pith. sign in

arxiv: 2606.18814 · v1 · pith:M6FDAUECnew · submitted 2026-06-17 · 💻 cs.IR

LensKit-Auto

Max Breit , Anass Amezian El Idrissi , Rishikesh Giriraj Kulkarni , Luca Quade This is my paper

Pith reviewed 2026-06-26 19:30 UTC · model grok-4.3

classification 💻 cs.IR
keywords recommender systemsautomated machine learninghyperparameter optimizationLensKitTree Parzen Estimatormeta-learningAutoRecSys
0
0 comments X

The pith

LensKit-Auto now runs on current LensKit and adds Tree Parzen Estimator for automatic recommender tuning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper updates LensKit-Auto, a black-box tool that takes a dataset and returns the best recommender algorithm plus hyperparameters. It restores compatibility with the latest LensKit release and adds Tree Parzen Estimator as a second optimization method. New capabilities include algorithm reuse, optimization visualization, refreshed documentation, and an adapted meta-learning pipeline to build supporting datasets. These steps aim to let users without tuning expertise obtain workable recommenders for applications such as streaming or marketplaces.

Core claim

LensKit-Auto is extended to function with the new LensKit version, incorporates the Tree Parzen Estimator alongside prior optimizers, supports reuse of the selected algorithm, supplies process visualizations, updates its documentation, and adapts an existing meta-learning framework to produce suitable meta-datasets, thereby restoring compatibility and increasing accessibility for non-expert users.

What carries the argument

LensKit-Auto black-box interface that ingests a dataset and outputs an algorithm-hyperparameter pair, now extended with version compatibility and Tree Parzen Estimator search.

If this is right

  • Users can run the tool on current LensKit installations without version conflicts.
  • Non-experts obtain algorithm recommendations through the same black-box call as before.
  • Tree Parzen Estimator supplies an alternative search strategy that may converge differently on some datasets.
  • Visualization output lets users inspect how the optimizer explored the space.
  • The meta-dataset preparation step readies the framework for future meta-learning additions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Wider adoption of automated tuning could reduce manual trial-and-error in production recommender deployments.
  • Meta-learning integration might shorten search time on new datasets by transferring knowledge from prior runs.
  • The reuse feature enables direct deployment of the discovered model without extra steps.
  • Updated documentation lowers the barrier for researchers adding new algorithms to the search space.

Load-bearing premise

The code changes for LensKit compatibility and the Tree Parzen Estimator integrate cleanly and produce usable results on real recommender datasets.

What would settle it

Install the updated LensKit-Auto, run it on the MovieLens dataset, and verify that it completes the search without errors and returns a model whose performance can be measured on held-out data.

Figures

Figures reproduced from arXiv: 2606.18814 by Anass Amezian El Idrissi, Luca Quade, Max Breit, Rishikesh Giriraj Kulkarni.

Figure 1
Figure 1. Figure 1: High-level workflow of LensKit-Auto. LensKit framework with functionality for automated recommender system ex￾perimentation. In particular, it automates algorithm selection, hyperparameter optimization, and post-hoc model ensembling for both rating-prediction and top-N recommendation scenarios [60]. In this way, LensKit-Auto reduces the manual effort required to configure, compare, and evaluate recommender… view at source ↗
Figure 2
Figure 2. Figure 2: Some examples of the DeepCAVE output 22 [PITH_FULL_IMAGE:figures/full_fig_p022_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of the LensKit-Auto documentation before and after the [PITH_FULL_IMAGE:figures/full_fig_p028_3.png] view at source ↗
read the original abstract

