Schoolhouse

Specialty centers · Applied ML Systems

Twenty-five printable capstone briefs you can assign this term

Free Applied ML Systems briefs built around Virginia and Henrico public data. Students pick a scoped question, work the data, and write what the model does and does not support. You run two checkpoints and score. Every brief has its own PDF, and all twenty-five are in the bank PDF. No account. No student data leaves your school.

Read the worked sample (DS-04)Download DS-02 PDFDownload full bank PDF

Next steps

  1. Download or read the worked sample (DS-04).
  2. Share with one teacher and pick a brief for this term.
  3. If your center already has a project slot this year, answer one question — not a purchase.

How to run one

  • Students choose the brief. You do not invent twenty-five projects.
  • Two scheduled checkpoints. Score with the six questions below.
  • Mentors are advisory and optional. If you cannot staff one, run the brief with a teacher and a rubric.
  • These briefs do not produce verified computer-science credit. No AI or CS course in Virginia does.
  1. R1. Is the question answerable with this data, and did the student narrow it?
  2. R2. Where did the data come from, what changed, and can someone else reproduce it?
  3. R3. Is there an honest baseline, and does the model beat it for a named reason?
  4. R4. Did they measure what matters, look at what failed, and quantify uncertainty?
  5. R5. Can a non-specialist read the result and not overclaim it?
  6. R6. Who is affected, how does this fail, and what did the student decline to claim?

Free now: this brief bank, how to run, and the scoring questions on this page. Other specialty tracks also have live banks today.

Capstone Pack (optional): printable rubric kit, five C's evidence template, mentor briefing, and judge scorecard — when you want a defensible center run, not just a class assignment. How Capstone Pack fits the center program.

Not an IT / data-science center?

Same spine. Different capstone track.

Applied ML is the worked example of the format. Every other specialty pathway has a live bank too, so you can judge fit for your center.

All 13 tracks →

Featured briefs

DS-04 · worked sample

What actually predicts chronic absenteeism?

Which school-level factors actually associate with chronic absenteeism — and which of the ones people assume matter do not survive controls?

Before assigning: open the VDOE School Quality Profiles download page in a browser and confirm the Chronic Absenteeism export is still there. Automated link checks sometimes fail on this portal even when the file is fine.

Read DS-04Download PDF

DS-02

Is the property assessment fair across the county?

Assessment regressivity — where lower-value homes are assessed at a higher fraction of market value than higher-value homes — is measurable. Is it present here?

Uses Henrico open assessment data and Census ACS — public sources, live when last checked.

Read DS-02Download PDF

More briefs

Twenty-three more scoped questions. Each is a full brief on its page and is included in the bank PDF above, with its own single-brief PDF too.

  1. DS-01 · PDFPredicting when the bus is actually comingHow far apart are they, and can you predict the gap for a given route, stop, and time of day better than assuming the bus is on time?
  2. DS-03 · PDFTomorrow's air, from today's air and weatherCan you predict tomorrow's peak PM2.5 at a Richmond-area monitor better than "same as today"?
  3. DS-05 · PDFForecasting the JamesGiven upstream gauge readings and rainfall, can you predict James River stage at Richmond 12 hours ahead well enough to be useful to someone deciding whether to move a boat?
  4. DS-06 · PDFWhere a delay at RIC actually comes fromUsing tail numbers, can you quantify how much of a departure delay at Richmond International is inherited rather than locally caused?
  5. DS-07 · PDFWho can actually reach a grocery store?Using road networks and transit, how different does access look when measured by travel time — and for whom does the answer change most?
  6. DS-08 · PDFBroadband, income, and what the map does not showDoes reported availability match what the ACS says about actual household subscription — and where is the gap largest?
  7. DS-09 · PDFCrash severity, and the limits of predictionGiven crash circumstances — road type, lighting, weather, restraint use — how well can severity be predicted, and what happens to the model's usefulness when you remove the variables a policymaker cannot change?
  8. DS-10 · PDFForecasting the gridCan you forecast next-day hourly electricity demand for the PJM region better than a "same hour last week" baseline, and where does the model break?
  9. DS-11 · PDFThe hot side of the streetWithin Richmond, how much of surface temperature variation is explained by canopy — and does the pattern line up with historical redlining boundaries?
  10. DS-12 · PDFA housing model that knows what it does not knowBuild a home-value model for a Richmond-area ZIP set. Then do the part that matters: find the segments where it is systematically wrong, and decide whether it should be used at all.
  11. DS-13 · PDFAre the birds moving north?Pick a species with dense occurrence records. Has the centroid or northern edge of its observed range shifted over the last thirty years — and how much of any apparent shift is just more people with phones?
  12. DS-14 · PDFA recommender that is not just popularBuild a movie recommender. Then measure what it does to the tail: does it surface anything a user would not have found anyway, and what happens to a brand-new user or a brand-new item?
  13. DS-15 · PDFMessy labels, real productsCan you predict a product's nutrition grade from its ingredient text — and what does the failure pattern tell you about who contributes data?
  14. DS-16 · PDFWhat the coverage emphasizesTake one well-defined local or regional news topic over a fixed window. Do outlets differ measurably in what they emphasize — which entities and themes co-occur — and can you show it without claiming to have measured bias?
  15. DS-17 · PDFWhat a job posting actually asks forUsing occupational skill data, map how skill requirements differ across occupations in one Virginia industry — and identify which skills are shared across occupations that people think of as unrelated.
  16. DS-18 · PDFPredicting the health inspectionUsing restaurant inspection history, can you predict which establishments will fail their next inspection — and should a health department actually use such a model to target visits?
  17. DS-19 · PDFFifteen minutes to a parkWhat fraction of Henrico residents live within a 15-minute walk of a public park or library, and how does that fraction differ across income and age groups?
  18. DS-20 · PDFSmall-area population forecastingForecast tract-level population five years out for a Richmond-area county. Then do the real work: quantify how wrong such forecasts typically are, by backtesting against tracts you already know the answer for.
  19. DS-21 · PDFWhat a storm costsUsing historical storm event records, model reported property damage from event characteristics — and then confront how badly damage reporting behaves as a target variable.
  20. DS-22 · PDFPredicting graduation, and deciding not toUsing institution-level higher-education data, model graduation rates from institutional characteristics. Then answer the harder question: what would go wrong if an admissions office used this model on individuals?
  21. DS-23 · PDFIs the water safe, and how would you know?Using water-quality monitoring records for a Virginia watershed, classify whether a sample exceeds a standard — and quantify how much monitoring gaps limit what can be said.
  22. DS-24 · PDFHow many cars, really?Can you estimate volume on unmonitored segments from road characteristics and network position — and how confident should anyone be in those estimates?
  23. DS-25 · PDFBreak a published resultChoose a published model or benchmark result on a classic public dataset. Reproduce it. Then find the conditions under which it fails, and write the model card its authors did not.

After you try a brief

Does your center already have a place for this work?

One question, not a purchase. Helps us know whether a free bank is enough or whether Capstone Pack instruments matter. Product or source issues stay on this page under Feedback.

Answer one questionTalk about Capstone PackRequest a quote

All 13 tracks

Full brief banks for every specialty track are live today. See the specialty-centers overview for the pathway map.

Download the full bank PDFSee all 13 tracks

Feedback

Source moved? Something unclear? Tell us here — you do not have to leave an email.

Optional email gets a confirmation. Please do not include student names.