AI in retail & consumer goods
Forecast and manage demand, enhance supply chain performance, and boost shopper profitability using AI from the leader in analytics.
AI use cases for retail & consumer goods
Accelerate innovation and deliver bottom-line performance with AI to automate labor-intensive supply chain processes, improve operational efficiency and deliver better customer experiences. Get more done faster with AI solutions from SAS.
Simplify and accelerate operational planning
Accelerate daily operational planning with AI-driven exception management, root-cause investigation, scenario analysis and guided recommendations that help planners take action faster.
The value of this solution:
- Faster innovation.
- Trustworthy, explainable results.
- Better outcomes.
AI techniques used in this solution:
- Conversational AI capabilities powered by large language models (LLMs) and natural language interfaces that help users access analytics, investigate operational issues and explore planning scenarios using natural language.
How AI helps:
- Faster innovation: Chatbot capabilities provide faster access to analytics, identifying and responding to voice prompts with context-aware, on-demand insights. This results in better planning, decisions and outcomes without requiring deep supply chain expertise.
The AI models provide:
- On-demand analytics that reduces user-based query workloads.
- Automated business rules that enable improved, timely decision making.
- Easy interaction with analytics using natural written language.
Predict product demand more accurately
Automate forecasting, freeing up time-strapped demand planners from looking at hundreds or even thousands of forecasts. The solution allows planning at greater frequency, more accurately predicting short-term demand fluctuations while reducing human intervention.
The value of this solution:
- Faster decision making.
- Highly accurate forecasting.
- Inventory optimization.
AI techniques used in this solution:
- Machine learning-assisted forecasts predict the accuracy of system-generated forecasts and alert planners of the need for adjustment.
How AI helps:
- Alerts demand planners to forecast accuracy variances and advises on supply adjustments. This saves time by automatically suggesting explainable, trackable and accountable overrides, freeing planners from manually reviewing numerous forecasts.
The AI models provide:
- Rapidly analyzes consumer demand signals at detailed product levels, down to weekly or daily, to identify unaligned demand plans.
- Automates tasks and alerts planners to potential forecast misses early, reducing the time spent on sell-thru evaluations.
A major global CPG company improved the overall accuracy of human forecast intervention by between 6.3% and 9.2% for product demand predictions using machine learning-assisted demand planning techniques.
Optimize warehouse utilization and inventory flow
Enable warehouse and supply chain teams to better understand warehouse capacity, utilization and inventory flow. SAS analytics helps organizations monitor operational activity, evaluate utilization scenarios and identify opportunities to improve warehouse efficiency and inventory placement decisions.
The value of this solution:
- Maximized operational efficiency.
- Better outcomes from supply chain management decisions.
- Cost savings.
AI techniques used in this solution:
- Conversational AI capabilities combined with analytics, optimization and natural language interfaces help users explore warehouse utilization data, evaluate operational scenarios and identify opportunities for improvement.
- Provide grounded, explainable insights using enterprise data, analytics and governed AI processes.
How AI helps:
- Faster Innovation: Conversational interfaces provide faster access to analytics and operational insights, helping users investigate warehouse performance, utilization trends and inventory movement more efficiently.
The AI models provide:
- Supports warehouse and inventory decisions by combining analytics, optimization and scenario evaluation to help users understand the potential impact of changing demand patterns, inventory levels and utilization targets.
The AI chatbot helps warehouse specialists at a global food and beverage company use voice prompts to optimize capacity based on demand and shipments.
Take advantage of AI-powered pricing & promotion strategy
Use AI to analyze situational factors, including market trends, customer behavior and product life cycles, to gain optimal pricing and promotion strategies for retail products across channels.
The value of this solution:
- Increased revenue.
- Better customer experience.
AI techniques used in this solution:
- The SAS assistant is powered by a GenAI agent trained on subject-specific LLMs to recommend pricing strategies.
How AI helps:
- Provides suggestions on pricing actions to achieve the target margins based on the product costs, shelf-life/seasonality, promotional lift and other constraints.
- Informs procurement, allocation and replenishment decisions at multiple levels of the product hierarchy.
The AI models provide:
- Enables easy interaction with analytics and improved pricing and supply chain decision making for faster decisions that lead to greater revenue and margins.
- Pricing process optimization for greater efficiency and productivity.
Improve insights and decisions with synthetic data
Empower marketers with generated synthetic data to complete data that reflects the diversity of their customer base. Synthetic data is based on the same features and characteristics as real data, enabling you to protect sensitive information and avoid security issues while enhancing data quality and producing more effective models.
The value of this solution:
- Increased revenue and market share.
- Accelerated innovation.
- Greater productivity.
- Maximized operational efficiency.
AI techniques used in this solution:
- Synthetic data cost-effectively fills in data gaps, including for specific customer subsegments or irregular issues/events in the network and protects sensitive private or proprietary data.
How AI helps:
- Save money on the high costs of data collection.
- Improve precision in predictions, reducing errors in risk assessment while retaining explainability for decisions.
- Streamline analytics, accelerating data processing and decision making.
- Create more effective models with improved data quality.
- Optimize production processes for greater efficiency and productivity.
- Increase data monetization safely, avoiding legal risk.