Recommender systems have a wide area of application, e.g. in fields like video streaming, social media, or digital marketplaces. But, for a recommender-system, finding the right algorithm with the right hyperparameters is a reoccurring challenge. There is no one-fits-all solution, since the performance of one algorithm can vary immensely on different data sets. Due to the challenges of finding the right algorithm and the broad use of recommender-systems, it is of interest to create an Automated Recommender System (AutoRecSys) that takes on the task of finding the right algorithm-hyperparameter-combination for a given data set. In this work, we present the enhancement of LensKit-Auto, a framework introduced by Vente et al., that solves exactly this task of finding a fitting algorithm-hyperparameter-combination. LensKit-Auto's biggest strength lies in its ease of use, where it operates as a black-box, into which the user can feed their data set and receive the information of which algorithm and hyperparameters work best on this data set. In this work, we bring LensKit-Auto up to date, so that it works with the new version of its underlying framework, LensKit. We also implement further functionalities, such as the Tree Parzen Estimator as an additional optimization method, the ability to reuse the found algorithm, updated documentation, and the ability to visualize the optimization process. We also adapt an existing meta-learning framework to generate a suitable meta-dataset for LensKit-Auto, which could enable the integration of meta-learning into LensKit-Auto in the future. The presented changes bring LensKit-Auto up to date and enhance its usability, so that even non-experts in the field can find the right algorithm for their use case.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript describes updates to LensKit-Auto, an automated recommender system (AutoRecSys) framework originally introduced by Vente et al. The updates include compatibility with the new LensKit version, addition of the Tree Parzen Estimator as an optimization method, functionality to reuse the selected algorithm, visualization of the optimization process, updated documentation, and adaptation of an existing meta-learning framework to generate a meta-dataset for potential future integration. The central claim is that these changes bring the tool up to date and enhance its usability as a black-box system, enabling even non-experts to identify suitable algorithms and hyperparameters for a given dataset.

Significance. If the described updates function correctly and are validated, the work could provide a practical contribution to the AutoRecSys literature by improving accessibility of an existing framework in the recommender systems community. The addition of TPE and visualization features addresses common usability gaps in hyperparameter optimization tools. However, the absence of any empirical validation means the significance remains potential rather than demonstrated; the manuscript does not establish that the changes preserve or improve performance on real data.

major comments (1)
  1. [Abstract] Abstract and manuscript body: The central usability claim for non-experts requires that the compatibility updates, TPE integration, reuse functionality, and visualization all operate without errors and produce usable results. However, the text provides no execution traces, error rates, runtime measurements, output quality checks, or any evaluation on datasets to support this. This is load-bearing because the claim rests entirely on the implementation description without evidence.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and constructive feedback on our manuscript describing updates to LensKit-Auto. We provide a point-by-point response to the major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract and manuscript body: The central usability claim for non-experts requires that the compatibility updates, TPE integration, reuse functionality, and visualization all operate without errors and produce usable results. However, the text provides no execution traces, error rates, runtime measurements, output quality checks, or any evaluation on datasets to support this. This is load-bearing because the claim rests entirely on the implementation description without evidence.

    Authors: The manuscript is intended as a description of software updates to an existing framework, building upon the original LensKit-Auto work which included empirical evaluations. Our contributions focus on compatibility, new optimization methods (TPE is a standard approach), reuse functionality, visualization, and documentation improvements. These are standard software engineering practices, and the open-source nature of the project allows users to inspect and test the implementation directly. We do not claim new performance results but rather enhanced accessibility. Therefore, we believe the implementation description is sufficient to support the usability claims without additional empirical sections in this update paper. revision: no

Circularity Check

0 steps flagged

No derivations or predictions present; software update paper is self-contained

full rationale

The manuscript is a description of software enhancements to LensKit-Auto (compatibility with updated LensKit, addition of Tree Parzen Estimator, reuse functionality, visualization, and meta-dataset adaptation). No equations, predictions, fitted parameters, or derivation chains appear anywhere in the text. The single citation to Vente et al. is historical context for the original framework and does not serve as a load-bearing premise for any result. All claims reduce to statements of what was implemented, with no reduction to self-citation or input data by construction. This is the expected non-finding for an engineering update paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a software engineering contribution with no mathematical claims, free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5863 in / 1033 out tokens · 29737 ms · 2026-06-26T19:30:38.585588+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

