← Home

APPLIED RESEARCH

A business question.
A complete body of evidence.

Start with the decision and finding. Explore the methods, uncertainty and reproducible source. Browse the research agenda for questions still being investigated.

Find the research behind the decision.

6 of 60 program studies published

4 evaluated synthetic demonstrations

20 industries in the research agenda

3 matching studies

S22 / Sports analytics and baseball

Pitcher development signals that survive the next season

A player-development group needs to distinguish durable pitch quality from small-sample outcomes. Test whether pitch characteristics and context improve forecasts of future swing-and-miss and contact quality beyond recent results.

Awaiting prerequisite

Hierarchical shrinkage; staged probabilities; temporal transfer

Research question and proposed design

Create pitcher/pitch-type season histories from Statcast with explicit tracking-era and field-availability checks. Model swing, miss and contact outcomes in stages, using count, handedness and pitch characteristics available at the relevant stage. Pool sparse pitcher/pitch-type estimates hierarchically and forecast a later season.

Evaluation: Use season-forward holdouts and pitcher-level uncertainty. Compare with prior-season rates and league/pitch-type averages. Report calibration, log loss for binary outcomes, contact-quality error and rank stability across pitch-count thresholds and tracking eras.

Boundary: Observed pitch selection depends on opponent and situation. The study cannot prove that changing pitch mix improves performance, and outcome-stage variables must not leak into pre-pitch forecasts.

No completed finding is claimed for this topic.

Statcast / Baseball Savant ↗

Original dataset selection position 1 within this industry. This is research-selection metadata, not measured model performance.

S23 / Sports analytics and baseball

Baseball strategy as a risk-sensitive decision problem

A baseball strategy analyst wants to quantify when a stolen-base attempt or other base-running choice is worth the risk. Estimate the break-even success probability under different base-out states and scoring environments.

Planned

Markov reward processes; expected utility; partial pooling

Research question and proposed design

Parse Retrosheet events into validated base-out transitions and inning runs. Estimate era-specific run-expectancy tables with shrinkage for sparse states. For a stolen-base decision, compare expected runs after success, failure and no attempt using documented transition assumptions.

Evaluation: Hold out seasons and check run-expectancy calibration and transition validity. Compare pooled and era-specific tables, bootstrap by game, and test rare-state sensitivity. Validate the transition engine with known game-state identities and explicitly distinguish predictive checks from causal policy evaluation.

Boundary: Managers select attempts non-randomly, and observed non-attempts are not randomized controls. Historical decision replay cannot by itself establish that a new strategy would cause more wins.

No completed finding is claimed for this topic.

Retrosheet play-by-play ↗

Original dataset selection position 2 within this industry. This is research-selection metadata, not measured model performance.

S24 / Sports analytics and baseball

Roster allocation under aging and performance uncertainty

A roster planner must allocate a fixed budget across players with uncertain future production. Test whether modeling aging, playing time and downside risk changes a roster relative to ranking last season's statistics.

Planned

Hierarchical aging curves; survivor-bias analysis; portfolio optimization

Research question and proposed design

Build historical player-season panels with era normalization and a prespecified offensive run-value formula. Forecast playing time and offensive production jointly using hierarchical age curves and flexible challengers. Optimize a simplified roster under position and budget constraints, using documented salary-covered seasons or clearly synthetic costs.

Evaluation: Use season-forward holdouts and compare against last-season production and age-neutral forecasts. Report production error, interval coverage and roster-performance distributions in historical replay. Stress retirement/selection assumptions and salary coverage; keep hindsight-optimal comparisons confined to the simulation.

Boundary: Lahman is not a complete current payroll or scouting database. A simplified offensive roster omits defense, injuries and contractual constraints unless explicitly added; it cannot establish current front-office value.

No completed finding is claimed for this topic.

Lahman Baseball Database ↗

Original dataset selection position 3 within this industry. This is research-selection metadata, not measured model performance.

Program progress counts the 60 numbered studies separately from the four original synthetic demonstrations. Planned topics have no public case-study route. Published findings link to evaluated artifacts and research code.