​

• Problem Statement Title- Limited SKU-Level ROAS Tracking: Campaign analysis was restricted to aggregated performance, preventing granular SKU-level insights. This created risks of stockouts and misaligned marketing investments with inventory planning.
• Team Name- BugHustlers
• Team Members- Palak Mundada , Pragya Richa

​

We propose a platform that combines campaign performance data with inventory information to provide SKU-level insights.

• Collect data from multiple ad campaigns (Google Ads, Meta, Amazon, etc.) and inventory/ERP systems.
• Integrate and analyze the data to track SKU-level ROAS, identify mismatches (e.g., high spend with low stock), and provide alerts.
• Visual dashboard shows performance for each SKU, helping marketers make informed decisions.
• Generate actionable recommendations for adjusting campaign budgets and prioritizing products based on stock and past performance.

Goal: Ensure marketing spend is aligned with product availability, avoid stockouts, and optimize overall campaign effectiveness.

Unique Value Proposition:

Our solution connects campaign performance with inventory at the SKU level, delivering real-time insights, predictive demand forecasting, and smart budget reallocation. Unlike existing tools, it aligns ad spend with stock availability to avoid stockouts, reduce waste, and maximize ROI.

Why It Matters: Innovation & Impact

• Provides SKU-level visibility instead of aggregated campaign data.
• Connects marketing spend with actual stock availability.
• Prevents wasted ad budget on low-stock or unavailable products.
• Helps avoid stockouts and lost sales opportunities.
• Supports smarter budget planning with demand forecasts.

​

​

​

Data Collection:

Campaign Data (Google Ads, Meta, Amazon, etc.)

→ SKU-level: Spend, Clicks, Conversions, ROAS Inventory/ERP

→ Stock levels, sales history, replenishment

Data Integration & Analysis:

Merge campaign + inventory data Map SKU

→ performance + stock Compute metrics & detect mismatches (high spend/low stock, low spend/high stock)

​

Analytics Dashboard: SKU-level ROAS tracking Highlight gaps & provide visual insights Alerts for mismatched SKUs

AI Recommendations:

Demand Forecasting → predict SKU-level sales Budget Reallocation → optimize next-day/next-week spend Future SKU Planning → identify top products to promote

Actionable Insights:

Export recommendations to campaign workflows Align spend with demand & stock Prevent stockouts & reduce waste

​

​

Feasibility

• Python provides strong support for data processing, integration, and AI modeling.
• SQL ensures reliable storage, querying, and joining of campaign + inventory data.
• Dashboard tools (Streamlit) make insights easily accessible for marketers.

​

Challenges & Risks

• Limited or inconsistent data from ad/inventory systems.
• Data integration complexity across multiple sources.
• Accuracy of demand forecasting in dynamic markets.

​

Strategies to Overcome

• Start with pilot SKUs, then scale gradually.
• Regularly validate and retrain forecasting models

​

​

Impact:

• Shifts campaign analysis from aggregated to SKU-level.
• Aligns marketing spend with real inventory status.
• Enables data-driven decisions for future planning.

​

Benefits:

• Prevents stockouts and lost sales.
• Reduces wasted ad spend.
• Improves ROI and budget efficiency.
• Gives marketers clear, actionable insights.

​