73 extracted references · 21 canonical work pages

  1. [1]

    Accessed: 31.03.2026

    Amazon2014 datasets.https://grouplens.org/datasets/movielens/. Accessed: 31.03.2026

    2026

  2. [2]

    Autogluon documentation.https://auto.gluon.ai/stable/index. html. Accessed: 31.03.2026

    2026

  3. [3]

    Accessed: 31.03.2026

    Homepage of the omni cluster of the university of siegen.https:// cluster.uni-siegen.de/. Accessed: 31.03.2026

    2026

  4. [4]

    Accessed: 30.03.2026

    Deepcave documentation.https://automl.github.io/DeepCAVE/main/ index.html. Accessed: 30.03.2026

    2026

  5. [5]

    Ac- cessed: 31.03.2026

    Lenskit documentation.https://lenskit.org/stable/index.html. Ac- cessed: 31.03.2026

    2026

  6. [6]

    Accessed: 31.03.2026

    Meta-learning framework git repository.https://github.com/ ISG-Siegen/RecSys-Algorithm-Selection-Ranking-Implicit-LBR, . Accessed: 31.03.2026

    2026

  7. [7]

    Accessed: 31.03.2026

    Git repository of the adapted meta-learning framework.https://github.com/LucaQuade/ RecSys-Algorithm-Selection-Ranking-Implicit-LBR, . Accessed: 31.03.2026

    2026

  8. [8]

    Accessed: 31.03.2026

    Movielens datasets.https://cseweb.ucsd.edu/ ~jmcauley/datasets/ amazon/links.html. Accessed: 31.03.2026

    2026

  9. [9]

    Accessed: 31.03.2026

    Recbole documentation.https://recbole.io/docs/, . Accessed: 31.03.2026

    2026

  10. [10]

    Accessed: 31.03.2026

    Recpack documentation.https://recpack.froomle.ai/, . Accessed: 31.03.2026

    2026

  11. [11]

    Ac- cessed: 31.03.2026

    Slurm documentation.https://slurm.schedmd.com/overview.html. Ac- cessed: 31.03.2026

    2026

  12. [12]

    Adomavicius and A

    G. Adomavicius and A. Tuzhilin. Toward the next generation of recom- mender systems: a survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 17(6):734–749,

  13. [13]

    doi: 10.1109/TKDE.2005.99

    work page doi:10.1109/tkde.2005.99 2005

  14. [14]

    Aggarwal.Recommender Systems: The Textbook

    Charu C. Aggarwal.Recommender Systems: The Textbook. Springer, 2016. doi: 10.1007/978-3-319-29659-3

    work page doi:10.1007/978-3-319-29659-3 2016

  15. [15]

    Xavier Amatriain and Justin Basilico.Recommender Systems in Industry: A Netflix Case Study, pages 385–419. 01 2015. ISBN 978-1-4899-7636-9. doi: 10.1007/978-1-4899-7637-6 11. 38

    work page doi:10.1007/978-1-4899-7637-6 2015

  16. [16]

    Auto-surprise: An automated recommender-system (autorecsys) library with tree of parzens estimator (tpe) optimization

    Rohan Anand and Joeran Beel. Auto-surprise: An automated recommender-system (autorecsys) library with tree of parzens estimator (tpe) optimization. InProceedings of the 14th ACM Conference on Rec- ommender Systems, RecSys ’20, page 585–587, New York, NY, USA, 2020. Association for Computing Machinery. ISBN 9781450375832. doi: 10.1145/ 3383313.3411467. URL...

    work page doi:10.1145/3383313.3411467 2020

  17. [17]

    Auto-surprise: An automated recommender-system (autorecsys) library with tree of parzens estimator (tpe) optimization

    Rohan Anand and Joeran Beel. Auto-surprise: An automated recommender-system (autorecsys) library with tree of parzens estimator (tpe) optimization. InProceedings of the 14th ACM Conference on Recom- mender Systems, pages 585–587, 2020

