Evaluating Machine Learning–Driven Fraud Detection: Evidence from AquaData in Quito's Metropolitan Public Company of Drinking Water and Sanitation (EPMAPS)

The general objective of this Technical Cooperation is to determine the causal impact of machine learning-driven inspection targeting, through the AquaData algorithm, on fraud detection effectiveness, inspector productivity, revenue recovery, and apparent losses at EPMAPS. Its specific objectives are: (i) to design and implement a randomized controlled trial (RCT) in which sectors are randomly assigned to algorithm-driven or expert-based inspection prioritization at EPMAPS, and to compare the two approaches; (ii) to establish a standardized, high-frequency data collection protocol that supports the evaluation and strengthens the utility's inspection information systems going forward; and (iii) to produce actionable evidence to inform the institutionalization of the tool within the utility and its replication across other water utilities in the region.

Project Detail

Country

Ecuador

Project Number

EC-T1647

Approval Date

Project Status

Preparation

Project Type

Technical Cooperation

Sector

WATER AND SANITATION

Subsector

WATER SUPPLY URBAN

Lending Instrument

Lending Instrument Code

Modality

Facility Type

Environmental and Social Impact Category (ESIC)

Total Cost

USD 150,000.00

Country Counterpart Financing

Original Amount Approved

USD 150,000.00

Can’t find a document? Request information

Preparation Phase

https://www.iadb.org/viewer/EZIDB001878-1883266182-3

TC Abstract

EC-T1647 - TC Abstract.pdf

Oct. 01, 2026

English

Have an Environmental or Social issue related to IDB projects? File a Complaint