Cost-sensitive classification problem (Poster)

T.G.K. Calders; M. Pechenizkiy

Cost-sensitive classification problem (Poster)

T.G.K. Calders, M. Pechenizkiy

Data Mining

Research output: Contribution to conference › Poster

1 Downloads (Pure)

Abstract

In practical situations almost all classification problems are cost-sensitive or utility based one way or another. This exercise mimics a real situation in which students first have to translate a description into a datamining workflow, learn a prediction model, apply it to new data, and set up a testing strategy to estimate what will be the performance. The exercise is suitable for students following an introductory data mining course; it has been used in my introductory data mining class (3ECTS; 3rd BSc Computer Science students) for two years now. Students work on it in class for approximately 1 hour and finish the exercise at home. Solutions are to be sent to the lecturer and discussion the solutions the next lecture takes approximately 30 minutes.

Original language	English
Pages	1-6
Publication status	Published - 2012
Event	conference; Workshop on Teaching Machine Learning; 2012-06-30; 2012-06-30 - Duration: 30 Jun 2012 → 30 Jun 2012

Conference

Conference	conference; Workshop on Teaching Machine Learning; 2012-06-30; 2012-06-30
Period	30/06/12 → 30/06/12
Other	Workshop on Teaching Machine Learning

Bibliographical note

Workshop on Teaching Machine Learning (Edinburgh, Scotland, June 30, 2012; co-located with ICML 2012)

Fingerprint Dive into the research topics of 'Cost-sensitive classification problem (Poster)'. Together they form a unique fingerprint.

Cite this

@conference{19b9810667324c308d70716c0b459841,

title = "Cost-sensitive classification problem (Poster)",

abstract = "In practical situations almost all classification problems are cost-sensitive or utility based one way or another. This exercise mimics a real situation in which students first have to translate a description into a datamining workflow, learn a prediction model, apply it to new data, and set up a testing strategy to estimate what will be the performance. The exercise is suitable for students following an introductory data mining course; it has been used in my introductory data mining class (3ECTS; 3rd BSc Computer Science students) for two years now. Students work on it in class for approximately 1 hour and finish the exercise at home. Solutions are to be sent to the lecturer and discussion the solutions the next lecture takes approximately 30 minutes.",

author = "T.G.K. Calders and M. Pechenizkiy",

note = "Workshop on Teaching Machine Learning (Edinburgh, Scotland, June 30, 2012; co-located with ICML 2012); conference; Workshop on Teaching Machine Learning; 2012-06-30; 2012-06-30 ; Conference date: 30-06-2012 Through 30-06-2012",

year = "2012",

language = "English",

pages = "1--6",

}

TY - CONF

T1 - Cost-sensitive classification problem (Poster)

AU - Calders, T.G.K.

AU - Pechenizkiy, M.

N1 - Workshop on Teaching Machine Learning (Edinburgh, Scotland, June 30, 2012; co-located with ICML 2012)

PY - 2012

Y1 - 2012

N2 - In practical situations almost all classification problems are cost-sensitive or utility based one way or another. This exercise mimics a real situation in which students first have to translate a description into a datamining workflow, learn a prediction model, apply it to new data, and set up a testing strategy to estimate what will be the performance. The exercise is suitable for students following an introductory data mining course; it has been used in my introductory data mining class (3ECTS; 3rd BSc Computer Science students) for two years now. Students work on it in class for approximately 1 hour and finish the exercise at home. Solutions are to be sent to the lecturer and discussion the solutions the next lecture takes approximately 30 minutes.

AB - In practical situations almost all classification problems are cost-sensitive or utility based one way or another. This exercise mimics a real situation in which students first have to translate a description into a datamining workflow, learn a prediction model, apply it to new data, and set up a testing strategy to estimate what will be the performance. The exercise is suitable for students following an introductory data mining course; it has been used in my introductory data mining class (3ECTS; 3rd BSc Computer Science students) for two years now. Students work on it in class for approximately 1 hour and finish the exercise at home. Solutions are to be sent to the lecturer and discussion the solutions the next lecture takes approximately 30 minutes.

M3 - Poster

SP - 1

EP - 6

T2 - conference; Workshop on Teaching Machine Learning; 2012-06-30; 2012-06-30

Y2 - 30 June 2012 through 30 June 2012

ER -