Fast and accurate causal inference from time series data

Yuxiao Huang, Samantha Kleinberg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

Causal inference from time series data is a key problem in many fields, and new massive datasets have made it more critical than ever. Accuracy and speed are primary factors in choosing a causal inference method, as they determine which hypotheses can be tested, how much of the search space can be explored, and what decisions can be made based on the results. In this work we present a new causal inference framework that 1) improves the accuracy of inferences in time series data, and 2) enables faster computation of causal significance. Instead of evaluating relationships individually, using only features of the data, this approach exploits the connections between each causal relationship's relative levels of significance.We provide theoretical guarantees of correctness and speed (with an order of magnitude improvement) and empirically demonstrate improved FDR, FNR, and computation speed relative to leading approaches.

Original languageEnglish
Title of host publicationProceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015
EditorsWilliam Eberle, Ingrid Russell
Pages49-54
Number of pages6
ISBN (Electronic)9781577357308
StatePublished - 2015
Event28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015 - Hollywood, United States
Duration: 18 May 201520 May 2015

Publication series

NameProceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015

Conference

Conference28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015
Country/TerritoryUnited States
CityHollywood
Period18/05/1520/05/15

Fingerprint

Dive into the research topics of 'Fast and accurate causal inference from time series data'. Together they form a unique fingerprint.

Cite this