🍎 Supply Chain Quality Control for Perishable Items

Supply Chain Quality Control for Perishable Items is a data visualization and analytics project focused on optimizing the shelf life, pricing, and transportation of perishable goods — specifically apples — within the supply chain.
The project explores how data-driven decisions can minimize food waste, enhance delivery efficiency, and ensure top-quality produce reaches customers at the right time and cost.

🚀 Overview

Perishable products like fruits pose major challenges in logistics, quality control, and sustainability.
This project analyzes attributes such as sweetness, crunchiness, ripeness, juiciness, and acidity to determine overall fruit quality. By integrating this with shelf life, transportation days, and distance, it provides insights into:

• How to match product quality with optimal delivery routes.

• Which suppliers offer the best balance between price, quality, and distance.

• How to reduce waste by aligning shelf life with transportation timelines.

🎯 Project Goals

• Optimize delivery times and provider selection based on product quality.

• Maximize shelf life utilization for better quality management and reduced spoilage.

• Develop pricing strategies that reflect product quality and transport costs.

• Visualize supply chain relationships for actionable insights on efficiency and quality control.

🧩 Data Exploration

The dataset focuses on multiple quality indicators for apples and includes merged data on transportation and shelf life. Key steps include:

• Dataset Quality Check: Examined attributes like size, sweetness, and ripeness to assess product quality distribution.

• Assigning Quality Levels: Classified apples as Good, Better, or Best based on key physical and sensory traits.

• Merging Supply Data: Integrated transport times, distances, and costs per destination to create a unified dataset.

• Insights Generation: Identified optimal supplier-to-store routes based on quality levels, transport days, and shelf life thresholds.

📊 Data Analysis

Conducted using Python (Google Colab) for data processing and visualization. Key analyses include:

• Supplier dominance by state and quality category.

• Shelf-life-based transportation optimization.

• Distance and provider performance comparison.

• Best supplier identification based on price, quality, and proximity.

• Analysis of low-shelf-life vs. long-distance product viability.

📈 Data Visualization

Created multiple visualizations to interpret complex supply relationships:

• Distribution of Quality Levels: Visualized the proportion of Good, Better, and Best apples.

• Average Distance vs. Quality Levels: Showed how product quality impacts transport range.

• Attribute Comparison: Analyzed juiciness, crunchiness, size, and sweetness against quality tiers.

• Shelf Life by Quality: Displayed how higher-quality produce sustains longer shelf life.

• Price Heat Maps: Compared supplier pricing across states for optimal sourcing.

• Supplier Distance Optimization: Visualized the effect of choosing nearest best-quality suppliers to reduce waste.

⚙️ Tech Stack

🧠 Evaluation Metrics

• Data Visualization Effectiveness: Ability of visuals to reflect realistic patterns and insights.

• Insight Discovery Rate: Number and quality of actionable findings from the dataset.

🌱 Future Scope

• Add probability of damage during transport to adjust price dynamically.

• Track year-round supplier quality consistency for long-term contracts.

• Include automated quality enhancement steps based on transport conditions.

• Expand datasets to include multiple fruits and regional logistics.

• Integrate with real-time IoT sensor data for dynamic quality monitoring.