    2020

  18. [18]

    Green recommender systems: Optimizing dataset size for energy-efficient algorithm perfor- mance

    Ardalan Arabzadeh, Tobias Vente, and Joeran Beel. Green recommender systems: Optimizing dataset size for energy-efficient algorithm perfor- mance. InInternational Workshop on Recommender Systems for Sustain- ability and Social Good, pages 73–82. Springer, 2024

    2024

  19. [19]

    4.3 best-practices for offline evaluations of recommender systems.Evaluation Perspectives of Recommender Systems: Driving Re- search and Education, 55(8):110, 2022

    Joeran Beel, Dietmar Jannach, Alan Said, Guy Shani, Tobias Vente, and Lukas Wegmeth. 4.3 best-practices for offline evaluations of recommender systems.Evaluation Perspectives of Recommender Systems: Driving Re- search and Education, 55(8):110, 2022

    2022

  20. [20]

    Random search for hyper-parameter optimization.Journal of Machine Learning Research, 13(10):281–305, 2012

    James Bergstra and Yoshua Bengio. Random search for hyper-parameter optimization.Journal of Machine Learning Research, 13(10):281–305, 2012. URLhttp://jmlr.org/papers/v13/bergstra12a.html

    2012

  21. [21]

    Random search for hyper-parameter optimization.Journal of machine learning research, 13(2), 2012

    James Bergstra and Yoshua Bengio. Random search for hyper-parameter optimization.Journal of machine learning research, 13(2), 2012

    2012

  22. [22]

    Algo- rithms for hyper-parameter optimization

    James Bergstra, R´ emi Bardenet, Yoshua Bengio, and Bal´ azs K´ egl. Algo- rithms for hyper-parameter optimization. InProceedings of the 25th Inter- national Conference on Neural Information Processing Systems, NIPS’11, page 2546–2554, Red Hook, NY, USA, 2011. Curran Associates Inc. ISBN 9781618395993

    2011

  23. [23]

    Progress in recommender sys- tems research: Crisis? what crisis?AI Magazine, 42(3):43–54,

    Paolo Cremonesi and Dietmar Jannach. Progress in recommender sys- tems research: Crisis? what crisis?AI Magazine, 42(3):43–54,

  24. [24]

    URLhttps:// onlinelibrary.wiley.com/doi/abs/10.1609/aimag.v42i3.18145

    doi: https://doi.org/10.1609/aimag.v42i3.18145. URLhttps:// onlinelibrary.wiley.com/doi/abs/10.1609/aimag.v42i3.18145

    work page doi:10.1609/aimag.v42i3.18145

  25. [25]

    de Carvalho

    Tiago Cunha, Carlos Soares, and Andr´ e C.P.L.F. de Carvalho. Met- alearning and recommender systems: A literature review and empirical study on the algorithm selection problem for collaborative filtering.In- formation Sciences, 423:128–144, 2018. ISSN 0020-0255. doi: https: //doi.org/10.1016/j.ins.2017.09.050. URLhttps://www.sciencedirect. com/science/ar...

    work page doi:10.1016/j.ins.2017.09.050 2018

  26. [26]

    Item-based top-n recommenda- tion algorithms.ACM Transactions on Information Systems (TOIS), 22 (1):143–177, 2004

    Mukund Deshpande and George Karypis. Item-based top-n recommenda- tion algorithms.ACM Transactions on Information Systems (TOIS), 22 (1):143–177, 2004. 39

    2004

  27. [27]

    Lenskit for python: Next-generation software for recommender systems experiments

    Michael D Ekstrand. Lenskit for python: Next-generation software for recommender systems experiments. InProceedings of the 29th ACM inter- national conference on information & knowledge management, pages 2999– 3006, 2020

    2020

  28. [28]