The AI models provide:
- Trustworthy, simplified data augmentation and generation.
- More complete data that can improve the usefulness of the data set.
- Better protection of sensitive data.
Hyper-personalize ads at scale
Put the power of personalized advertising in your brand’s hands. This ad delivery solution works in your ecosystem and enables effective ad personalization based on your marketing and advertising data.
The value of this solution:
- Better customer experience.
- Increased revenue.
- Scalability.
- Regulatory compliance.
AI techniques used in this solution:
- Machine learning enables you to manage customers, business rules and analytics in a converged solution.
How AI helps:
- Make ad content decisions based on real-time testing and live results.
- Create a positive feedback loop that encourages iteration and improvement through personalized advertising.
- Improve advertising efficiencies by streamlining the ad-serving process, reducing the need for manual data movement.
- Capitalize on the zero-, first- and second-party data and audience information you need without the cost and risk associated with data movement and duplication.
- Increase ad personalization and targeted ad precision with information on customer behaviors, interests and demographics that resides outside of traditional advertising solutions.
- Create more robust audiences using data from multiple platforms, resulting in better performance and ROI.
- Maintain control over your advertising delivery engine so you can understand which data and analytical models you're using to deliver personalized advertising on your owned and operated channels.
The AI models provide:
- Automation of delivery, user data flows and campaign optimization.
- A deep understanding of viewer preferences for highly personalized campaigns.
- Highly-targeted, real-time ad decisioning on an immense scale.
Improve your call center productivity
Manage your call center’s schedule, more accurately forecast incoming calls, streamline correspondence and complaints processes and automate conversation transcript analysis. Use insights from the transcripts and even social media to improve communication and prevent customer churn.
The value of this solution:
- Cost savings.
- Better customer experience and lower churn.
- Greater productivity.
- Maximized operational efficiency.
AI techniques used in this solution:
- Machine learning, optimization and NLP enable you to create highly accurate forecasts, analyze communication, make operational improvements and improve customer service.
- Use LLMs to understand and update model metadata.
- Analytical capabilities like forecasting, machine learning and deep learning models, and other tools may be easily combined with LLMs and GenAI in business processes to provide actual value in automation and ease of use.
How AI helps:
- Create a more consistent customer experience with increased personalization.
- Upskill employees faster.
- Reduce complaint handling time and associated costs.
- Increase call center productivity and efficiency.
- Lower overhead costs.
- Prepare schedules faster, accommodate ad-hoc changes and generate a new schedule quickly and accurately.
- Enable better cooperation with employees and adapt quickly to employees' flexible scheduling needs.
- Ensure the best possible KPIs.
- Improve sales by including Next Best Offer/Next Best Action (NBO/NBA), along with anti-churn tasks.
The AI models provide:
- Improved resources and skill sets based on the number of call-center queues, opening hours, available shifts and service line agreements (SLAs) to fulfill.
- Automation and greater efficiencies for improved productivity.
- Accelerated schedule preparation, plus quick and accurate rescheduling.
- Improved KPIs.
AI in retail: Frequently asked questions
What AI use cases does SAS support for retail and consumer goods?
SAS outlines seven main AI use cases for retail and CPG: simplifying and accelerating operational planning, predicting product demand more accurately, optimizing warehouse utilization and inventory flow, AI-powered pricing and promotion strategy, improving insights and decisions with synthetic data, hyper-personalizing ads at scale and improving call center productivity.
How does AI simplify operational planning in retail?
SAS uses conversational AI capabilities powered by LLMs and natural language interfaces that help users access analytics, investigate operational issues and explore planning scenarios using natural language. Automate daily operational planning tasks such as exception alerting, root cause analysis, what-if scenario analysis and next-best-action recommendations, without requiring deep supply chain expertise.
How much more accurate does SAS AI make demand forecasting?
SAS reports that a major global CPG company improved the overall accuracy of human forecast intervention by between 6.3% and 9.2% for product demand predictions using machine learning-assisted demand planning.
How does SAS AI help optimize warehouse utilization and inventory flow?
SAS combines conversational AI with analytics and optimization to help warehouse and supply chain teams explore capacity, utilization and inventory data using natural language. Users can evaluate operational scenarios and see the potential impact of changing demand, inventory levels or utilization targets – with grounded, explainable insights from enterprise data. The result: faster access to operational insights, better supply chain decisions and lower costs.
Can SAS AI help set pricing and promotion strategy in retail?
Yes. SAS offers a GenAI agent trained on subject-specific LLMs to recommend pricing actions that hit target margins based on product costs, shelf life or seasonality, promotional lift and other constraints, while also informing procurement, allocation and replenishment decisions across the product hierarchy.
What is synthetic data used for in retail?
Synthetic data lets retailers fill gaps in customer data, including for specific subsegments or irregular events, using data with the same features and characteristics as real data. This protects sensitive or proprietary information while improving data quality and model performance, without the cost of additional data collection.
How can SAS AI improve retail call center productivity?
SAS combines machine learning, optimization and NLP to forecast incoming call volume, streamline correspondence and complaints and automate analysis of conversation transcripts (and even social media). This helps companies with faster, more accurate scheduling, reduced complaint-handling time and better customer retention through next-best-offer/next-best-action recommendations.