Data-driven static analysis usesleverages largeextensive amounts of codecodebases to infer coding rules and improve the accuracy of the analysis.<ref name="dewes">{{cite web |title=Learning from other's mistakes: Data-driven code analysis. |url=https://www.slideshare.net/japh44/talk-handout-46938511 |website=www.slideshare.net |date=13 April 2015 |language=en}}</ref><ref>{{BetterCite sourcejournal |last=Söderberg |first=Emma |last2=Church |first2=Luke |last3=Höst |first3=Martin needed|date=September2021-06-21 2020|title=Open Data-driven Usability Improvements of Static Code Analysis and its Challenges |url=https://doi.org/10.1145/3463274.3463808 |journal=Proceedings of the 25th International Conference on Evaluation and Assessment in Software Engineering |series=EASE '21 |___location=New York, NY, USA |publisher=Association for Computing Machinery |pages=272–277 |doi=10.1145/3463274.3463808 |isbn=978-1-4503-9053-8}}</ref> For instance, one can use all Java open-source packages available on [[GitHub]] to learn a good analysis strategystrategies. The rule inference can use machine learning techniques.<ref name="OhYang2015">{{cite book|last1=Oh|first1=Hakjoo|title=Proceedings of the 2015 ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications - OOPSLA 2015|last2=Yang|first2=Hongseok|last3=Yi|first3=Kwangkeun|chapter=Learning a strategy for adapting a program analysis via bayesian optimisation|year=2015|pages=572–588|doi=10.1145/2814270.2814309|isbn=9781450336895|s2cid=13940725|url=https://ora.ox.ac.uk/objects/uuid:f656bcfd-ec1b-477c-9185-ff2c7490a207}}</ref> It is also possible to learn from a large amount of past fixes and warnings.<ref name="dewes"/>{{Better source needed|date=September 2020}}
