James Young

I build decision systems for complex domains.

I represent the variables, constraints, and uncertainty that shape an outcome; separate what can be controlled from what cannot; simulate possible actions; and decide on the best feasible next step. Each result improves the next decision.

Decision systems · Interactive AI · Scientific machine learning

Represent → Simulate → Decide → Learn

Evidence and variables feed a decision system; outcomes and new observations improve the next decision.
01 / How it works

Represent the system → Simulate possibilities → Decide what to do → Learn from the result.

Represent the outcome, controllable variables, outside conditions, and real constraints. Then simulate plausible scenarios, decide among feasible actions, and use each result to improve the next choice.

See the method in different domains

Choose a domain. The details change, but the four-step decision loop stays the same.

Decision to improveHow should limited resources be allocated to produce the best result?
What success looks likeMore impact from the resources available
What you can change
where the budget goestimingchannel mixcapacity
What you need to account for
starting conditionsmarket changesaccesspast performance
What limits the choice
total budgetcoverage requirementspolicyavailable capacity
How options are evaluatedEstimate likely outcomes, compare scenarios, and choose the best feasible allocation
Recommended next stepAn allocation plan, expected result, and way to measure what happens
01Represent02Simulate03Decide04Learn

The method is consistent; each implementation is built around the data, constraints, and authority of the people making the decision.

02 / Where it applies

Decision systems. Interactive AI. Scientific machine learning.

Three expressions of the same approach: represent a complex domain clearly, make its possibilities explorable, and turn uncertainty into a better next decision.

01 / Decision systems

Choose the best feasible action, not just the most likely outcome.

Represent what shapes an outcome, simulate realistic options, and decide what to do under real constraints. The technical foundation can include response modeling, causal inference, forecasting, and constrained optimization.

From a one-time prediction to a system that plans, measures, and improves.
02 / Interactive AI

Make AI useful without giving up privacy, control, or trust.

Use local LLMs, governed conversational analytics, and adaptable pipelines to make complex work easier while keeping calculations, evidence, and sensitive data under control.

From a standalone assistant to a private, verifiable decision workflow.
03 / Scientific machine learning

Use limited experiments where they can teach the most.

Combine biological evidence to rank candidates, balance performance with uncertainty, and choose what to test next. The methods include protein language models, multi-omics, comparative genomics, and active learning.

From a ranked prediction to a continuous experiment-and-learning loop.

I work with startups, enterprises, and research institutes, beginning with one important problem and extending what proves useful.

03 / Systems built

Systems built around real choices.

Examples include optimizing resource allocation, working privately with long documents, answering business questions with evidence, adapting analytics to new data, and deciding which experiment to run next.

04 / Evidence

Published research shows the method in a difficult setting.

When every experiment is slow and expensive, choosing what to test next matters.

I combine biological evidence and machine learning to narrow large search spaces, compare promising candidates, show what remains uncertain, and plan the next useful experiment.

Figure 01 / choosing the next experiment
The goal is not only a prediction. It is a better, testable next experiment.