSlides (1).pptx
Rokach-GomaxSlides (1).pptxRokach-GomaxSlides (1).pptx
Rokach-GomaxSlides (1).pptx
 
Rokach-GomaxSlides.pptx
Rokach-GomaxSlides.pptxRokach-GomaxSlides.pptx
Rokach-GomaxSlides.pptx
 
Search Quality Evaluation to Help Reproducibility: An Open-source Approach
Search Quality Evaluation to Help Reproducibility: An Open-source ApproachSearch Quality Evaluation to Help Reproducibility: An Open-source Approach
Search Quality Evaluation to Help Reproducibility: An Open-source Approach
 
IntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdfIntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdf
 
Buidling large scale recommendation engine
Buidling large scale recommendation engineBuidling large scale recommendation engine
Buidling large scale recommendation engine
 
acmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptxacmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptx
 
Search Quality Evaluation to Help Reproducibility : an Open Source Approach
Search Quality Evaluation to Help Reproducibility : an Open Source ApproachSearch Quality Evaluation to Help Reproducibility : an Open Source Approach
Search Quality Evaluation to Help Reproducibility : an Open Source Approach
 
Recommender Systems and Linked Open Data
Recommender Systems and Linked Open DataRecommender Systems and Linked Open Data
Recommender Systems and Linked Open Data
 
Sistemas de Recomendação sem Enrolação
Sistemas de Recomendação sem Enrolação Sistemas de Recomendação sem Enrolação
Sistemas de Recomendação sem Enrolação
 
Summer internship 2014 report by Rishabh Misra, Thapar University
Summer internship 2014 report by Rishabh Misra, Thapar UniversitySummer internship 2014 report by Rishabh Misra, Thapar University
Summer internship 2014 report by Rishabh Misra, Thapar University
 
Item basedcollaborativefilteringrecommendationalgorithms
Item basedcollaborativefilteringrecommendationalgorithmsItem basedcollaborativefilteringrecommendationalgorithms
Item basedcollaborativefilteringrecommendationalgorithms
 
Recsys2016 Tutorial by Xavier and Deepak
Recsys2016 Tutorial by Xavier and DeepakRecsys2016 Tutorial by Xavier and Deepak
Recsys2016 Tutorial by Xavier and Deepak
 
CSTalks-Quaternary Semantics Recomandation System-24 Aug
CSTalks-Quaternary Semantics Recomandation System-24 AugCSTalks-Quaternary Semantics Recomandation System-24 Aug
CSTalks-Quaternary Semantics Recomandation System-24 Aug
 
Collaborative Filtering Recommendation System
Collaborative Filtering Recommendation SystemCollaborative Filtering Recommendation System
Collaborative Filtering Recommendation System
 
Overview of recommender system
Overview of recommender systemOverview of recommender system
Overview of recommender system
 
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
 
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
 
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
 
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by HadoopRecommendation Engine Powered by Hadoop
Recommendation Engine Powered by Hadoop
 

Recently uploaded

一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
nscud
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
vcaxypu
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
MaleehaSheikh2
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
ArpitMalhotra16
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMI
AlejandraGmez176757
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
ewymefz
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
alex933524
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Linda486226
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar
 
社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .
NABLAS株式会社
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
axoqas
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
StarCompliance.io
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
axoqas
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
jerlynmaetalle
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单
enxupq
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
James Polillo
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
Oppotus
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
haila53
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Subhajit Sahu
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 

Recently uploaded (20)

一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
 
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
一比一原版(ArtEZ毕业证)ArtEZ艺术学院毕业证成绩单
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMI
 
一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
 
社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
 
一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单一比一原版(QU毕业证)皇后大学毕业证成绩单
一比一原版(QU毕业证)皇后大学毕业证成绩单
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
 
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdfCh03-Managing the Object-Oriented Information Systems Project a.pdf
Ch03-Managing the Object-Oriented Information Systems Project a.pdf
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 