    Ekstrand, John T

    Michael D. Ekstrand, John T. Riedl, and Joseph A. Konstan. Collaborative filtering recommender systems.Found. Trends Hum.-Comput. Interact., 4 (2):81–173, February 2011. ISSN 1551-3955. doi: 10.1561/1100000009. URLhttps://doi.org/10.1561/1100000009

    work page doi:10.1561/1100000009 2011

  29. [29]

    Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alex Smola

    Nick Erickson, Jonas W. Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alex Smola. Autogluon-tabular: Robust and accurate automl for structured data.ArXiv, abs/2003.06505, 2020. URLhttps: //api.semanticscholar.org/CorpusID:212725762

    Pith/arXiv arXiv 2003

  30. [30]

    Efficient and robust au- tomated machine learning

    Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Sprin- genberg, Manuel Blum, and Frank Hutter. Efficient and robust au- tomated machine learning. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors,Advances in Neural In- formation Processing Systems, volume 28. Curran Associates, Inc.,

  31. [31]

    URLhttps://proceedings.neurips.cc/paper_files/paper/ 2015/file/11d0e6287202fced83f79975ec59a3a6-Paper.pdf

    2015

  32. [32]

    A survey of accuracy evaluation met- rics of recommendation tasks.Journal of Machine Learning Research, 10 (12), 2009

    Asela Gunawardana and Guy Shani. A survey of accuracy evaluation met- rics of recommendation tasks.Journal of Machine Learning Research, 10 (12), 2009

    2009

  33. [33]

    Evaluating recom- mender systems

    Asela Gunawardana, Guy Shani, and Sivan Yogev. Evaluating recom- mender systems. InRecommender systems handbook, pages 547–601. Springer, 2012

    2012

  34. [34]

    Evaluating collaborative filtering recommender systems.ACM Transactions on Information Systems (TOIS), 22(1):5–53, 2004

    Jonathan L Herlocker, Joseph A Konstan, Loren G Terveen, and John T Riedl. Evaluating collaborative filtering recommender systems.ACM Transactions on Information Systems (TOIS), 22(1):5–53, 2004

    2004

  35. [36]

    Collaborative filtering for implicit feedback datasets

    Yifan Hu, Yehuda Koren, and Chris Volinsky. Collaborative filtering for implicit feedback datasets. InProceedings of the 2008 Eighth IEEE Inter- national Conference on Data Mining, ICDM ’08, page 263–272, USA, 2008. IEEE Computer Society. ISBN 9780769535029. doi: 10.1109/ICDM.2008

    work page doi:10.1109/icdm.2008 2008

  36. [37]

    URLhttps://doi.org/10.1109/ICDM.2008.22

    work page doi:10.1109/icdm.2008.22 2008

  37. [38]

    Collaborative filtering for implicit feedback datasets

    Yifan Hu, Yehuda Koren, and Chris Volinsky. Collaborative filtering for implicit feedback datasets. In2008 Eighth IEEE international conference on data mining, pages 263–272. Ieee, 2008. 40

    2008

  38. [39]

    Hoos, and Kevin Leyton-Brown

    Frank Hutter, Holger H. Hoos, and Kevin Leyton-Brown. Sequential model- based optimization for general algorithm configuration. InProceedings of the 5th International Conference on Learning and Intelligent Optimization, LION’05, page 507–523, Berlin, Heidelberg, 2011. Springer-Verlag. ISBN 9783642255656. doi: 10.1007/978-3-642-25566-3 40. URLhttps://doi. ...

    work page doi:10.1007/978-3-642-25566-3 2011

  39. [40]

    Springer, 2019

    Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren.Automated Machine Learning: Methods, Systems, Challenges. Springer, 2019. doi: 10.1007/ 978-3-030-05318-5

    2019

  40. [41]

    Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren.Automated Machine Learning - Methods, Systems, Challenges. 01 2019. ISBN 978-3-030-05317-

    2019

  41. [42]

    doi: 10.1007/978-3-030-05318-5

    work page doi:10.1007/978-3-030-05318-5

  42. [43]

