- author = "Randal S. Olson and Jason H. Moore",
- title = "{TPOT}: A Tree-based Pipeline Optimization Tool for Automating Data Science",
- booktitle = "AutoML 2016 workshop",
- year = "2016",
- editor = "Frank Hutter and Lars Kotthoff and Joaquin Vanschoren",
- address = "New York City, USA",
- month = jun # " 24",
- note = "Collocated with ICML",
- keywords = "genetic algorithms, genetic programming, TPOT, Python, automated machine learning, hyperparameter optimization, pipeline optimization, Pareto optimization, data science",
-
URL = "
https://docs.google.com/viewer?a=v&pid=sites&srcid=ZGVmYXVsdGRvbWFpbnxhdXRvbWwyMDE2fGd4OmFmYjMyNWU2NWI1YTBmZg",
-
code_url = "https://github.com/EpistasisLab/tpot",
- size = "8 pages",
- abstract = "As data science becomes more mainstream, there will be an ever-growing demand for data science tools that are more accessible, flexible, and scalable. In response to this demand, automated machine learning (AutoML) researchers have begun building systems that automate the process of designing and optimizing machine learning pipelines. In this paper we present TPOT, an open source genetic programming-based AutoML system that optimizes a series of feature preprocessors and machine learning models with the goal of maximizing classification accuracy on a supervised classification task. We benchmark TPOT on a series of 150 supervised classification tasks and find that it significantly outperforms a basic machine learning analysis in 22 of them, while experiencing minimal degradation in accuracy on 5 of the benchmarks, all without any domain knowledge nor human input. As such, GP-based AutoML systems show considerable promise in the AutoML domain.",
-
notes = "Replaced by
\cite{Olson:2019:autoML}
https://sites.google.com/site/automl2016/
https://github.com/EpistasisLab/tpot",
