Selected work · Applied analytics

Applied Analytics Casework

Selected analytical casework spanning preference research, predictive modeling, optimization, recommendation systems, and simulation.

Analytical casework

The challenge

A model matters only when it sharpens the decision.

Leaders often have a consequential question but not a dependable way to connect fragmented data, uncertain assumptions, and competing tradeoffs to a decision they can defend.

The response

Use the method the question requires.

This selected body of analytical work informs Axlete’s approach: structure the decision, choose fit-for-purpose methods, compare alternatives, and make the decision artifact inspectable. The public atlas preserves those decision structures. The separate capacity exercise below uses a constructed scenario data, not an original client result.

Decision modelingMachine learningOptimization & simulation

Casework atlas

The question is only the beginning.

Select a case to inspect the evidence structure, analytical method, and decision artifact. Nothing advances until the visitor asks the next question.

Atlas · AA-01Six decision structuresSanitized public casework
Preference · configuration · simulation

See which tradeoffs can sustain a coherent offer.

Preference work connects what people choose to the configuration decisions a product team can actually make. Competing offers remain visible long enough to compare tradeoffs rather than collapsing too early into one answer.

  1. 01 · Question

    Which combination of safety, autonomy, connectivity, energy, and comfort should shape a new mobility offer?

  2. 02 · Evidence structure

    Attribute levels, respondent choices, segment definitions, and candidate offer configurations.

  3. 03 · Method
    • Conjoint analysis
    • Customer segmentation
    • Choice simulation
  4. 04 · Decision artifact

    Offer-configuration comparison with a simulated market-choice readout.

About this example

Illustrative decision structure for comparing product configurations, preference segments, and offer tradeoffs.

Public edition

Applied analytics · Inspectable numerical exercise

The constraint changes the answer.

Explore one capacity decision behind the atlas. This illustrative numerical exercise demonstrates how capacity, demand, and objectives shape an allocation.

Interactive example · Demonstration dataCapacity fixture CA-01

6 A units. 3 B units.

Selected from every feasible whole-unit allocation under the capacity and demand constraints. The objective is the largest contribution.

Contribution$690
Completed units9
Hours used / available24 / 24
Unused hours0
AVAILABLE CAPACITY · 24 HA · 6 × 3 H = 18 HB · 3 × 2 H = 6 HUNALLOCATED · 0 H
Inspect the fixture, objective & calculation

Constructed scenario dated October 1, 2026. Product A: 3 hours/unit, $90 contribution/unit, demand cap 6. Product B: 2 hours/unit, $50 contribution/unit, demand cap 8. Both quantities must be nonnegative integers.

Constraint: 3A + 2B ≤ 24; 0 ≤ A ≤ 6; 0 ≤ B ≤ 8. Contribution = 90A + 50B. Completed units = A + B. The model enumerates all feasible pairs; ties in unit volume prefer higher contribution. Remaining ties retain the first enumerated pair.

Selected calculation: 90 × 6 + 50 × 3 = $690. The demonstration model excludes setup costs, sequencing, uncertainty, demand estimation, and inventory. Contribution is not revenue or net profit.

Decision artifact: a feasible allocation with its objective, constraints, unused capacity, and assumptions attached.

Work with Axlete

Bring this capability to your organization.

Connect the methods and systems shown here to your next implementation.

Decision Brief

A clear decision starts with a bounded question.

A written brief, source register, explicit assumptions, recommendations, and supporting analysis agreed in scope.

Indicative: 10 business days after the question, scope, and source access are agreed. Fixed fee agreed before work begins.

Request the brief