Food Import Logistics & Supply Chain Management System
The company operated warehouses across 3 countries, serving regional customers with a mixed fleet of full-size articulated trucks for inter-warehouse and large customer deliveries, and smaller vans for last-mile local distribution. Its network was highly complex: demand fluctuated sharply by season and customer, supply chains crossed multiple borders, and product shelf life imposed strict stock-rotation requirements. Yet operations were still managed largely manually, with route planning done by phone, inventory tracked in country-specific spreadsheets, and demand forecasts based on sales managers' gut feel.
The result was poor route loading, spoilage caused by weak stock rotation, and excess warehouse inventory tying up capital.
Solution
We built an end-to-end logistics and supply chain platform that improved planning, execution, and financial visibility across the entire operation. The solution combined AI-driven demand forecasting with optimized routing for full-size trucks and last-mile vans, including multi-stop truckloads across 2–3 locations, while warehouse inventory and spoilage tracking helped reduce waste and improve stock control. A comprehensive financial management layer tied together costs and revenues, giving the business a clearer view of margins and overall performance.
The platform also streamlined the full supply chain cycle, from forecasting customer orders for the upcoming week to generating invoices and calculating margins. Customer order pattern analysis highlighted ordering deviations to surface early churn risks and upsell opportunities, while carrier performance tracking provided insights into on-time delivery, damage, and cost per kilometer to support more informed procurement negotiations and stronger carrier selection.
Key Achievements
-17%
Total transport cost achieved through route optimization and load consolidation
-25%
Reduction in product spoilage and waste losses via FEFO rules and improved forecasting
-20%
Reduction in overall warehouse inventory value through AI-driven replenishment planning
Stack & Architecture
Frontend
All UI for the System
React + TypeScript
Backend
Business logic, routing engine, forecasting model serving
Python / FastAPI
AI/ML
Demand forecasting + Google OR-Tools for VRP optimization
Prophet + OR-Tools
Database
Single source and data storage
PostgreSQL
Maps
Geocoding, distance matrix, live traffic-adjusted ETAs
Google Maps Platform
Infrastructure
Hosted SaaS infrastructure
AWS
Key Features
AI Demand Analysis & Forecasting
Machine learning forecasts demand per customer and SKU (eggs by size/grade, flour by type, oil by pack size) using order history, seasonality, customer growth trends, and external signals such as local events and holidays. This helps reduce stockouts, cut waste, and support smarter purchasing with a daily 14-day rolling forecast.
Full-Size Truck Route Optimization
Optimizes articulated truck loads for deliveries between central warehouses and large customers. Streamline multi-stop routing across 2–3 locations while accounting for time windows, driver hour regulations, and product compatibility constraints.
Last-Mile Van Routing
Daily route optimization for local delivery vans serving smaller customers from regional warehouses. It accounts for customer time windows, vehicle capacity, and driver familiarity scoring, while enabling dynamic re-routing for failed or changed orders and Google Maps integration for live traffic ETAs. The result is more efficient daily planning, fewer missed windows, better use of van capacity, and faster responses when routes change — helping local delivery operators improve reliability and service quality.
Warehouse & Inventory Management
Real-time stock visibility across all warehouses by product, lot, arrival date, and expiry date helps food and perishable goods distributors reduce spoilage, improve order accuracy, and move inventory before it expires. Enforcing FEFO (First Expired First Out) picking rules ensures the oldest stock ships first, lowering write-offs and supporting better product freshness for customers. Inter-warehouse transfer recommendations help teams rebalance stock levels proactively, avoid local overstock or stockouts, and improve service levels across the network.
Spoilage & Loss Tracking
Logs loss events (egg breakage, flour moisture damage, oil oxidation, returns) categorized by cause, location, and responsible party to reduce waste, speed supplier reimbursements, and improve accountability. Automatically generates supplier claims for transit damage and flags abnormal loss costs for operational review.
Financial Management
Calculates total landed cost per shipment, including product cost, customs, freight, warehouse handling, and last-mile delivery, so teams can see true margin impact at a glance. Tracks real-time gross margins by SKU, customer, and country alongside accounts payable and accounts receivable to improve pricing decisions, profitability visibility, and operational control.
The company transitioned from manual, The challenge was fragmented spreadsheets and disconnected operations across warehouses in three countries. The solution was to build a unified digital ecosystem, automate route planning for the mixed fleet, and deploy AI-driven demand forecasting. The business impact was maximized truck load capacity, reduced product spoilage within strict shelf-life constraints, eliminated excess inventory, unlocked working capital, and streamlined distribution.
