Trjtdtk

Why did the HMS Bounty go back to a time when whales are already rare?

Why is so much work done on numerical verification of the Riemann Hypothesis?

What should you do when eye contact makes your subordinate uncomfortable?

Is it better practice to read straight from sheet music rather than memorize it?

Does an advisor owe his/her student anything? Will an advisor keep a PhD student only out of pity?

Offered money to buy a house, seller is asking for more to cover gap between their listing and mortgage owed

Is a model fitted to data or is data fitted to a model?

Do Legal Documents Require Signing In Standard Pen Colors?

What spells are affected by the size of the caster?

Is there a single word describing earning money through any means?

Varistor? Purpose and principle

Freedom of speech and where it applies

Will the technology I first learn determine the direction of my future career?

What is the difference between Reference and Background image in 2.8

Biological Blimps: Propulsion

Reply 'no position' while the job posting is still there

What if a revenant (monster) gains fire resistance?

Non-trope happy ending?

Bob has never been a M before

How should I respond when I lied about my education and the company finds out through background check?

Pre-mixing cryogenic fuels and using only one fuel tank

The IT department bottlenecks progress. How should I handle this?

How is flyblackbird.com operating under Part 91K?

What prevents the use of a multi-segment ILS for non-straight approaches?

Variable Importance in unsupervised anomaly detection algorithms

Outlier detection for unbalanced classesNetwork Anomaly detectionhow to compare different sets of time series dataUnsupervised Anomaly Detection in ImagesUsing local outlier factor score to detect outliers at run timeHow would I apply anomaly detection to time series data in LSTM?Anomaly Detection: Model Creation & ImplementationKnowing Feature Importance from Sparse Matrix

0

$begingroup$

I am working on an anomaly detection problem to detect fraud in insurance claims. I have used the PyOD package and used algorithms like ABOD, CBLOF, Isolation Forest, and AutoEncoder. I couldn't find any way to identify the important features which make the data points anomalies ( like variable Importance in Random Forest). Is there a way to identify the important features in unsupervised anomaly detection?

python clustering anomaly-detection

share|improve this question

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

$endgroup$

add a comment | 

0

$begingroup$

I am working on an anomaly detection problem to detect fraud in insurance claims. I have used the PyOD package and used algorithms like ABOD, CBLOF, Isolation Forest, and AutoEncoder. I couldn't find any way to identify the important features which make the data points anomalies ( like variable Importance in Random Forest). Is there a way to identify the important features in unsupervised anomaly detection?

python clustering anomaly-detection

share|improve this question

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

$endgroup$

add a comment | 

$begingroup$

I am working on an anomaly detection problem to detect fraud in insurance claims. I have used the PyOD package and used algorithms like ABOD, CBLOF, Isolation Forest, and AutoEncoder. I couldn't find any way to identify the important features which make the data points anomalies ( like variable Importance in Random Forest). Is there a way to identify the important features in unsupervised anomaly detection?

python clustering anomaly-detection

share|improve this question

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

$endgroup$

share|improve this question

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

share|improve this question

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

edited Mar 19 at 17:01

Ethan

564223

edited Mar 19 at 17:01

Ethan

564223

asked Mar 19 at 13:36

GokulramGokulram

62

asked Mar 19 at 13:36

GokulramGokulram

62

2 Answers
2

active

oldest

votes

1

$begingroup$

This question has been asked so many times, yet I believe no widely accepted answer exists, especially in the case of black box models such as neural networks.

A way to go may be sensitivity analysis, i.e. evaluate the change in the output of the model for small changes in the individual inputs. The higher the change in the output, the more important the feature.

share|improve this answer

answered Mar 19 at 18:50

pcko1pcko1

1,581417

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the answer
  $endgroup$
  – Gokulram
  Mar 20 at 12:37
  

  
  
  
  

add a comment | 

0

$begingroup$

There have been workshops dedicated to "outlier detection and description" (ODD), but there came out nothing from them that convinced me, unfortunately. but YMMV.
It definitely won't be enough to just use some library! You'll need to read and implement papers. There are subspace outlier detectors and correlation outliers, for example, that will tell you which features were relevant for a particular outlier.

