evidoria

← Back to browse

Good practice Imported

Sisbén IV — Colombia's Algorithmic Poverty-Targeting Score, and What an Independent Study Found Wrong With It

Colombia · Bogotá · See the Colombia profile · See the Bogotá profile

Evidence: Observational / pre–post Top 74% 47/100 · Ask Evidence Copilot about this practice

Colombia's Sisbén IV algorithm scores households on housing, health, education and labour data to decide eligibility for social programmes nationwide. A 2024 study found only slight agreement with the official poverty index: 37.69% of non-poor households misclassified as poor.

37.69%
Non-poor households misclassified as poor (2024)
4.89%
IPM-poor households missed by Sisbén IV (2024)
<0.36
Agreement with official poverty index (Cohen's kappa) (2024)
49.9%
Sisbén III inclusion error vs monetary poverty
64.8%
Sisbén III inclusion error vs multidimensional poverty

Details

Maturity
Established
Promoter
Departamento Nacional de Planeación (DNP)
Period
2020–present
Keywords
social protection, welfare targeting, poverty measurement, statistics

Context

Sisbén is Colombia's national targeting instrument, run by the Departamento Nacional de Planeación, used to decide eligibility for dozens of social programmes including health subsidies, the Colombia Mayor pension, housing subsidies and education grants.

Objectives

Since 2020, Metodología IV has combined housing, health, education and labour-market variables into a household score, replacing the earlier per-capita-income proxy, sorting households into groups A-D that individual programmes use to set eligibility cut-offs.

Activities

A peer-reviewed 2024 study in Desarrollo y Sociedad (Universidad de los Andes) compared Sisbén IV's household classifications directly against Colombia's official Multidimensional Poverty Index.

Results

The study found only slight statistical agreement (Cohen's kappa below 0.36): 37.69% of households the official index does not consider poor were nonetheless classified as poor by Sisbén, while 4.89% of officially poor households were missed entirely.

Conclusions

Independent analysis situates this against the prior Sisbén III methodology's even larger inclusion errors (49.9% against monetary poverty, 64.8% against multidimensional poverty), and advocates raise concerns about the opacity of the score to the citizens it classifies.

Implementation
Indicative cost
Medium (€50k–€500k)
Time to results
Long (> 3 years)
Staffing & skills
Departamento Nacional de Planeación (DNP) methodology team, municipal Sisbén survey enumerators

Conditions for success

  • accurate household survey data collection (housing, health, education, labour variables)
  • periodic independent validation against official poverty measures
  • accessible appeals process for citizens to contest scores

Common failure modes

  • only slight statistical agreement (kappa<0.36) with the official Multidimensional Poverty Index
  • 37.69% of non-poor households misclassified as poor
  • opaque scoring process and difficult-to-navigate appeals for affected citizens

Where it fits

Governance type
national planning department targeting instrument
Scale
national
Income level
upper-middle-income

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful