IDEAS home Printed from https://ideas.repec.org/p/idb/brikps/12962.html
   My bibliography  Save this paper

Automatic Product Classification in International Trade: Machine Learning and Large Language Models

Author

Listed:
  • Marra de Artiñano, Ignacio
  • Riottini Depetris, Franco
  • Volpe Martincus, Christian

Abstract

Accurately classifying products is essential in international trade. Virtually all countries categorize products into tariff lines using the Harmonized System (HS) nomenclature for both statistical and duty collection purposes. In this paper, we apply and assess several different algorithms to automatically classify products based on text descriptions. To do so, we use agricultural product descriptions from several public agencies, including customs authorities and the United States Department of Agriculture (USDA). We find that while traditional machine learning (ML) models tend to perform well within the dataset in which they were trained, their precision drops dramatically when implemented outside of it. In contrast, large language models (LLMs) such as GPT 3.5 show a consistently good performance across all datasets, with accuracy rates ranging between 60% and 90% depending on HS aggregation levels. Our analysis highlights the valuable role that artificial intelligence (AI) can play in facilitating product classification at scale and, more generally, in enhancing the categorization of unstructured data.

Suggested Citation

  • Marra de Artiñano, Ignacio & Riottini Depetris, Franco & Volpe Martincus, Christian, 2023. "Automatic Product Classification in International Trade: Machine Learning and Large Language Models," IDB Publications (Working Papers) 12962, Inter-American Development Bank.
    • Handle: RePEc:idb:brikps:12962
    DOI: http://dx.doi.org/10.18235/0005012
    as

    Download full text from publisher

    File URL: https://publications.iadb.org/publications/english/document/Automatic-Product-Classification-in-International-Trade-Machine-Learning-and-Large-Language-Models.pdf
    Download Restriction: no
    File URL: https://libkey.io/http://dx.doi.org/10.18235/0005012?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Alejandro Lopez-Lira & Yuehua Tang, 2023. "Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models," Papers 2304.07619, arXiv.org, revised Sep 2023.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Liping Wang & Jiawei Li & Lifan Zhao & Zhizhuo Kou & Xiaohan Wang & Xinyi Zhu & Hao Wang & Yanyan Shen & Lei Chen, 2023. "Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey," Papers 2308.04947, arXiv.org.
    2. Alex Kim & Maximilian Muhn & Valeri Nikolaev, 2023. "From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI," Papers 2310.17721, arXiv.org.
    3. Udit Gupta, 2023. "GPT-InvestAR: Enhancing Stock Investment Strategies through Annual Report Analysis with Large Language Models," Papers 2309.03079, arXiv.org.
    4. Haohan Zhang & Fengrui Hua & Chengjin Xu & Jian Guo & Hao Kong & Ruiting Zuo, 2023. "Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?," Papers 2306.14222, arXiv.org.
    5. Ummara Mumtaz & Summaya Mumtaz, 2023. "Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis," Papers 2311.06273, arXiv.org.
    6. Georgios Fatouros & Konstantinos Metaxas & John Soldatos & Dimosthenis Kyriazis, 2024. "Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection," Papers 2401.03737, arXiv.org.
    7. Marius Hofert, 2023. "Correlation Pitfalls with ChatGPT: Would You Fall for Them?," Risks, MDPI, vol. 11(7), pages 1-17, June.
    8. Zihan Chen & Lei Nico Zheng & Cheng Lu & Jialu Yuan & Di Zhu, 2023. "ChatGPT Informed Graph Neural Network for Stock Movement Prediction," Papers 2306.03763, arXiv.org, revised Sep 2023.
    9. Baptiste Lefort & Eric Benhamou & Jean-Jacques Ohana & David Saltiel & Beatrice Guez & Damien Challet, 2024. "Can ChatGPT Compute Trustworthy Sentiment Scores from Bloomberg Market Wraps?," Papers 2401.05447, arXiv.org.
    10. Claudia Biancotti & Carolina Camassa, 2023. "Loquacity and visible emotion: ChatGPT as a policy advisor," Questioni di Economia e Finanza (Occasional Papers) 814, Bank of Italy, Economic Research and International Relations Area.
    11. Paul Glasserman & Caden Lin, 2023. "Assessing Look-Ahead Bias in Stock Return Predictions Generated By GPT Sentiment Analysis," Papers 2309.17322, arXiv.org.
    12. Kelvin J. L. Koa & Yunshan Ma & Ritchie Ng & Tat-Seng Chua, 2024. "Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models," Papers 2402.03659, arXiv.org, revised Feb 2024.
    13. Thomas R. Cook & Sophia Kazinnik & Anne Lundgaard Hansen & Peter McAdam, 2023. "Evaluating Local Language Models: An Application to Bank Earnings Calls," Research Working Paper RWP 23-12, Federal Reserve Bank of Kansas City.
    14. Yujie Ding & Shuai Jia & Tianyi Ma & Bingcheng Mao & Xiuze Zhou & Liuliu Li & Dongming Han, 2023. "Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction," Papers 2310.05627, arXiv.org.
    15. Rick Steinert & Saskia Altmann, 2023. "Linking microblogging sentiments to stock price movement: An application of GPT-4," Papers 2308.16771, arXiv.org.
    16. Jeongbin Kim & Matthew Kovach & Kyu-Min Lee & Euncheol Shin & Hector Tzavellas, 2024. "Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice," Papers 2401.07345, arXiv.org.
    17. Zihan Dong & Xinyu Fan & Zhiyuan Peng, 2024. "FNSPID: A Comprehensive Financial News Dataset in Time Series," Papers 2402.06698, arXiv.org.
    18. Boyang Yu, 2023. "Benchmarking Large Language Model Volatility," Papers 2311.15180, arXiv.org.
    19. Junwei Su & Shan Wu & Jinhui Li, 2024. "MTRGL:Effective Temporal Correlation Discerning through Multi-modal Temporal Relational Graph Learning," Papers 2401.14199, arXiv.org, revised Feb 2024.

    More about this item

    Keywords

    Product Classification; machine learning; Large Language Models; Trade;
    All these keywords.

    JEL classification:

    • F10 - International Economics - - Trade - - - General
    • C55 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Large Data Sets: Modeling and Analysis
    • C81 - Mathematical and Quantitative Methods - - Data Collection and Data Estimation Methodology; Computer Programs - - - Methodology for Collecting, Estimating, and Organizing Microeconomic Data; Data Access
    • C88 - Mathematical and Quantitative Methods - - Data Collection and Data Estimation Methodology; Computer Programs - - - Other Computer Software

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:idb:brikps:12962. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Felipe Herrera Library (email available below). General contact details of provider: https://edirc.repec.org/data/iadbbus.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.