    Springer, 2019

    Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren.Automated machine learning: methods, systems, challenges. Springer, 2019

    2019

  43. [44]

    Cumulated gain-based evaluation of ir techniques.ACM Transactions on Information Systems (TOIS), 20 (4):422–446, 2002

    Kalervo J¨ arvelin and Jaana Kek¨ al¨ ainen. Cumulated gain-based evaluation of ir techniques.ACM Transactions on Information Systems (TOIS), 20 (4):422–446, 2002

    2002

  44. [46]

    Matrix factorization tech- niques for recommender systems.Computer, 42(8):30–37, 2009

    Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization tech- niques for recommender systems.Computer, 42(8):30–37, 2009

    2009

  45. [47]

    Matrix Factorization Techniques for Recommender Systems.Computer, 42(8):30–37, August 2009

    Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization tech- niques for recommender systems.Computer, 42(8):30–37, August 2009. ISSN 0018-9162. doi: 10.1109/MC.2009.263. URLhttps://doi.org/10. 1109/MC.2009.263

    work page doi:10.1109/mc.2009.263 2009

  46. [48]

    Recpack: An(other) experimentation toolkit for top-n recommendation using implicit feedback data

    Lien Michiels, Robin Verachtert, and Bart Goethals. Recpack: An(other) experimentation toolkit for top-n recommendation using implicit feedback data. InProceedings of the 16th ACM Conference on Recommender Sys- tems, RecSys ’22, page 648–651, New York, NY, USA, 2022. Association for Computing Machinery. ISBN 9781450392785. doi: 10.1145/3523227. 3551472. U...

    work page doi:10.1145/3523227 2022

  47. [49]

    On estimation of a probability density function and mode.The Annals of Mathematical Statistics, 33(3):1065–1076, 1962

    Emanuel Parzen. On estimation of a probability density function and mode.The Annals of Mathematical Statistics, 33(3):1065–1076, 1962. ISSN 00034851. URLhttp://www.jstor.org/stable/2237880

    arXiv 1962

  48. [50]

    Open- ing the black box: Automated software analysis for algorithm selection

    Damir Pulatov, Marie Anastacio, Lars Kotthoff, and Holger Hoos. Open- ing the black box: Automated software analysis for algorithm selection. In Isabelle Guyon, Marius Lindauer, Mihaela van der Schaar, Frank Hut- ter, and Roman Garnett, editors,Proceedings of the First International 41 Conference on Automated Machine Learning, volume 188 ofProceedings of ...

    2022

  49. [51]

    Bpr: Bayesian personalized ranking from implicit feedback

    Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt- Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI ’09, page 452–461, Arlington, Virginia, USA, 2009. AUAI Press. ISBN 9780974903958

    2009

  50. [52]

    Kantor, ed- itors.Recommender Systems Handbook

    Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul B. Kantor, ed- itors.Recommender Systems Handbook. Springer, 2011. doi: 10.1007/ 978-0-387-85820-3

    2011

  51. [53]

    2001 , isbn =

    Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. Item- based collaborative filtering recommendation algorithms. InProceedings of the 10th International Conference on World Wide Web, WWW ’01, page 285–295, New York, NY, USA, 2001. Association for Computing Machinery. ISBN 1581133480. doi: 10.1145/371920.372071. URLhttps://doi.org/ 10.1145/371...

    work page doi:10.1145/371920.372071 2001

  52. [54]

    Deepcave: An interactive analysis tool for automated machine learning, 2022

    Ren´ e Sass, Eddie Bergman, Andr´ e Biedenkapp, Frank Hutter, and Marius Lindauer. Deepcave: An interactive analysis tool for automated machine learning, 2022. URLhttps://arxiv.org/abs/2206.03493

    arXiv 2022

  53. [55]

