Highly Accurate Prediction of Jobs Runtime Classes

TL;DR

This paper presents a novel method for accurately classifying jobs into runtime categories using a Gaussian mixture model and CART classifier, achieving over 90% accuracy to enhance scheduling efficiency.

Contribution

The paper introduces a new approach combining Gaussian mixture modeling with CART classification for precise job runtime class prediction.

Findings

Achieved 90% overall accuracy in runtime class prediction.

Sensitivity and specificity both exceeded 90%.

Method improves job scheduling performance.

Abstract

Separating the short jobs from the long is a known technique to improve scheduling performance. In this paper we describe a method we developed for accurately predicting the runtimes classes of the jobs to enable this separation. Our method uses the fact that the runtimes can be represented as a mixture of overlapping Gaussian distributions, in order to train a CART classifier to provide the prediction. The threshold that separates the short jobs from the long jobs is determined during the evaluation of the classifier to maximize prediction accuracy. Our results indicate overall accuracy of 90% for the data set used in our study, with sensitivity and specificity both above 90%.