Recsys 2018 overview and highlights

  • 2. Recsys Overview - Deep learning is “omnipresent” now (no more specialized workshop or DL-specific track) - Reinforcement Learning gaining popularity (industry mostly) - User-centric papers (calibration, diversity…) - Evaluation and Metrics - Recsys Challenge (Spotify) - LTR - Tutorials (material & slides here) - Mixed Methods (Spotify) - Sequence-aware RS (Politecnico di Milano + Pandora) - OpenRec (open-source and modular library for NN algo’s) - Deep Learning (Flipkart) - Emotions and Personality in Recommender Systems - Many authors are making their code available
  • 3. Reinforcement Learning Traditionally used in robotics, games (AlphaGo), self-driving cars... Why RL in RS? RS have 2 competing goals: ● Recommend items with the highest user predicted engagement (exploit) ● Recommend items with uncertain predicted user engagement to gather more information (explore) => Traditional RS focus on exploiting only. Exploration is important in settings with new users, new items and dynamic user preferences.
  • 4. RS problem framed as a RL problem RL: Sequential decision making problem At step t, an agent must perform an action at in an uncertain environment which presents the agent with a new reward r(t+1) and a new state s(t+1). Example: ● action: recommend a product ● reward: click or no click (binary) The goal of the agent is to learn a policy indicating the action that maximises the total reward collected: greedy, epsilon-greedy, upper confidence bound (UCD), Thompson sampling...
  • 5. Netflix: Artwork recommendation using RL Personalise artwork of movie titles so users can better decide whether to watch something or not
  • 7. Netflix: Artwork recommendation using RL Choose an action uniformly at random with probability epsilon.
  • 8. RL @ Recsys 2018 - REVEAL: workshop on Offline Evaluation for Recommender Systems - BEARS (Insight, Athena): Evaluation framework to test bandit-based RS - Netflix: Artwork recommendation using RL - Pandora: Rank modules to show to users (i.e. “friday mood”, ...) - Spotify: Jointly learn what items and explanations to show to users - Criteo: Causal Embeddings (best paper) - Deal with data confounded by the recommender by combining a large sample of biased feedback data with a small sample of unbiased feedback data.
  • 9. However... Deep Reinforcement Learning Doesn't Work Yet (Feb 2018) Reinforcement Learning never worked, and 'deep' only helped a bit (Feb 2018) RL Researchers
  • 11. Calibrated Recommendations (Steck) - Nominated paper by Harald Steck (Netflix) - RS trained on accuracy tend to focus on user’s main interests (unbalanced recommendations) - E.g. user’s items 70% romance and 30% action → an uncalibrated algorithm would recommend most items in the romance category - The work proposes a calibration metric and performs an evaluation on MovieLens
  • 13. Calibration Metric CKL (p, q) = 0 → p(g | u) = q(g | u) (perfect calibration)
  • 14. Calibration Method Goal: Find the optimal set I* of items to recommend Maximum marginal relevance:
  • 15. Calibration vs Diversity If we have 2 genres, romance and action, the most diverse list would contain 50% romance and 50% action movies. But it does not consider the accuracy - diversity tradeoff for each user (some users may not want diverse recommendations) -> ~ personalized diversity Extension taking into account diversity (introduce a new param beta that controls the calibration-diversity tradeoff): Diversity- promoting prior Calibration target
  • 16. Results calibration - accuracy tradeoff (controlled by lambda)
  • 17. Reciprocal Recommender Systems (Kleinerman et al) Reciprocal -> online dating, jobs… (recommending people), marketplaces (items) For each user receiving a recommendation, the system finds the optimal balance of: ● Likelihood of the user accepting the recommendation ● Likelihood of the recommended user positively responding Evaluation on an online dating site (app) marketplaces,
  • 18. Reciprocal Recommender Systems (Kleinerman et al) Approach based on combining: ● Collaborative filtering -> score for each user pair CF(x,y) ● AdaBoost classifier that predicts the probability that a user will respond to another user based on features from the sender and the receiver (content + popularity features) -> PR(y,x) Classifier AUC = 0.83 Baseline = CF (on its own) Learn a weight that balances CF and PR
  • 20. Automatic Playlist Continuation Given a playlist, what songs should be played after? Input: A user-created playlist, represented by: ● Playlist metadata ● A list of the K tracks in the playlist, K = [0, 1, 5, 10, 25, or 100] Output: A list of 500 recommended tracks, ordered by relevance
  • 21. Top 3 Teams: 1st place: Two-stage model: ● 1st: WRMF + CNN + user-user + item-Item neighborhood models. ● 2nd: gradient boosting model used to re-rank the retrieved songs 2nd place: Multimodal CF that uses an autoencoder and a character-level CBB 3rd place: Two-stage model: ● 1st: LightFM ● 2nd: gradient boosting
  • 22. Winning Team Model Architecture Two-stage Model for Automatic Playlist Continuation at Scale [Volkovs et al]
  • 23. Winning Team Model Architecture First Stage: Linear weighted ensemble method: Second Stage: Learning to rank using gradient boosting trees (GBT) ● first stage scores (s_blend, s_wrmf…) + other engineered features ● pairwise ranking loss ● 150 trees; depth = 10 (XGBoost library) Cold-start handled as a separate problem
  • 24. Main Findings ● Blending (1st stage) already produced high performance (high recall of 90% 20K candidate songs - 60% in the top 1K). ● Neighbourhood based approaches outperformed CNN and WRMF (CNN was the worst performing) ● Re-scaling similarity scores using inverse popularity [Verstrepen et al] significantly improved the accuracy of the 2 neighbourhood-based approaches ● First few trees of GBM (2nd stage) already beat performance of blending (1st stage) because GBM uses output of blender (scores of the different models) as input
