Rethinking The Recommender Research Ecosystem: Reproducibility, Openness, and LensKit
2011. Rethinking The Recommender Research Ecosystem: Reproducibility, Openness, and LensKit. In Proceedings of the Fifth ACM Conference on Recommender Systems (RecSys '11). ACM, 133–140. DOI:10.1145/2043932.2043958. Acceptance rate: 27% (20% for oral presentation, which this received). Cited 72 times (133 est.)., , , and .
The LensKit software itself is available from its project site.
Recommender systems research is being slowed by the difficulty of replicating and comparing research results. Published research uses various experimental methodologies and metrics that are difficult to compare. It also often fails to sufficiently document the details of proposed algorithms or the evaluations employed. Researchers waste time reimplementing well-known algorithms, and the new implementations may miss key details from the original algorithm or its subsequent refinements. When proposing new algorithms, researchers should compare them against finely-tuned implementations of the leading prior algorithms using state-of-the-art evaluation methodologies. With few exceptions, published algorithmic improvements in our field should be accompanied by working code in a standard framework, including test harnesses to reproduce the described results. To that end, we present the design and freely distributable source code of LensKit, a flexible platform for reproducible recommender systems research. LensKit provides carefully tuned implementations of the leading collaborative filtering algorithms, APIs for common recommender system use cases, and an evaluation framework for performing reproducible offline evaluations of algorithms. We demonstrate the utility of LensKit by replicating and extending a set of prior comparative studies of recommender algorithms --- showing limitations in some of the original results --- and by investigating a question recently raised by a leader in the recommender systems community on problems with error-based prediction evaluation.
- Version of record in the ACM Digital Library (free PDF via ACM Author-izer)
- Author version PDF
- Blog post on user-user similarity functions, why our results make theoretical sense, and the history of the sub-optimal design decisions.
- Blog post on item-item similarity functions and the theoretical underpinnings of our empirical results.
- LensKit project
- Experiment and analysis scripts (zip file version)
- Chapters 3 and 5 of my thesis contains an expanded and updated description of LensKit and some of the experiments in this paper.