Predict Graduate Employment Outcomes

Connect education completion, first employment and household context to study the transition from graduation to work.

The record concepts include completion date, qualification level, post-study employment outcome, age / life stage, household relationships, dated demographic events and enrolment history. Explore first recorded jobs after education completion. Distinguish transition duration from incomplete follow-up. Keep education and household history separate from future outcomes.

This dataset is prepared to order. Choose the city, date range and required scope; the accepted order defines the population, final fields, formats and delivery.

Onboarded city options

Nairobi (Kenya) · Lagos (Nigeria)

Custom city requests

African Major Cities · Additional cities require availability, scope and quote confirmation.

Data type

Synthetic

Connected domains

Demographics, Education, Employment, Households

Catalogue structure

Longitudinal

Key features

Record concepts for your order-specific extract.

Who it is for

• ML engineers
• universities
• workforce planners
• education researchers

Proposed study unit

Eligible education completion event

Connect completion, first work and household history to study entry into employment.

Record concepts for your extract

• completion date
• qualification level
• post-study employment outcome
• age / life stage
• household relationships
• dated demographic events
• enrolment history

The agreed specification defines the final columns, keys, relationships and observation period for your order.

Published reference applications

• Evidence-qualified binary employment prediction using TargetEmployedPostStudySafe
• Outcome-category classification using TargetOutcomeCategory
• Time-to-first-employment analysis using TargetDaysToFirstEmployment
• Programme and qualification comparisons
• Household-context analysis at completion where linkage is available
• Lifecycle-event analysis with events restricted to the intended candidate cohort

Custom study design

Define eligible completions and prior employment; evaluate event probability and time to first job using information available at completion. Preserve incomplete follow-up.

The published Nairobi reference and an order-specific forecasting study have different evaluation contracts. Six- or twelve-month questions below are proposed custom study definitions, not a claim that the reference caps positive employment outcomes at those horizons.

Proposed questions for your custom order

1. Can education and household histories predict whether a graduate starts a first recorded job within 12 months of completing education, and how long that transition takes?
2. How quickly do graduates enter their first observed job?
3. How long does the transition from study to a first job take?
4. Which education pathways are followed by different early career outcomes?
5. Who enters employment within six or twelve months of completing study?
6. Which education and household histories help distinguish shorter and longer transitions?
7. How does employment-prediction performance vary across later graduation cohorts within the available historical coverage?
8. Which graduate groups have the largest differences between predicted and observed outcomes?

Proposed research and analytical applications

• Prediction prototyping
• Feature exploration
• Temporal validation
• Cohort comparison

Study and modeling guidance

Published Nairobi reference split

The reference uses deterministic, outcome-stratified random benchmark splits. Preserve the published CandidateKey assignments; these are not chronological cohorts.

Reference binary target

Use TargetEmployedPostStudySafe. The 2,090 evidence-unavailable candidates have a null safe target; unavailable historical evidence is different from right-censoring. IsCensored is zero in this frozen release.

Prediction-time inputs

Use the documented completion-time context: DateOfBirth, QualificationLevel, ProgrammeName, EnrollmentDate and available HouseholdRelationship. Raw identifiers, later employment evidence, targets and retrospective follow-up are excluded from predictors.

Custom temporal studies

Chronological evaluation may be appropriate for an agreed forecasting extract with dated cohorts and suitable follow-up. Define the prediction anchor, information cutoff, test period and handling of incomplete observation for that custom study.

Data generation

FCTE synthetic city engine

Data classification

Synthetic

FCTE generation methods and published city/domain checks provide source context. The order defines the final extract and the release-specific checks, documentation and limitations supplied with it.

Reference validation

These results describe the frozen Nairobi reference release ml-01-v1.1-COMMERCIAL_READY. Validation for a prepared custom extract is defined with that order.

This frozen Nairobi reference release only

Reference release modeling notes

Binary target

Use TargetEmployedPostStudySafe; 2,090 evidence-unavailable candidates have a null safe target. The legacy target forces these cases to zero.

Follow-up convention

OutcomeHorizonDays=365 is a minimum follow-up convention, not an upper limit on positive employment outcomes.

Split

Keep the deterministic, outcome-stratified random benchmark split. This reference is not a temporal benchmark.

Prediction-time context

Approved groups use DateOfBirth, QualificationLevel, ProgrammeName, EnrollmentDate and available HouseholdRelationship as of CompletionDate. Exclude identifiers, target evidence and later follow-up from predictors.

Events

The combined event configuration spans citizens in all candidate splits. Filter events to the intended candidate or citizen cohort before split-sensitive analysis.

Reference boundaries

• The frozen reference contains completed tertiary episodes from 1963–2008; it is not a contemporary graduate survey.
• 2,090 candidates have insufficient target evidence. This differs from right-censoring; IsCensored is zero throughout this frozen release.
• Household linkage is available for 4,689 of the 13,105 candidate rows.
• The qualification mix favors DEGREE; synthetic employment rates have not been externally calibrated as Kenyan graduate outcomes.

Known limitations

• Define first employment, target horizon and follow-up before training. Verify job-start dates and outcome completeness; evaluate later cohorts using only information available at prediction time.
• Recorded job starts do not establish complete labour-force outcomes.
• Synthetic associations do not establish real-world employment effects.
• Synthetic records describe generated scenarios; they do not establish observed population prevalence or real-world causal effects.

Catalogue base price

$395 USD

Price basis

Base price per selected city

Availability

Prepared after order

The displayed catalogue amount is a base price per selected city. Your requested dates, population, fields, formats and usage rights determine the agreed scope and final quote. Applicable published discounts and taxes are confirmed with that quote.

Your prepared package

Your order confirms the data files, documentation, evidence, examples and release controls included in the prepared package.

• Agreed data extract
• Schema and field documentation
• Release-specific evidence and limitations
• Agreed loading or analysis examples
• Licence, manifest, checksums and delivery note

SD_RESEARCH_DATASET/
├── data/
│   ├── citizens.parquet
│   ├── education_events.parquet
│   ├── employment_events.parquet
│   └── household_history.parquet
├── tasks/
│   ├── task_definition.yaml
│   ├── train.parquet
│   ├── validation.parquet
│   └── test.parquet
├── evaluation/
│   ├── baseline_model.py
│   ├── metrics.json
│   └── example_notebook.ipynb
├── documentation/
│   ├── README.md
│   ├── DATA_DICTIONARY.csv
│   ├── SCHEMA.md
│   └── METHODOLOGY.md
├── evidence/
│   ├── CERTIFICATION.json
│   ├── VALIDATION_REPORT.pdf
│   └── KNOWN_LIMITATIONS.md
├── MANIFEST.json
├── CHECKSUMS.sha256
└── LICENSE.pdf

Delivery process

Confirm the cities, date range, records, formats, rights and price in writing. The order-specific extract is then prepared and supplied under the agreed payment and delivery conditions.

One secure download package for the agreed release and licensed entity.

Delivery timing, access expiry, formats and prerequisites are confirmed in the accepted order.

Support, refreshes, future releases, hosting and APIs are included only when expressly ordered.

Data Licensing Agreement · 2026-10

A non-exclusive, non-transferable licence for the named customer within the accepted scope and duration.

Permitted use

Internal research, development, testing and analytics within the accepted order.

Model training

Model training, external applications, commercial distribution and access by other legal entities must be expressly addressed in the order.

Redistribution

Raw or substantially reconstructable data cannot be resold, published or redistributed without separate written authorization.

Attribution

Preserve release provenance and applicable third-party notices. Published outputs must identify the data as synthetic.