% IMPORTANT: The following is UTF-8 encoded. This means that in the presence % of non-ASCII characters, it will not work with BibTeX 0.99 or older. % Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or % “biber”. @ARTICLE{Sasse:1018240, author = {Sasse, Leonard and Nicolaisen-Sobesky, Eliana and Dukart, Jürgen and Eickhoff, Simon B. and Götz, Michael and Hamdan, Sami and Komeyer, Vera and Kulkarni, Abhijit and Lahnakoski, Juha and Love, Bradley C. and Raimondo, Federico and Patil, Kaustubh R.}, title = {{O}n {L}eakage in {M}achine {L}earning {P}ipelines}, publisher = {arXiv}, reportid = {FZJ-2023-04636}, year = {2023}, abstract = {Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity stems from the promise of sample-level prediction with applications across a variety of fields from physics and marketing to healthcare. However, if not properly implemented and evaluated, ML pipelines may contain leakage typically resulting in overoptimistic performance estimates and failure to generalize to new data. This can have severe negative financial and societal implications. Our aim is to expand understanding associated with causes leading to leakage when designing, implementing, and evaluating ML pipelines. Illustrated by concrete examples, we provide a comprehensive overview and discussion of various types of leakage that may arise in ML pipelines.}, keywords = {Machine Learning (cs.LG) (Other) / Artificial Intelligence (cs.AI) (Other) / FOS: Computer and information sciences (Other)}, cin = {INM-7}, cid = {I:(DE-Juel1)INM-7-20090406}, pnm = {5254 - Neuroscientific Data Analytics and AI (POF4-525)}, pid = {G:(DE-HGF)POF4-5254}, typ = {PUB:(DE-HGF)25}, doi = {10.48550/ARXIV.2311.04179}, url = {https://juser.fz-juelich.de/record/1018240}, }