Open Collections

UBC Graduate Research

Predicting Job Salaries from Text Descriptions Jackman, Shaun; Reid, Graham

Abstract

An online job listing web site has extensive data that is primarily unstructured text descriptions of the posted jobs. Many listings provide a salary, but as many as half do not. For those listings that do not provide a salary, it is useful to predict a salary based on the description of that job. We tested a variety of regression methods, including maximum-likelihood regression, lasso regression, artificial neural net- works and random forests. We optimized the parameters of each of these methods, validated the performance of each model using cross validation and compared the performance of these methods on a withheld test data set.

Item Metadata

Title
Predicting Job Salaries from Text Descriptions
Creator
Jackman, Shaun; Reid, Graham
Date Issued
2013-04-16
Description
An online job listing web site has extensive data that is primarily unstructured text descriptions of the posted jobs. Many listings provide a salary, but as many as half do not. For those listings that do not provide a salary, it is useful to predict a salary based on the description of that job. We tested a variety of regression methods, including maximum-likelihood regression, lasso regression, artificial neural net- works and random forests. We optimized the parameters of each of these methods, validated the performance of each model using cross validation and compared the performance of these methods on a withheld test data set.
Subject
Machine learning
Genre
Article
Type
Text
Language
eng
Series
University of British Columbia. STAT 540
Date Available
2013-09-17
Provider
Vancouver : University of British Columbia Library
Rights
Attribution-NonCommercial-ShareAlike 2.5 Canada
DOI
10.14288/1.0075767
URI
http://hdl.handle.net/2429/45081
Affiliation
Science, Faculty of; Statistics, Department of
Campus
UBCV
Peer Review Status
Unreviewed
Scholarly Level
Graduate
Rights URI
http://creativecommons.org/licenses/by-nc-sa/2.5/ca/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

Attribution-NonCommercial-ShareAlike 2.5 Canada