Project contribution

The wider collaboration explored how AI and data analytics could improve inventory, labour, and warehouse operations. My analysis contribution concentrated on finding candidate consolidation opportunities from order, shipment, pallet, postcode, and location data.

Rather than claiming an automated operational decision-maker, the work produced an auditable analysis route that could help practitioners inspect possible pairings before any real-world action.

Data AnalysisGeospatial ReasoningOrder ConsolidationDecision Support

From operational data to reviewable opportunities

1. Prepare

Clean and align order headers, order lines, and geocoded address records.

2. Filter

Apply practical shipment, release, carrier, timing, and pallet-capacity criteria.

3. Compare

Use postcode/geographic proximity and combined-pallet checks to identify candidate pairings.

4. Inspect

Surface results through tables and geographic visualisations for human operational review.

What the analysis showed

The notebook explored order-density patterns, carrier and status distributions, potential consolidation conditions, and location-based comparisons. It also made an important analytical result visible: stringent filtering can leave no candidates, so assumptions must be inspected and adjusted rather than treating an empty result as a business conclusion.

This work informed my interest in responsible AI applications: data work is useful when the pipeline, criteria, and uncertainty are visible to the people making the decision.

Data and confidentiality

This portfolio deliberately excludes underlying records, map coordinates, customer identifiers, operational thresholds, and detailed results. The page describes the analytical approach only, respecting the project’s commercial and data-governance context.