Integrating Machine Learning and Fairness Economics for Dynamic Coffee Pricing in Vietnam

DOI

10.2991/978-94-6239-624-1_16How to use a DOI?

Keywords

coffee prices; farm-gate pricing; time-series forecasting; Ridge regression; fairness economics; Vietnam

Abstract

Vietnam is the world’s second-largest coffee producer, yet smallholder farmers in the Central Highlands remain highly exposed to price volatility and information asymmetries in domestic farm-gate markets. This paper proposes an integrated framework that links time-series forecasting with fairnessoriented pricing for Robusta coffee farmers in Dak Lak. Using a monthly dataset from 2016–2024, we estimate a parsimonious autoregressive AR (1) model for one-month-ahead forecasts and a Ridge regression model with rolling macro-trade, climate and cost features for twelve-month-ahead forecasts. Both models are trained on the pre-boom period 2016–2022 and evaluated out-of-sample on the turbulent 2023–2024 price surge. The AR (1) model delivers highly accurate short-term forecasts, while the twelve-month Ridge model explains around 90% of the variance in farmgate prices during the boom, with mean absolute errors below 6,200 VND/kg. Building on these forecasts, we construct a “fair price corridor” as a symmetric band around the twelve-month forecast based on the model’s root mean squared error. The corridor is interpreted as a data-driven reference range for negotiation and risk communication, rather than a normative definition of fairness. We illustrate how such a corridor could support timing, storage and investment decisions by farmers and cooperatives, and how it could act as an early-warning tool for policymakers. The study is deliberately modest in methodological novelty and limited to one province and commodity, but demonstrates how simple, transparent models can underpin fairness-oriented decision support in smallholder-dominated value chains.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Thi Yen Nhi Nguyen
PY  - 2026
DA  - 2026/04/06
TI  - Integrating Machine Learning and Fairness Economics for Dynamic Coffee Pricing in Vietnam
BT  - Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
PB  - Atlantis Press
SP  - 213
EP  - 225
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-624-1_16
DO  - 10.2991/978-94-6239-624-1_16
ID  - Nguyen2026
ER  -