Integrating AI into household survey data encoding workflows

Abstract

This paper explores the strategies employed to develop a system leveraging deep learning and natural language processing techniques for automating aspects of record coding in statistical data products. The work focuses on the Mexican Statistical Institute (INEGI), where the proposed AI model aims to reduce the volume of records requiring manual coding. The experiments conducted demonstrate the potential for these methodological innovations to partially replace traditional manual coding processes. Specifically, a novel phase has been introduced into INEGI’s data encoding workflows, utilizing an AI model to select a subset of records for which the model has a high degree of confidence in assigning the correct codes. This approach seeks to minimize the need for manual intervention. To evaluate the effectiveness of this proposal, a production line was implemented that mirrored the existing process but included the AI-based phase. The results show that the use of deep learning algorithms can achieve a significant 50% reduction in manual coding tasks without compromising the quality of the output.

Keywords

deep learning natural language processing automated coding household surveys

Get full access to this article

View all access options for this article.

References

Chaisricharoen

Srimaharaj

Boonyanant

, et al. Ontology model for automatic duplication reducing for industrial standard assessment. In: 2021 Joint international conference on digital arts, media and technology with ECTI northern section conference on electrical, electronics, computer and telecommunication engineering, 2021, IEEE. DOI: 10.1109/ectidamtncon51128.2021.9425757. https://doi.org/10.1109%2Fectidamtncon51128.2021.9425757.

Ikudo

Lane

Staudt

, et al. Occupational classifications: a machine learning approach. J Econ Soc Meas 2020; 44: 57–87.

Gweon

Schonlau

Kaczmirek

, et al. Three methods for occupation coding based on statistical learning. J Off Stat 2017a; 33: 101.

Gweon

Schonlau

Kaczmirek

, et al. Improving the accuracy of automated occupation coding at any production rate. SSRN Electron J 2017b. DOI: https://doi.org/10.2139/ssrn.2777765. https://doi.org/10.2139%2Fssrn.2777765 .

Oehlert

Schulz

Parker

. NAICS code prediction using supervised methods. Stat Public Policy 2022; 9: 58–66.

INEGI. Sistema nacional de clasificación de ocupaciones 2011 : SINCO.

Wood

Muthyala

Jin

, et al. Automated industry classification with deep learning. In: 2017 IEEE international conference on big data (Big Data), 2017, IEEE. DOI: 10.1109/bigdata.2017.8257920. https://doi.org/10.1109%2Fbigdata.2017.8257920.

Schierholz

Schonlau

. Machine learning for occupation coding—a comparison study. J Surv Stat Methodol 2021; 9: 1013–1034.

Turrell

Speigner

Djumalieva

, et al. Transforming naturally occurring text data into economic statistics: the case of online job vacancy postings. 2019. DOI: 10.3386/w25837. https://doi.org/10.3386%2Fw25837.

10.

Dwicahyo

Yuniarto

. Deep learning for Indonesia standard industrial classification. In: 2020 International conference on electrical engineering and informatics (ICELTICs), 2020, IEEE. DOI: 10.1109/iceltics50595.2020.9315361. https://doi.org/10.1109%2Ficeltics50595.2020.9315361.

11.

Peycheva

Sakshaug

Calderwood

. Occupation coding during the interview in a web-first sequential mixed-mode survey. J Off Stat 2021; 37: 981–1007.

12.

Colasanti

Macchia

Vicari

. The automatic coding of economic activities descriptions for web users. 2009.

13.

Thompson

Kornbau

Vesely

. Creating an automated industry and occupation coding process for the American community survey. unpublished report, 2012.

14.

Takahashi

Taki

Tanabe

, et al. An automatic coding system with a three-grade confidence level corresponding to the national/international occupation and industry standard-open to the public on the web. In: KEOD, 2014, pp.369–375.