    Adams, and Nando de Freitas

    Bobak Shahriari, Kevin Swersky, Ziyu Wang,{Ryan P.}Adams, and Nando {De Freitas}. Taking the human out of the loop: A review of bayesian optimization.Proceedings of the IEEE, 104(1):148–175, January 2016. ISSN 0018-9219. doi: 10.1109/JPROC.2015.2494218. Publisher Copyright:© 1963-2012 IEEE

    work page doi:10.1109/jproc.2015.2494218 2016

  54. [56]

    Everyone’s a winner! on hyper- parameter tuning of recommendation models

    Faisal Shehzad and Dietmar Jannach. Everyone’s a winner! on hyper- parameter tuning of recommendation models. InProceedings of the 17th ACM Conference on Recommender Systems, RecSys ’23, page 652–657, New York, NY, USA, 2023. Association for Computing Machinery. ISBN 9798400702419. doi: 10.1145/3604915.3609488. URLhttps://doi.org/ 10.1145/3604915.3609488

    work page doi:10.1145/3604915.3609488 2023

  55. [57]

    Jasper Snoek, Hugo Larochelle, and Ryan P. Adams. Practical bayesian optimization of machine learning algorithms, 2012. URLhttps://arxiv. org/abs/1206.2944

    Pith/arXiv arXiv 2012

  56. [58]

    Practical bayesian op- timization of machine learning algorithms.Advances in neural information processing systems, 25, 2012

    Jasper Snoek, Hugo Larochelle, and Ryan P Adams. Practical bayesian op- timization of machine learning algorithms.Advances in neural information processing systems, 25, 2012

    2012

  57. [59]

    librec-auto: A tool for 42 recommender systems experimentation

    Nasim Sonboli, Masoud Mansoury, Ziyue Guo, Shreyas Kadekodi, Weiwen Liu, Zijun Liu, Andrew Schwartz, and Robin Burke. librec-auto: A tool for 42 recommender systems experimentation. InProceedings of the 30th ACM In- ternational Conference on Information & Knowledge Management, CIKM ’21, page 4584–4593, New York, NY, USA, 2021. Association for Comput- ing ...

    work page doi:10.1145/3459637.3482006 2021

  58. [60]

    Khoshgoftaar

    Xiaoyuan Su and Taghi M. Khoshgoftaar. A survey of collaborative filtering techniques.Advances in Artificial Intelligence, 2009(1):421425. doi: https: //doi.org/10.1155/2009/421425. URLhttps://onlinelibrary.wiley. com/doi/abs/10.1155/2009/421425

    work page doi:10.1155/2009/421425 2009

  59. [61]

    Auto-weka: Combined selection and hyperparameter optimization of classi- fication algorithms

    Chris Thornton, Frank Hutter, Holger H Hoos, and Kevin Leyton-Brown. Auto-weka: Combined selection and hyperparameter optimization of classi- fication algorithms. InProceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 847–855, 2013

    2013

  60. [62]

    Evaluating group recommender systems

    Christoph Trattner, Alan Said, Ludovico Boratto, and Alexander Felfernig. Evaluating group recommender systems. InGroup recommender systems: an introduction, pages 63–75. Springer, 2023

    2023

  61. [63]

    Meta-learning

    Joaquin Vanschoren. Meta-learning. pages 39–68

  62. [64]

    Advancing automation of design decisions in recommender system pipelines

    Tobias Vente. Advancing automation of design decisions in recommender system pipelines. InProceedings of the 17th ACM Conference on Recom- mender Systems, pages 1355–1360, 2023

    2023

  63. [65]

    Introducing lenskit-auto, an experimental automated recommender system (autorecsys) toolkit

    Tobias Vente, Michael Ekstrand, and Joeran Beel. Introducing lenskit-auto, an experimental automated recommender system (autorecsys) toolkit. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1212–1216, 2023

    2023

  64. [66]

    Greedy ensemble selection for top-n recommendations

    Tobias Vente, Zainil Mehta, Lukas Wegmeth, and Joeran Beel. Greedy ensemble selection for top-n recommendations. InRobustRecSys@ RecSys, pages 12–16, 2024

