Paper: arXiv 2308.02491
Authors: Lea Karbevska, César A. Hidalgo
Abstract
Value chain data is crucial to navigate economic disruptions, such as those caused by the COVID-19 pandemic and the war in Ukraine. Yet, despite its importance, publicly available value chain datasets, such as the World Input-Output Database’’, Inter-Country Input-Output Tables’’, EXIOBASE’’ or the EORA’’, lack detailed information about products (e.g. Radio Receivers, Telephones, Electrical Capacitors, LCDs, etc.) and rely instead on more aggregate industrial sectors (e.g. Electrical Equipment, Telecommunications). Here, we introduce a method based on machine learning and trade theory to infer product-level value chain relationships from fine-grained international trade data. We apply our method to data summarizing the exports and imports of 300+ world regions (e.g. states in the U.S., prefectures in Japan, etc.) and 1200+ products to infer value chain information implicit in their trade patterns. Furthermore, we use proportional allocation to assign the trade flow between regions and countries. This work provides an approximate method to map value chain data at the product level with a relevant trade flow, that should be of interest to people working in logistics, trade, and sustainable development.
Complexity vs Empirical Score
- Math Complexity: 4.0/10
- Empirical Rigor: 6.0/10 (capped from 7.0: no out-of-sample test; see penalty flags)
- Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 7.0)
Why this score: The paper uses an optimization model and trade theory concepts, but the math is not excessively dense or advanced, focusing on a practical method. The empirical component is strong, leveraging fine-grained international trade data for over 300 regions and 1200+ products, with clear data cleaning and validation steps against OECD data, making it highly applicable for real-world analysis.
Research Flowchart
flowchart TD
A["Research Goal:<br>Map Global Value Chains<br>at the Product Level"] --> B{"Methodology"}
B --> C["Input Data:<br>Trade Data<br>300+ Regions & 1200+ Products"]
C --> D["ML & Trade Theory:<br>Infer Product-Level Relationships"]
D --> E["Proportional Allocation:<br>Assign Trade Flows<br>Regions & Countries"]
E --> F["Key Outcomes:<br>Granular Value Chain Maps<br>Actionable Logistics Insights"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes the “Backward & Forward” method that combines machine‑learning and trade‑theory to infer product‑level value‑chain relationships from fine‑grained international trade data.
Source sentence
Here, we introduce a method based on machine learning and trade theory to infer product-level value chain relationships from fine-grained international trade data.
Assumes 5
- Imports are allocated to sectors in the same proportion as local inputs (proportional allocation). model
Source sentence
That is, they assume, for instance, that if 20% of the steel produced in a country is used for the production of machinery, then 20% of the steel imported from any country will also be used for the production of machinery.
- A location with RCA > 1 in a product is specialized in that product. data
Source sentence
RCA larger than 1 in a product, we say that the location is specialized in that product since it exports more than what it is expected for a location of the same size and for a product with the same global market.
- Specialization patterns across geographies can be used as features to recover global value‑chain information. model
Source sentence
Our hypothesis is that by exploiting specialization patterns across multiple geographies we can generate features that when fed in a machine learning model can recover information about global value chains.
- The fine‑grained trade data (2017‑2020) is sufficiently representative of product‑level flows. data
Source sentence
We leverage fine-grained international data compiled by the Observatory of Economic Complexity
Show 1 more
- The OECD Inter‑Country Input‑Output table provides a valid benchmark for fine‑tuning the product‑level dataset. data
Source sentence
construct a product-level dataset fine-tuned on the OECD Inter‑Country Input‑Output table
Data
- Observatory of Economic Complexity trade data macro public
Source sentence
spanning from the year 2017 to 2020. This is data on exports and imports at the regional level for 1,226 HS4 level and 5,890 HS6 level unique products.
- OECD Inter‑Country Input‑Output table macro public
Source sentence
construct a product-level dataset fine-tuned on the OECD Inter‑Country Input‑Output table
Costs
Not applicable
Finds 2
- The Backward & Forward method outperforms a random baseline, identifying at least one correct input for more than 40% of the data—over twice the random baseline performance. performance
Source sentence
the “Backward & Forward” method outperforms the random baseline, identifying at least one correct input for more than 40% of the data, which is more than twice as much as the capabilities of a random baseline model.
- The method correctly identifies three inputs for complex products such as cars, integrated circuits, computers, and telephones. performance
Source sentence
We also demonstrate that the method identifies correctly three inputs for complex products such as cars, integrated circuits, computers, and telephones.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 8 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.