TU Darmstadt / ULB / TUprints

STATSREP-ML: Statistical Evaluation & Reporting Framework for Machine Learning Results

Guckelsberger, Christian and Schulz, Axel :
STATSREP-ML: Statistical Evaluation & Reporting Framework for Machine Learning Results.
In: Technical Report (ISSN 1864-0516), TUD-CS-2015-0027. Darmstadt, Germany
[Report], (2014)

[img]
Preview
Text
Report_Final.pdf
Available under Creative Commons Attribution Non-commercial No-derivatives 3.0 de.

Download (174kB) | Preview
Item Type: Report
Title: STATSREP-ML: Statistical Evaluation & Reporting Framework for Machine Learning Results
Language: English
Abstract:

In this report, we present STATSREP-ML, which is an open-source solution for automating the process of evaluating machine-learning results. It calculates qualitative statistics, performs the appropriate tests and reports them in a comprehensive way. It largely, but not exclusively, relies on well-tested and robust statistics implementations in R, and uses the tests the machine-learning community largely agreed upon.

Series Name: Technical Report
Volume: TUD-CS-2015-0027
Place of Publication: Darmstadt, Germany
Uncontrolled Keywords: Machine Learning, Statistics, Evaluation
Classification DDC: 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
500 Naturwissenschaften und Mathematik > 510 Mathematik
600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften
Divisions: 20 Department of Computer Science > Telecooperation
Date Deposited: 05 Jan 2015 10:07
Last Modified: 06 Jul 2016 06:13
Related URLs:
URN: urn:nbn:de:tuda-tuprints-42940
URI: http://tuprints.ulb.tu-darmstadt.de/id/eprint/4294
Export:
Actions (login required)
View Item View Item

Downloads

Downloads per month over past year