Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp01jq085p029
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorSingh, Jaswinder
dc.contributor.authorStengel, Gabriel
dc.date.accessioned2020-10-01T21:26:21Z-
dc.date.available2020-10-01T21:26:21Z-
dc.date.created2020-05-03
dc.date.issued2020-10-01-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/dsp01jq085p029-
dc.description.abstractHere, we presentAthena: a statistical querying tool that can perform advancedeconometric analysis using natural language queries.Contemporary economic analysis is done mainly using tools like Stata, R, and(sometimes) Python. These tools require expertise to master, and consequentlythey are inaccessible to many students and individuals without the requisite guid-ance or training. Athena provides an alternative method of statistical and econo-metric exploration, free of arcane syntactic requirements. In this work, we outlinethe application: its construction, design, and usage. The product utilizes context-free-grammars for semantic parsing and its statistical engine is expansive –– con-taining a plethora of econometric functionality. Additionally, Athena can reasonabout unseen data and is capable of some machine learning and data visualiza-tion.Ultimately, Athena is a creation of many academic research areas and encom-passes domains from natural language understanding to automated instrumentselection. This project is open source and can be viewed on my github.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleAthena: A Flexible Econometric Querying Tool
dc.typePrinceton University Senior Theses
pu.date.classyear2020
pu.departmentComputer Science
pu.pdf.coverpageSeniorThesisCoverPage
pu.contributor.authorid961229193
Appears in Collections:Computer Science, 1988-2020

Files in This Item:
File Description SizeFormat 
STENGEL-GABRIEL-THESIS.pdf2.29 MBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.