AI-Driven Demand Forecasting for
Transforming distribution with predictive accuracy.
How Cathay LA turned supply chain unpredictability into operational advantage using machine learning — reducing overstock, improving forecast accuracy, and ensuring high-demand items are always in stock.
Overcoming Forecasting Inaccuracy in Manufacturing Operations
Cathay LA, Inc., established in 1979, is a full-line wholesale distributor specializing in food products and kitchen supplies. With an inventory exceeding 20,000 products, including dried goods and kitchenware, they cater to a diverse clientele across various regions.
- Seasonal Variations: Fluctuating demand for certain ingredients during specific times of the year.
- Market Trends: Rapid shifts in consumer preferences impacting product demand.
- Inventory Management: Balancing stock levels to prevent overstocking or stockouts.
Our Process
Steps to Success
Captivix initiated the engagement with an AI Innovation Workshop, aligning Cathay LA’s procurement and IT leaders to uncover pain points and AI opportunities.
Demand forecasting emerged as the top use case to pilot — measurable, data-ready, and ROI-focused. case.
Step 1: Use Case Definition
Captivix led a collaborative workshop with Cathay LA’s key stakeholders to identify automation-ready opportunities.
- Aligned on business goals and operational pain points
- Prioritized use cases by value vs. effort
- Demand forecasting ranked highest in feasibility and strategic impact
🧭 Explore Use Case Prioritization
Step 2: Data Review & Feasibility
Our data engineers analyzed three years of operational history to evaluate readiness.
- Mapped order history, supplier lead times, SKU movement
- Identified seasonal and promotional demand signals
- Resolved data gaps and inconsistencies for reliable model training
🔍 Discover Data Insights
Step 3: Pilot Development
We built and tested a hybrid forecasting model tailored to Cathay LA’s operations.
- Used Facebook Prophet and XGBoost to capture time-series and trend data
- Trained models using SKU-level history, seasonality, and external variables
- Tuned hyperparameters and validated results through backtesting
🛠️ Explore Model Architecture
Step 4: Validation & Demo
The model’s performance was benchmarked against Cathay LA’s manual forecasts.
- Compared outputs over several product categories and time windows
- Delivered a live demo to stakeholders, showing measurable improvements
- Enabled confidence in next-step implementation
📊 View Forecast Accuracy Reports
Step 5: Recommendations for Scaling
We outlined a clear roadmap to move the pilot into production.
- Integration with Cathay LA’s procurement & ERP systems
- Dashboarding and alert features for planners
- Ongoing model refinement and training based on feedback loops
🚀 Explore Scaling Strategy
Tangible Results & Operational Impact
Stronger Forecasts. Leaner Inventory. Smarter Decisions.
Captivix’s AI-driven forecasting pilot delivered measurable improvements for Cathay LA — helping them move from reactive planning to predictive decision-making.
- 22% improvement in forecast accuracy over traditional methods
- 15% reduction in excess inventory for key product categories
- Higher availability of in-demand SKUs during seasonal peaks
- Freed up valuable planning hours by 50% - shifting from spreadsheets to strategic focus
