Saving Millions in Government Procurement Through Data Science and Market Design

33 Pages Posted: 20 Jan 2023 Last revised: 30 Nov 2023

See all articles by Marcelo Olivares

Marcelo Olivares

University of Chile; University of Chile - Engineering Department

Daniela Saban

Stanford Graduate School of Business

Gabriel Y. Weintraub

Stanford Graduate School of Business, Stanford University

Eduardo Lara

University of Chile

Piero Zanocco

University of Chile

Paula Moreno

ChileCompra

Date Written: January 1, 2023

Abstract

Framework agreements (FAs) are procurement mechanisms used in private and public organizations by which a central procurement agency selects an assortment of products, typically through auctions, and then affiliated organizations can purchase from the selected assortment as needs arise. In Chile's central procurement agency (ChileCompra), FAs accounted for 23% of the procurement expenditures during 2018-19. However, descriptive analysis of purchase transaction data suggests that some FAs exhibited low levels of competition in the auctions used to select the suppliers, which could potentially result in larger government expenditures. We collaborated with ChileCompra to redesign FAs to enhance competition introducing two important changes: (i) standardize the product catalogue using natural language processing algorithms; (ii) use this product standardization to induce more competition in the auctions to select of suppliers. These changes were implemented through an experimental design in the new Food FA to measure its impact, showing that inducing more intense competition in the auction stage reduced transaction prices by 8%. This pilot study ultimately led ChileCompra to implement a similar design in all of its FAs, and many of the improvements in the design of the FAs were included in the new regulation on government purchases. If we were to extrapolate the savings from our pilot re-design to all of these FAs, the total savings would amount to around US$64 million in 2022.

Suggested Citation

Olivares, Marcelo and Saban, Daniela and Weintraub, Gabriel Y. and Lara, Eduardo and Zanocco, Piero and Moreno, Paula, Saving Millions in Government Procurement Through Data Science and Market Design (January 1, 2023). Stanford University Graduate School of Business Research Paper No. 4327950, Available at SSRN: https://ssrn.com/abstract=4327950 or http://dx.doi.org/10.2139/ssrn.4327950

Marcelo Olivares (Contact Author)

University of Chile ( email )

Pío Nono Nº1, Providencia
Santiago, R. Metropolitana 7520421
Chile

University of Chile - Engineering Department ( email )

Republica 701 Santiago
Chile

Daniela Saban

Stanford Graduate School of Business ( email )

655 Knight Way
Stanford, CA 94305-5015
United States

Gabriel Y. Weintraub

Stanford Graduate School of Business, Stanford University ( email )

Stanford, CA 94305
United States

Eduardo Lara

University of Chile ( email )

Pío Nono Nº1, Providencia
Santiago, R. Metropolitana 7520421
Chile

Piero Zanocco

University of Chile ( email )

Beauchef 851
Santiago, R. Metropolitana 8370285
Chile

Paula Moreno

ChileCompra

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
139
Abstract Views
723
Rank
379,169
PlumX Metrics