ReloPortal Redesign
Phase 1: Scope and Research
ReloPortal Redesign
Phase 1: Scope and Research
ReloPortal Redesign
Phase 1: Scope and Research
Home Depot | Pricing & Merchandising Decision Case Study
Designing AI-driven pricing decision systems that translate complex merchandising logic into operational tools
Enabling merchandising teams to interpret pricing dynamics with greater confidence across internal retail systems.
The Home Depot | Principal Product Designer | Enterprise Retail, Pricing & Merchandising |
Platforms: Web, Internal Enterprise Tools
Overview
Designed an AI-assisted pricing platform that translated machine learning outputs and complex merchandising data into clear,
actionable pricing decisions. Merchandising teams were managing thousands of SKUs across categories, requiring them
to interpret inconsistent data signals, pricing rules, and competitive inputs. Existing tools surfaced data but did not support decision-making.
The platform introduced structured decision workflows that aligned model outputs, business constraints, and user intent, enabling teams
to evaluate pricing scenarios, understand tradeoffs, and act with confidence.
Role & Leadership
Led product design for enterprise pricing systems used by merchandising and pricing teams to analyze, model, and execute pricing strategies.
Partnered with Product, Engineering, and Data Science to align experience with system behavior, pricing logic, and operational workflows. Defined interaction models and decision frameworks that translated complex system inputs into usable, scalable tools.
The Challenge
Merchandising teams lacked clear visibility into pricing dynamics across categories.
Data was fragmented, signals were inconsistent, and tools required heavy interpretation.
The challenge was not just accessing data, but enabling confident decision-making, connecting pricing strategy to execution
while maintaining clarity across complex retail environments.
Decision System Design
The platform was designed as a decision-support system that translated pricing logic into structured workflows.
Model outputs, pricing rules, and competitive signals were transformed into interpretable decision pathways,
allowing users to evaluate options, understand tradeoffs, and take action. Interaction models reduced cognitive load
while maintaining transparency into how recommendations were generated.
Key Decision Frameworks & System Models
These frameworks provided a consistent structure for evaluating pricing decisions across merchandising teams.
This artifact shows how I set shared language and scope early, aligning stakeholders around outcomes,
constraints, and the role AI should play before any screen-level design began.
This canvas framed the effort in a way cross-functional partners could rally around.
It clarified what “price recommendation” and “optimization” meant in human terms, identified who the work served,
and established what must remain explicit due to enterprise constraints (pricing risk, volatility, and accountability).
Value Hierarchy - Pricing
Structured pricing pathways supported scenario-based evaluation
and improved coordination across merchandising functions.
Defined a value hierarchy connecting business objectives, pricing strategies, and execution constraints.
This structure ensured pricing decisions were grounded in margin, growth, and competitive positioning, while maintaining clarity and accountability across merchandising workflows.
Pricing Decision Intelligence Model
Insights were surfaced through consolidated summaries that supported strategic pricing reviews.
Created a decision model that translated complex pricing inputs into guided workflows.
The system surfaced key signals, recommended actions, and expected outcomes, helping teams move from analysis to decision-making with greater speed and confidence.
Five Pillars
Process flows translated pricing inputs into interpretable decision pathways.
Established core principles guiding how pricing decisions should be structured, communicated, and executed.
These pillars ensured consistency across workflows, reinforced transparency in recommendations,
and aligned decision-making across teams and systems.
Visual Strategy Mapping
Visual mapping connected pricing intelligence to merchandising decision journeys.
Mapped end-to-end pricing workflows, connecting data signals, model outputs, and user actions into a unified decision journey. This provided clarity across the system, ensuring users could move from insight to action
without losing context or confidence.
Impact & Outcomes
The platform enabled merchandising teams to move from fragmented data analysis to structured, decision-driven workflows.
Teams gained clearer visibility into pricing dynamics, improved alignment between strategy and execution,
and increased confidence in acting on AI-generated recommendations.
The result was faster decision-making, reduced cognitive load, and more consistent pricing outcomes
across large-scale retail operations. Teams shifted from reactive pricing analysis to proactive, decision-driven workflows.