Retailers and consumer goods companies are facing unprecedented times.
We know your primary focus is on the health and safety of your associates, customers and families as you try to adapt your business to rapidly changing dynamics. SAS shares the same focused commitment. We're here to support you with domain experts, data scientists and SAS solutions to help you better comprehend, manage and navigate these uncertain times. As you deal with critical business issues across your organizations, we can help with understanding demand, identifying customer behavior, optimizing your supply chain and beyond.
- Supply Chain Scenario Planning
- Supply Chain Demand Sensing
- Short-Term Product Substitution
- Basket Optimization
- Operationalizing Analytics
End-to-End Supply Chain Scenario Planning
Significant changes in demand patterns and constant market disruptions have many organizations struggling to stabilize end-to-end supply chains. SAS can help you take a comprehensive approach to supply chain planning so you can:
- Provide the best response across your end-to-end supply chain using an optimization model that balances supply chain costs and constraints with meeting sales goals.
- Create consistent, synchronized plans for purchasing, inventory, transportation, sales and manufacturing.
- Run multiple scenarios for demand forecasts based on different recovery expectations, or potential markdown and promotion strategies.
- Capture effects across your entire product portfolio, including regular, perishable and seasonal goods.
Supply Chain Demand Sensing
You're facing the critical challenge of how to predict and plan for significant changes in consumer demand. SAS can help you improve demand sensing decisions across the supply chain – in the short term during the disease outbreak; in the midterm during the recovery period; and in the long term once the pandemic has subsided – with:
- Analytical recommendations for improving demand forecasts across all phases of the pandemic.
- Powerful data preparation capabilities for capturing both internal and external variables in forecast models.
- Machine learning algorithms to quickly assess demand shifts and automatically learn over time as new data is available.
- An iterative framework – from data to analytics to insights – that drives agile, improved forecasting decisions during times of uncertainty.
Short-Term Product Substitution
Across the supply chain, businesses are struggling to maintain high customer in-stock levels due to high demand and limited product availability. SAS can help you understand customer decision-making processes and provide substitution recommendations using advanced analytics and machine learning. With SAS you can:
- Adopt an analytically driven solution that maximizes customer satisfaction in this time of need.
- Establish customer decision trees that will help you understand how a customer chooses an item to buy.
- Use multiple analytically driven decision-making techniques to determine substitution products for like items.
Both online and offline shopping patterns have changed quickly. Basket optimization gives you insights for making data-driven decisions to best tune your inventory mix in a very challenging retail environment. SAS can help you identify which items are being purchased together so you can:
- Create product bundles of what consumers need now.
- Establish the best product placement and facings required.
- Make better product recommendations.
- Quickly make informed promotion decisions.
New challenges require fast answers. To effectively respond to changes, analytics must be agile and adaptable. Analytic models built on historical data may no longer hold up to the changes in consumer behavior and market dynamics. SAS can help you reassess your most mission-critical models and quickly adjust to the new reality by:
- Quickly recalibrating and deploying all your analytic models.
- Automatically retraining models when events dramatically change inputs.
- Maintaining and extending value generated from production models.
- Cataloging and deploying all models built in SAS, open source or from third-party vendors.