Logo des Repositoriums
 
Zeitschriftenartikel

Intelligent Questionnaires Using Approximate Dynamic Programming

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Text/Journal Article

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

De Gruyter

Zusammenfassung

Inefficient interaction such as long and/or repetitive questionnaires can be detrimental to user experience, which leads us to investigate the computation of an intelligent questionnaire for a prediction task. Given time and budget constraints (maximum <em>q</em> questions asked), this questionnaire will select adaptively the question sequence based on answers already given. Several use-cases with increased user and customer experience are given.</p><p>The problem is framed as a Markov Decision Process and solved numerically with approximate dynamic programming, exploiting the hierarchical and episodic structure of the problem. The approach, evaluated on toy models and classic supervised learning datasets, outperforms two baselines: a decision tree with budget constraint and a model with <em>q</em> best features systematically asked. The online problem, quite critical for deployment seems to pose no particular issue, under the right exploration strategy.</p><p>This setting is quite flexible and can incorporate easily initial available data and grouped questions.

Beschreibung

Logé, Frédéric; Pennec, Erwan Le; Amadou-Boubacar, Habiboulaye (2021): Intelligent Questionnaires Using Approximate Dynamic Programming. i-com: Vol. 19, No. 3. DOI: 10.1515/icom-2020-0022. Berlin: De Gruyter. PISSN: 2196-6826. pp. 227-237

Zitierform

Tags