Deep Learning for Economists

Melissa Dell

doi:10.1257/jel.20241733

journal article Mar 01, 2025

Deep Learning for Economists

Melissa Dell

Journal of Economic Literature Vol. 63 No. 1 pp. 5-58 · American Economic Association

View at Publisher Save 10.1257/jel.20241733

Abstract

Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images or measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative artificial intelligence (AI), and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive-scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points. The review is accompanied by a regularly updated companion website, EconDL ( https://econdl.github.io/ ), with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications. (JEL C38, C45, C88, D83)

Topics

No keywords indexed for this article. Browse by subject →

References

140

[1]

10.1257/jel.20201599

[2]

Alammar, Jay. 2018a. "The Illustrated Bert, Elmo, and co. (How NLP Cracked Transfer Learning)." Blog post. https://jalammar.github.io/illustrated-bert/.

[3]

Alammar, Jay. 2018b. "The Illustrated Transformer." Blog post. https://jalammar.github.io/illustrated-transformer/.

[4]

Alammar, Jay. 2019. "The Illustrated GPT-2 (Visualizing Transformer Language Models)." Blog post. http:// jalammar.github.io/illustrated-gpt2/.

[5]

Alammar, Jay. 2020. "Works-Visualizations and Animations." Blog post. https://jalammar.github.io/ how-gpt3-works-visualizations-animations/.

[6]

Transformers in Remote Sensing: A Survey

Abdulaziz Amer Aleissaee, Amandeep Kumar, Rao Muhammad Anwer et al.

Remote Sensing 10.3390/rs15071860

[7]

Ali, Alaaeldin, Hugo Touvron, Mathilde Caron, Piotr Bojanowski, Matthijs Douze, Armand Joulin, Ivan Laptev, etal 2021. "XCiT: Cross-Covariance Image Transformers." In Advances in Neural Information Processing Systems, Vol. 34, edited by M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, and J. Wortman Vaughan, 20014-27. Curran Associates, Inc.

[8]

10.1126/science.adi6000

[9]

Dell Melissa Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (2024)

[10]

Silcock Emily Preprint, arXiv. https://doi.org/10.48550/arXiv. (2024)

[11]

Yang Xinmei Preprint, arXiv. https://doi.org/10.48550/arXiv. (2024)

[12]

10.1146/annurev-economics-080217-053433

[13]

10.1257/jel.20191526

[14]

Bandara, Wele Gedara Chaminda, and Vishal M. Patel. 2022. "A Transformer-Based Siamese Network for Change Detection." In IGARSS 2022-2022 IEEE International Geoscience and Remore Sensing Symposium, 207-210. IEEE. 10.1109/igarss46834.2022.9883686

[15]

Beach, Brian, and W. Walker Hanlon. 2022. "Historical Newspaper Data: A Researcher's Guide and Toolkit." NBER Working Paper 30135. 10.3386/w30135

[16]

Learning long-term dependencies with gradient descent is difficult

Y. Bengio, P. Simard, P. Frasconi

IEEE Transactions on Neural Networks 10.1109/72.279181

[17]

Kumar Ankan Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)

[18]

Binette, Olivier, and Rebecca C. Steorts. 2022. "(Almost) All of Entity Resolution." Science Advances 8 (12): eabi8021. 10.1126/sciadv.abi8021

[19]

Mann Benjamin Advances in Neural Information Processing Systems (2020)

[20]

Bryan, Tom, Jacob Carlson, Abhishek Arora, and Melissa Dell. 2023. "EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge." In Proceedings of the 2023 Conference on Empirical Methods on Natural Language Processing: Systems Demonstrations, 579-596. Association for Computational Linguistics. 10.18653/v1/2023.emnlp-demo.52

[21]

Vasconcelos Nuno Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)

[22]

Vasconcelos Nuno IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)

[23]

Preprint, arXiv. https://doi.org/10.48550/arXiv. (2024)

[24]

Carion, Nicolas, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. "End-to-End Object Detection with Transformers." In Computer Vision-ECCV 2020, edited by Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, 213-229. Springer. 10.1007/978-3-030-58452-8_13