But in general I believe you'll quickly run into multiple testing problems: in real data, every point is anomalous if you just try attribute combinations hard enough. Donald Trump is anomalous because of his orange skin, fake hair, and small hands, for example. If you only look at his xenophobia, he probably is pretty normal, unfortunately.

share|improve this answer

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the hints.
  $endgroup$
  – Gokulram
  Mar 20 at 12:38
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);

else
createEditor();

);

function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47616%2fvariable-importance-in-unsupervised-anomaly-detection-algorithms%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

1

$begingroup$

This question has been asked so many times, yet I believe no widely accepted answer exists, especially in the case of black box models such as neural networks.

A way to go may be sensitivity analysis, i.e. evaluate the change in the output of the model for small changes in the individual inputs. The higher the change in the output, the more important the feature.

share|improve this answer

answered Mar 19 at 18:50

pcko1pcko1

1,581417

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the answer
  $endgroup$
  – Gokulram
  Mar 20 at 12:37
  

  
  
  
  

add a comment | 

1

$begingroup$

This question has been asked so many times, yet I believe no widely accepted answer exists, especially in the case of black box models such as neural networks.

A way to go may be sensitivity analysis, i.e. evaluate the change in the output of the model for small changes in the individual inputs. The higher the change in the output, the more important the feature.

share|improve this answer

answered Mar 19 at 18:50

pcko1pcko1

1,581417

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the answer
  $endgroup$
  – Gokulram
  Mar 20 at 12:37
  

  
  
  
  

add a comment | 

$begingroup$

This question has been asked so many times, yet I believe no widely accepted answer exists, especially in the case of black box models such as neural networks.

A way to go may be sensitivity analysis, i.e. evaluate the change in the output of the model for small changes in the individual inputs. The higher the change in the output, the more important the feature.

share|improve this answer

answered Mar 19 at 18:50

pcko1pcko1

1,581417

$endgroup$

share|improve this answer

answered Mar 19 at 18:50

pcko1pcko1

1,581417

answered Mar 19 at 18:50

pcko1pcko1

1,581417

answered Mar 19 at 18:50

pcko1pcko1

1,581417

0

$begingroup$

There have been workshops dedicated to "outlier detection and description" (ODD), but there came out nothing from them that convinced me, unfortunately. but YMMV.
It definitely won't be enough to just use some library! You'll need to read and implement papers. There are subspace outlier detectors and correlation outliers, for example, that will tell you which features were relevant for a particular outlier.

But in general I believe you'll quickly run into multiple testing problems: in real data, every point is anomalous if you just try attribute combinations hard enough. Donald Trump is anomalous because of his orange skin, fake hair, and small hands, for example. If you only look at his xenophobia, he probably is pretty normal, unfortunately.

share|improve this answer

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the hints.
  $endgroup$
  – Gokulram
  Mar 20 at 12:38
  

  
  
  
  

add a comment | 

0

$begingroup$

There have been workshops dedicated to "outlier detection and description" (ODD), but there came out nothing from them that convinced me, unfortunately. but YMMV.
It definitely won't be enough to just use some library! You'll need to read and implement papers. There are subspace outlier detectors and correlation outliers, for example, that will tell you which features were relevant for a particular outlier.

But in general I believe you'll quickly run into multiple testing problems: in real data, every point is anomalous if you just try attribute combinations hard enough. Donald Trump is anomalous because of his orange skin, fake hair, and small hands, for example. If you only look at his xenophobia, he probably is pretty normal, unfortunately.

share|improve this answer

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thank you for the hints.
  $endgroup$
  – Gokulram
  Mar 20 at 12:38
  

  
  
  
  

add a comment | 

$begingroup$

There have been workshops dedicated to "outlier detection and description" (ODD), but there came out nothing from them that convinced me, unfortunately. but YMMV.
It definitely won't be enough to just use some library! You'll need to read and implement papers. There are subspace outlier detectors and correlation outliers, for example, that will tell you which features were relevant for a particular outlier.

But in general I believe you'll quickly run into multiple testing problems: in real data, every point is anomalous if you just try attribute combinations hard enough. Donald Trump is anomalous because of his orange skin, fake hair, and small hands, for example. If you only look at his xenophobia, he probably is pretty normal, unfortunately.

share|improve this answer

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

$endgroup$

share|improve this answer

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624

answered Mar 19 at 19:35

Anony-MousseAnony-Mousse

5,010624