    2024

  65. [67]

    From clicks to carbon: the environmental toll of recommender systems

    Tobias Vente, Lukas Wegmeth, Alan Said, and Joeran Beel. From clicks to carbon: the environmental toll of recommender systems. InProceedings of the 18th ACM Conference on Recommender Systems, pages 580–590, 2024

    2024

  66. [68]

    Aps explorer: Navigating algorithm performance spaces for informed dataset selection

    Tobias Vente, Michael Heep, Abdullah Abbas, Theodor Sperle, Joeran Beel, and Bart Goethals. Aps explorer: Navigating algorithm performance spaces for informed dataset selection. InProceedings of the Nineteenth ACM Con- ference on Recommender Systems, pages 1322–1324, 2025

    2025

  67. [69]

    The potential of automl for recommender systems

    Tobias Vente, Lukas Wegmeth, and Joeran Beel. The potential of automl for recommender systems. InAdjunct Proceedings of the 33rd ACM Con- ference on User Modeling, Adaptation and Personalization, pages 371–378, 2025. 43

    2025

  68. [70]

    What to compare? towards un- derstanding user sessions on price comparison platforms

    Ahmadou Wagne and Julia Neidhardt. What to compare? towards un- derstanding user sessions on price comparison platforms. InProceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, page 1158–1162, New York, NY, USA, 2024. Association for Computing Ma- chinery. ISBN 9798400705052. doi: 10.1145/3640457.3691717. URL https://doi.org/10.1145/3...

    work page doi:10.1145/3640457.3691717 2024

  69. [71]

    What to compare? towards un- derstanding user sessions on price comparison platforms

    Lukas Wegmeth, Tobias Vente, and Joeran Beel. Recommender systems algorithm selection for ranking prediction on implicit feedback datasets. In Proceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, page 1163–1167, New York, NY, USA, 2024. Association for Computing Machinery. ISBN 9798400705052. doi: 10.1145/3640457.3691718. URL https:/...

    work page doi:10.1145/3640457.3691718 2024

  70. [72]

    Recommender systems algorithm selection for ranking prediction on implicit feedback datasets

    Lukas Wegmeth, Tobias Vente, and Joeran Beel. Recommender systems algorithm selection for ranking prediction on implicit feedback datasets. In Proceedings of the 18th ACM Conference on Recommender Systems, pages 1163–1167, 2024

    2024

  71. [73]

    Green recom- mender systems: Understanding and minimizing the carbon footprint of ai-powered personalization.ACM Transactions on Recommender Systems, 2025

    Lukas Wegmeth, Tobias Vente, Alan Said, and Joeran Beel. Green recom- mender systems: Understanding and minimizing the carbon footprint of ai-powered personalization.ACM Transactions on Recommender Systems, 2025

    2025

  72. [74]

    Recbole: Towards a unified, compre- hensive and efficient framework for recommendation algorithms

    Wayne Xin Zhao, Shanlei Mu, Yupeng Hou, Zihan Lin, Yushuo Chen, Xingyu Pan, Kaiyuan Li, Yujie Lu, Hui Wang, Changxin Tian, Yingqian Min, Zhichao Feng, Xinyan Fan, Xu Chen, Pengfei Wang, Wendi Ji, Yaliang Li, Xiaoling Wang, and Ji-Rong Wen. Recbole: Towards a unified, compre- hensive and efficient framework for recommendation algorithms. InProceed- ings of...

    work page doi:10.1145/3459637.3482016 2021

  73. [75]

    Automl for deep recommender systems: A survey.ACM Transactions on Information Systems, 41(4):1–38, 2023

    Ruiqi Zheng, Liang Qu, Bin Cui, Yuhui Shi, and Hongzhi Yin. Automl for deep recommender systems: A survey.ACM Transactions on Information Systems, 41(4):1–38, 2023. 44

    2023