- author = "Randal S. Olson and Nathan Bartley and Ryan J. Urbanowicz and Jason H. Moore",
- title = "Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science",
- booktitle = "GECCO '16: Proceedings of the 2016 Annual Conference on Genetic and Evolutionary Computation",
- year = "2016",
- editor = "Tobias Friedrich and Frank Neumann and Andrew M. Sutton and Martin Middendorf and Xiaodong Li and Emma Hart and Mengjie Zhang and Youhei Akimoto and Peter A. N. Bosman and Terry Soule and Risto Miikkulainen and Daniele Loiacono and Julian Togelius and Manuel Lopez-Ibanez and Holger Hoos and Julia Handl and Faustino Gomez and Carlos M. Fonseca and Heike Trautmann and Alberto Moraglio and William F. Punch and Krzysztof Krawiec and Zdenek Vasicek and Thomas Jansen and Jim Smith and Simone Ludwig and JJ Merelo and Boris Naujoks and Enrique Alba and Gabriela Ochoa and Simon Poulding and Dirk Sudholt and Timo Koetzing",
- pages = "485--492",
- month = "20-24 " # jul,
- organisation = "SIGEVO",
- address = "Denver, USA",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
- note = "SIGEVO Impact Award 2026",
- keywords = "genetic algorithms, genetic programming, AutoML, TPOT, pipeline optimization, hyperparameter optimization, SBSE, data science, machine learning, Supervised learning by classification, Pareto optimization, Python",
-
URL = "
https://arxiv.org/abs/1603.06212",
- isbn13 = "978-1-4503-4206-3",
-
DOI = "
10.1145/2908812.2908918",
-
code_url = "https://github.com/EpistasisLab/tpot",
- abstract = "As the field of data science continues to grow, there will be an ever-increasing demand for tools that make machine learning accessible to non-experts. we introduce the concept of tree-based pipeline optimization for automating one of the most tedious parts of machine learning--pipeline design. We implement an open source Tree-based Pipeline Optimization Tool (TPOT) in Python and demonstrate its effectiveness on a series of simulated and real-world benchmark data sets. In particular, we show that TPOT can design machine learning pipelines that provide a significant improvement over a basic machine learning analysis while requiring little to no input nor prior knowledge from the user. We also address the tendency for TPOT to design overly complex pipelines by integrating Pareto optimization, which produces compact pipelines without sacrificing classification accuracy. As such, this work represents an important step toward fully automating machine learning pipeline design.",
-
notes = "Also known as cite{OlsonGECCO2016} teapot
Cited by TPOT XGBoost Classification https://docs.uipath.com/ai-fabric/v0/docs/tpot-xgboost-classification
GECCO-2016 A Recombination of the 25th International Conference on Genetic Algorithms (ICGA-2016) and the 21st Annual Genetic Programming Conference (GP-2016)",
