MULTIVERSE: Mining Collective Data Science Knowledge from Code on the Web to Suggest Alternative Analysis Approaches

2021 · KDD

MULTIVERSE: Mining Collective Data Science Knowledge from Code on the Web to Suggest Alternative Analysis Approaches

Mike A. Merrill, Ge Zhang, Tim Althoff

Research illustration for MULTIVERSE: Mining Collective Data Science Knowledge from Code on the Web to Suggest Alternative Analysis Approaches

Data analyses are based on a series of “decision points” including data filtering, feature operationalization and selection, model specification, and parametric assumptions. In this work we mine Kaggle for hundreds of thousands of decision points and train a novel language model to suggest alternative analyses.

BibTeX

@inproceedings{merrill_multiverse_2021,
  title = {MULTIVERSE: Mining Collective Data Science Knowledge from Code on the Web to Suggest Alternative Analysis Approaches},
  author = {Mike A. Merrill and Ge Zhang and Tim Althoff},
  year = {2021},
  booktitle = {KDD},
  doi = {10.1145/3447548.3467455}
}