[25]

Carlson, Jacob., Tom Bryan, and Melissa Dell. 2024. "Efficient OCR for Building a Diverse Digital History." In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Vol. 1, edited by Lun-Wei Ku, Andre Martins, and Vivek Srikumar, 8105-15. Association for Computational Linguistics. 10.18653/v1/2024.acl-long.440

[26]

Touvron Hugo Proccedings of the IEEE/CVF International Conference on Computer Vision (2021)

[27]

Matias Preprint, arXiv. https://doi.org/10.48550/arXiv. (2022)

[28]

Xie Saining Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)

[29]

Double/debiased machine learning for treatment and structural parameters

Victor Chernozhukov, Denis Chetverikov, Mert Demirer et al.

The Econometrics Journal 10.1111/ectj.12097

[30]

10.3982/ecta18515

[31]

10.1080/01621459.2021.1920957

[32]

Learning a Similarity Metric Discriminatively, with Application to Face Verification

S. Chopra, R. Hadsell, Y. Lecun

2005 IEEE Computer Society Conference on Computer... 10.1109/cvpr.2005.202

[33]

10.1038/s42256-022-00445-z

[34]

Cao De Preprint, arXiv. https://doi.org/10.48550/arXiv. (2020)

[35]

Dell, Melissa. 2024. Data and Code for: "Deep Learning for Economists." American Economic Association; distributed by Inter-university Consortium for Political and Social Research. https://doi.org/10.3886/E210922V1.

[36]

Dell, Melissa, Jacob Carlson, Tom Bryan, Emily Silcock, Abhishek Arora, Zejiang Shen, Luca D'Amico-Wong, Quan Le, Pablo Querubin, and Leander Heldring. 2023. "American Stories: A Large-Scale Structured Text Dataset of Historical US Newspapers." In Advances in Neural Information and Processing Systems, Vol. 36, edited by A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine. Curran Associates, Inc.

[37]

ImageNet: A large-scale hierarchical image database

Jia Deng, Wei Dong, Richard Socher et al.

2009 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2009.5206848

[38]

Chang Ming-Wei Proceedings of NAACL-HLT (2019)

[39]

Sap Maarten Preprint, arXiv. https://doi.org/10.48550/arXiv. (2021)

[40]

Beyer Lucas Preprint, arXiv. https://doi.org/10.48550/arXiv. (2020)

[41]

Preprint, arXiv. https://doi.org/10.48550/arXiv. (2019)

[42]

Klein Aaron Proceedings of the 35th International Conference on Machine Learning (2018)

[43]

Fernández-Villaverde, Jesús. 2024. "Deep Learning for Macroeconomists." https://www.sas.upenn.edu/~jesusfv/ teaching.html.

[44]

Silcock Emily Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (2024)

[45]

Millard Koreen Preprint, arXiv. https://doi.org/10.48550/arXiv. (2022)

[46]

Datasheets for datasets

Timnit Gebru, Jamie Morgenstern, Briana Vecchione et al.

Communications of the ACM 10.1145/3458723

[47]

10.1257/jel.20181020

[48]

Gissin, Daniel, and Shai Shalev-Shwartz. 2019. "Discriminative Active Learning." Preprint, arXiv. https://doi. org/10.48550/arXiv.1907.06347.

[49]

Distill (2017)

[50]

Gong, Yuan, Yu-An Chung, and James Glass. 2021. "AST: Audio Spectrogram Transformer." Preprint, arXiv. https:// doi.org/10.48550/arXiv.2104.01778. 10.21437/interspeech.2021-698

Showing 50 of 140 references

Metrics

40

Citations

140

References

Details

Published: Mar 01, 2025
Vol/Issue: 63(1)
Pages: 5-58

Authors

M

Melissa Dell

Harvard University Department of Economics and NBER.

Cite This Article

Melissa Dell (2025). Deep Learning for Economists. Journal of Economic Literature, 63(1), 5-58. https://doi.org/10.1257/jel.20241733

Deep Learning for Economists

You May Also Like