Decision Intelligence
Which store configuration makes sense?
Our team audited and cleaned a business dataset, built an interactive management dashboard, tested margin scenarios and used optimisation to support a location and store configuration recommendation.
A dashboard, 60% to 70% margin scenarios and an optimisation recommendation.
Explore the evidence ↓01 · Decision
Our team defined the decision before selecting a method.
Which scenario and store configuration best supported the management objective, and how could the tradeoffs be made clear to regional directors?
A recommendation is only as useful as the assumptions behind it.
A dashboard could describe the business, but the assignment also required a choice about location and store configuration. Our team connected data checking, margin scenarios and optimisation so the recommendation could be examined rather than simply accepted.
The judgement in the work
Testing margins from 60% to 70% made the assumptions visible. The value of the model was in exposing the decision logic, not in claiming that an assessed recommendation had already delivered a commercial result.
02 · Approach
Our team organised the analysis in the following sequence.
- 01
Our team systematically audited missing values, outliers and inconsistencies, then applied appropriate cleaning.
- 02
We built a management dashboard with KPIs, charts, slicers, dynamic formulas and drill down.
- 03
We modelled margin scenarios from 60% to 70% using simulation and sensitivity analysis.
- 04
We used optimisation to compare location and store configuration choices before making a recommendation.
03 · Evidence
The results support the following interpretation.
Assessor feedback confirmed systematic data checking, appropriate cleaning, a useful interactive dashboard, a correct optimisation model and a justified recommendation. The submission received a provisional group mark of 75.
Scope: assessed four person team model; the project produced a recommendation rather than realised commercial impact.
Explore the model in 3D
Conceptual decision workflow from the team project. Three branches illustrate comparison, not the actual scenario count, calculated values or a proven optimal outcome.
Read the supporting case ↗04 · Decision implications
Our team translated the analysis into practical next steps.
- Put the management decision at the centre of the dashboard rather than treating every metric as equally important.
- Use scenarios to make the effect of changing assumptions visible before committing to a recommendation.
- Keep the model logic transparent enough for a decision maker to challenge and understand.
05 · Limits
The evidence has defined limits.
The work was an assessed decision model rather than a production deployment, so it demonstrates method, not realised revenue or margin.
06 · Next iteration
Our team would strengthen the next iteration.
Add external evidence and decision relevant KPIs such as sales per square metre, then publish a clearer formula and sensitivity audit.
07 · Attribution
I distinguish my contribution from the complete project output.
There were no fixed specialist roles. We divided the work as evenly as possible across four people, and every member covered the complete assignment. The dashboard, cleaning, scenarios and optimisation are therefore described as our team’s work.
Toolkit