Interpreting and clustering outliers with sapling random forests

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00219640" target="_blank" >RIV/68407700:21230/14:00219640 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/67985807:_____/14:00432410 RIV/68407700:21230/14:00219641 RIV/68407700:21240/14:00219641 RIV/68407700:21240/14:00219640

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Interpreting and clustering outliers with sapling random forests

Popis výsledku v původním jazyce

The main objective of outlier detection is find- ing samples considerably deviating from the majority. Such outliers, often referred to as anomalies, are nowadays more and more important, because they help to uncover in- teresting events within data. Consequently, a considerable amount of statistical and data mining techniques to iden- tify anomalies was proposed in the last few years, but only a few works at least mentioned why some sample was la- belled as an anomaly. Therefore, we propose a method based on specifically trained decision trees, called sapling random forest. Our method is able to interpret the output of arbitrary anomaly detector. The explanation is given as a subset of features, in which the sample is most deviating, or as con- junctions of atomic conditions, which can be viewed as antecedents of logical rules easily understandable by hu- mans. To simplify the investigation of suspicious samples even more, we propose two methods of clustering anoma- lies into groups. Such clusters can be investigated at once saving time and human efforts. The feasibility of our ap- proach is demonstrated on several synthetic and one real world datasets.

Název v anglickém jazyce

Interpreting and clustering outliers with sapling random forests

Popis výsledku anglicky

The main objective of outlier detection is find- ing samples considerably deviating from the majority. Such outliers, often referred to as anomalies, are nowadays more and more important, because they help to uncover in- teresting events within data. Consequently, a considerable amount of statistical and data mining techniques to iden- tify anomalies was proposed in the last few years, but only a few works at least mentioned why some sample was la- belled as an anomaly. Therefore, we propose a method based on specifically trained decision trees, called sapling random forest. Our method is able to interpret the output of arbitrary anomaly detector. The explanation is given as a subset of features, in which the sample is most deviating, or as con- junctions of atomic conditions, which can be viewed as antecedents of logical rules easily understandable by hu- mans. To simplify the investigation of suspicious samples even more, we propose two methods of clustering anoma- lies into groups. Such clusters can be investigated at once saving time and human efforts. The feasibility of our ap- proach is demonstrated on several synthetic and one real world datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA13-17187S" target="_blank" >GA13-17187S: Konstrukce pokročilých srozumitelných klasifikátorů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 14th conference ITAT 2014 – Workshops and Posters

ISBN

978-80-87136-19-5

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

61-67

Název nakladatele

Institute of Computer Science AS CR

Místo vydání

Praha

Místo konání akce

Demänovská Dolina

Datum konání akce

25. 9. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—