Free tools Windows power users keep installed
One-click scans. No signup required.
Short answer: No independent evidence shows that Microsoft built a system able to reliably identify, by name and address, which girls would become pregnant years later. Salta’s government did partner with Microsoft on a social-intervention platform, but the widely repeated “86%” figure came from Governor Juan Manuel Urtubey’s 2018 statement—not from a validated accuracy result.
A review by the University of Buenos Aires’ Applied Artificial Intelligence Laboratory (LIAA) found that the described evaluation could have overstated performance, used potentially incomplete pregnancy data, and attempted to forecast an outcome that the survey design did not measure. The episode is therefore best understood as a disputed public claim about a sensitive government algorithm, not a proven predictive breakthrough.
As an Amazon Associate I earn from qualifying purchases.
What the Salta platform was
The system was called the Plataforma Tecnológica de Intervención Social (Technological Platform for Social Intervention). The Not My AI report describes a pilot in Salta municipality beginning in 2015, developed through a partnership between Salta’s Ministry of Early Childhood and Microsoft. Its stated goals included preventing school dropout and teenage pregnancy.
Futurism’s summary of a 2022 Wired investigation says the province approved development in 2018. That reporting describes Microsoft involvement, but it does not by itself establish Microsoft’s exact technical ownership of every component or every deployment decision.
#1 Best Overall
- RESULTS IN 3 MINUTES: With this 3-count box of First Response Early Result Pregnancy Tests, get accurate results in 3 minutes, sooner than any other early detection test (2); 6 days before the day of your missed period
- NO EARLY DETECTION PREGNANCY TEST TELLS YOU FASTER (2): With reliable results in 3 minutes, no early detection pregnancy test gives you results sooner than First Response Early Result Pregnancy Tests
- OVER 99% ACCURATE: Early Result early pregnancy test is over 99% accurate at detecting pregnancy hormone levels on the day of your expected period (3) so you can have confidence in the results
- CONVENIENT & PORTABLE: Each disposable test is discreetly sized and individually wrapped so you can test anytime and anywhere
- SIMPLE TO USE AND READ: Place test tip in urine stream for 5 seconds and wait 3 minutes for results; after 3 minutes, this pregnancy test shows 2 pink lines for a pregnant result and 1 pink line to indicate a not pregnant result
What the governor claimed
During a television appearance on April 11, 2018, Governor Juan Manuel Urtubey described the technology this way, as quoted by LIAA:
“Vos podés hoy con la tecnología que tenés, podés ver, cinco o seis años antes, con nombre y apellido y domicilio, cuál es una niña, futura adolescente, que está un 86% predestinada a tener embarazo adolescente.”
A faithful translation is: “With the technology you have today, you can see five or six years in advance, by name, surname, and address, which girl, future adolescent, is 86% predestined to have a teenage pregnancy.” The wording is Urtubey’s public claim. It is not an independently measured model-accuracy statistic.
Recommended Free Tools
Claim versus evidence
| Public claim or reported feature | What the available evidence establishes |
|---|---|
| “86% predestined” to experience teenage pregnancy | Urtubey used that figure in his 2018 statement. LIAA challenged the methodology associated with the reported results; no independently validated accuracy figure is established. |
| A forecast five or six years ahead | LIAA says the described survey recorded pregnancy that had already happened or was current, which cannot by itself validate a prediction several years into the future. |
| Identification by name, surname, and address | The governor claimed this capability. The statement does not demonstrate that the system reliably made such individual predictions. |
| Microsoft-developed public technology | Reporting describes a Salta government–Microsoft partnership, while the precise division of technical responsibility remains unclear. |
Why LIAA disputed the reported performance
1. Synthetic examples were created before the data split
The methodology described in a GitHub document associated with a Microsoft employee used SMOTE, or Synthetic Minority Over-sampling Technique, before separating data into training and evaluation sets. SMOTE creates artificial examples of underrepresented cases. If synthetic or near-duplicate records derived from the same original examples appear in both sets, the evaluation set is no longer genuinely independent. LIAA warned that this contamination could make performance look better than it really was and concluded that the system’s true accuracy could not be determined from that procedure. Its technical review is published in “Sobre la predicción automática de embarazos adolescentes.”
