Supervised learning describes a class of problems that involves using a model to learn a mapping between input examples and the target variable. Supervised learning algorithms are trained using a labeled dataset and are taught to come to a specific conclusion based on historical data.
Unsupervised learning describes a class of problems that involves using a model to describe or extract relationships in data. Compared to supervised learning, unsupervised learning operates upon only the input data without expected outputs or target variables. Unsupervised learning algorithms ingest unlabeled datasets, look for similarities or patterns in the data and use that information to sort, group, and classify the data without being taught what to look for.
Reinforcement learning describes a class of problems where an agent (the learner) operates in an environment (everything the agent interacts with) and must learn to operate using feedback. The use of an environment means that there is no fixed training dataset, rather a goal or set of goals that an agent is required to achieve, actions they may perform, and feedback about performance toward the goal. The algorithm uses trial and error to determine which actions yield the best outcomes.
- Workforce trends and forecasting
- Recruiting optimization
- Capacity prediction
Consumer Packaged Goods
- Product lifecycle management
- Stock optimization
- Demand forecasting
- Supplier optimization
- Inventory planning and replenishment
- Risk analysis and monitoring
- Clinical and population health management
- Medical imaging insights
- Patient risk identification
Office of Finance
- Planning budgeting, forecasting, and cash flow analysis
- Revenue forecasting
- Fighting fraud, waste, and abuse
- Root cause analysis
- Ticket triage
- Anomaly detection
- Merchandise supply planning