  • 25. 2nd place: Multimodal Collaborative Filtering Multimodal approach that uses: 1. an autoencoder using the playlist and its categorical contents 2. a character-level CNN that only uses the playlist title MMCF: Multimodal Collaborative Filtering for Automatic Playlist Continuation. [Yang et al.]
  • 26. 2nd place: Multimodal Collaborative Filtering Combine the two models using a linear combination of output vectors witem & wtitle The autoencoder can capture the characteristics of a given playlist more precisely as the number of input items increases → give more weight to witem when number of items is higher N([p; ap ]): number of items I(Tp ): importance of the playlist title
  • 27. 3rd place: hybrid two-stage recommender 1st stage: LightFM used for generating candidates 2nd stage: ● LightFM features (features produced by LightFM (score(p, t) but also bp ,bt , < qp ,qt >) -- p=playlist, t=track ● Co-occurrence features related to playlist p and candidate track t ● e.g. number of playlists containing tracks t_i and t… → calculate it for each track in the playlist t_i and candidate track t. Use mean, min, max, and median statistics over the tracks in the playlist) A hybrid two-stage recommender system for automatic playlist continuation
  • 29. On the Robustness and Discriminative Power of IR Metrics for Top-N Recommendation (Valcarce et al) ● Studies the robustness and discriminative power of several ranking metrics (originally used in IR) when applied to the top-N recommendation task. ● A desirable metric for recommendation should be robust to incompleteness in the test set. ● Assess robustness by simulating sparsity and popularity bias in the test set (removing at random or removing top popular) and recalculating the metrics. ● Compare rankings of the test sets with Kendall’s correlation
  • 30. On the Robustness and Discriminative Power of IR Metrics for Top-N Recommendation (Valcarce et al) 3 datasets and 21 recommendation algorithms (All Items methodology) ● Precision is very robust to sparsity and popularity biases ● NDCG → high robustness to the sparsity bias and moderate robustness to the popularity bias. ● MRR: performs poorly in RS evaluation. Interesting approach to evaluate the robustness of our metrics for our own datasets
  • 31. Judging Similarity: A user-centric study of related item recommendations (Yao et al.) Evaluate item similarity Evaluate recommendation quality
  • 32. Judging Similarity: A user-centric study of related item recommendations (Yao et al.) ● User-centric evaluation of 6 related item algorithms: random, content- based (tag genome), content-based (user reviews), svd, item2vec, arm ● 700 participants (Movielens users invited by email) ● 2 research questions: ○ Which related item algorithms best match user perceptions of relatedness and recommendation quality? ○ How should related item algorithms be designed to improve the user experience? ● Survey and responses are publicly available
  • 33. Stratified sampling strategy ● 100 source items sampled from the top 2500 most popular items ○ Easier for people to know about the movies ○ 2500 most popular account for 80% of user ratings ● Stratified -> split 2500 into 10 groups, pick 10 random movies from each ● For each algorithm, retrieve top 10 neighbours ● Top 10,000 items considered as target items
  • 34. High correlation between similarity and recom. Quality (0.80 Spearman rank-order correlation) CB approaches outperform CF-based ones in terms of user expectations for similarity and recommendation quality
  • 35. Results and Conclusions of the Study - Content-based approaches item-similarity matches the most with user expectations compared to CF approaches - Perceived recommendation quality is also better. - Users said they want something in between “similar to their interests” and “not obvious” - Based on the user’s feedback the authors suggest that related item recommendations should combine item similarity with other factors such as diversity and serendipity.
  • 36. Interpreting User Inaction (Zhao et al.) Most work focuses on user’s interactions with items. This work focuses on studying the lack of interaction / inaction through a live user survey on MovieLens. Inaction doesn’t always mean negative feedback. E.g. “explore later” type of inaction is a positive user feedback. Research questions: ● What causes inaction? ● Can inaction reason be predicted? ● Can we improve recommender systems using an inaction model?
  • 37. Interpreting User Inaction (Zhao et al.) 7 categories of inaction: ● Not Noticed / Lack of attention (38.6%) ● Not Now (18.2%) ● Already Watched (14.6%) ● Others Better Titles (9.5%) ● Explore Later / Need more info to make a decision (6.9%) ● Would Not Enjoy / Not matching user’s taste (5.8%) ● Already Decided To Watch (5.8%) User’s lack of attention → UI design should try to optimize user attention
  • 38. Interpreting User Inaction (Zhao et al.) Used a multinomial regression model to predict the type / category of user inaction. Main Findings: => Reason for inaction is hard to predict → overall poor classification performance but some categories have high accuracy. => Predicted probability of “Not Now” could be used when to “skip” showing a recommendation and wait for a future session to show it.
  • 40. Mixed Methods (Discovery Weekly @ Spotify) Qualitative Quantitative
  • 41. Mixed Methods (Discovery Weekly @ Spotify) Qualitative: How to do interviews and surveys (best practices) E.g. scales shouldn’t have numbers, should have words Quantitative: How to collect data: attention, interaction, task-success
  • 42. Recsys 2019 See you in Copenhagen