Rank #2
- RAPID DETECTION PREGNANCY TEST: Includes two (w) Clearblue Rapid Detection Home Pregnancy Tests that can give you a result as fast as 1 minute[1]
- EASY TO USE: The extra-wide tip changes color to show you’ve hit the target. The comfortable-to-hold, long, curved handle for easy sampling also helps maintain hygiene
- EASY-TO-READ RESULTS: Clear plus (+) or minus (-) result
- OVER 99% ACCURATE: Over 99% accurate at detecting pregnancy from the day you expect your period[2]
- FLOODGUARD(TM) TECHNOLOGY: Helps cut down on #1 reported usage error by +70%[3]
2. Pregnancy data may not represent every pregnancy equally
Pregnancy is sensitive and can be concealed or underreported. LIAA’s concern is that records may reflect different reporting patterns among social groups rather than the underlying rate of pregnancy alone. That is a data-quality and representativeness problem; it is not a measured estimate of how large any group-specific bias was.
3. The outcome did not match the forecast horizon
The described survey asked about a pregnancy that was current or had already occurred. To test whether a child would become pregnant five or six years later, researchers would need appropriately timed longitudinal data collected before that event. A cross-sectional record of past or current pregnancy cannot establish that future prediction.
What information the system reportedly used
The reporting describes a dataset focused on girls, including ages 10–19. Listed fields included:
- Age and neighborhood
- Ethnicity and country of origin
- Education of the household head
- Disability
- Household size
- Whether the home had hot water in its bathroom
These are highly sensitive social and household characteristics. Their presence does not prove that any one field caused a prediction, nor does it show that the model separated social disadvantage from pregnancy risk in a scientifically valid way.
Rank #3
- EARLY DETECTION PREGNANCY TEST: Includes three (3) Clearblue Early Detection Pregnancy Tests
- EASY-TO-READ RESULTS: Two lines means you are pregnant. It does not matter how faint or dark (or how wide) the lines are
- OVER 99% ACCURATE: The Clearblue Early Detection Pregnancy Test is over 99% accurate from the day you expect your period[1]
- RESULTS 6 DAYS SOONER: Can tell you 6 days sooner than your missed period (5 days before you expect your period)[2]
- DETECTS hCG HORMONE: Can detect even low levels of the “pregnancy hormone” (hCG) in your urine[3]
Reports of home visits and location tracking
Futurism’s account of the Wired investigation says “territorial agents” visited people identified by the system, photographed them, and recorded GPS locations. The reporting also says no formal impact assessment had been conducted. Those details should be attributed to that investigation: the material available here does not establish how every record was stored, shared, retained, or deleted, or whether each reported practice occurred in every case.
The Not My AI report warns that weak data and automated targeting could stigmatize poor women and girls. That is a documented ethical concern, not a formal causal study proving downstream harm from this platform.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Could an algorithm predict teenage pregnancy?
Statistical models can identify correlations in historical records, but a correlation score is not destiny and does not automatically translate into an actionable prediction for a named child. A credible claim would require, at minimum:
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →- A clearly defined target, such as a pregnancy occurring within a specified future period
- Data collected before that period begins
- A genuinely independent test set, with preprocessing performed without contaminating evaluation records
- Transparent reporting of false positives, false negatives, calibration, and performance across demographic groups
- Evidence that the model improves outcomes without imposing disproportionate surveillance or stigma
The LIAA critique indicates that the methodology described for Salta did not establish those conditions.
Rank #4
- Reliable Accurate: Early pregnancy hCG test strips are cost effective, powered by intelligent Premom app. Home pregnancy strips are sealed in individual pouches.
- Easy to Test: Simply dip the test in your urine until the dye rises into the result window, approximately 5-10 seconds, lay flat to dry for 5 minutes, then read your results
- Easy to Read: Two lines means pregnant and one control line means not pregnant; No more guessing
- Early Detection: Pregnancy tests detect HCG levels as low as 25 mIU/mL in just 5 minutes
- Designed for convenient and easy at-home testing: We are committed to providing high-quality fertility test and care products, along with exceptional customer service. Our products have helped millions of users better understand their fertility
What remains unknown
Whether the platform is still operating
The available reporting does not establish whether the Salta system remains active, was discontinued, or was replaced by a later program.
What happened to collected records
There is no definitive account here of the downstream data lifecycle: retention periods, access controls, deletion, or later reuse of household, photographic, and GPS records.
Whether later deployments occurred
The material does not establish whether the same model or platform was deployed elsewhere after the reported Salta project.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
The defensible takeaway
Salta’s platform was a real public-sector technology project associated with Microsoft, and its stated aims included reducing school dropout and teenage pregnancy. But “86% predestined” was a governor’s description, not a validated accuracy result. LIAA identified evaluation contamination, potentially biased outcome data, and a mismatch between the survey and the claimed five- or six-year forecast. Until those issues are resolved with transparent, independent testing and clear safeguards, the claim should be treated as unproven—and the use of sensitive data to target identifiable girls as a serious accountability question.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
