Campaigns are one of the key components of Cortex Fabric. Cortex Fabric Campaigns empower businesses to make data-driven decisions that result in the best possible outcomes.
Campaigns provide a framework for defining the goals, KPIs, measurements, Data Sources, missions to generate executable models for tracking business goals, KPIs through continuous learning and feedback. (e.g. A Health Care provider creates a Campaign to get more patients to participate in preventative medical services.)
Before reading further make sure you've read the Introduction to Cortex Fabric.
Prerequisites to defining Campaigns:
Campaigns leverage Profiles and profile schemas that use Data Sources which have been pre-configured in the system. You must configure the following in the order presented below.
- Define Connection Secrets
- Define Connections
- Define Data Sources
- Build Profiles
- Register Models
- Build Skills
Campaigns must be defined in the following order:
- Define Cohort or the key actor of the campaign
- Leverage Profiles and profile schemas (from Data Sources) to define cohorts by constructing low-code expressions.
- e.g. Cohort = Male patients over 50 years of age
- Assign Cohort groups that are used to target campaign interventions
- e.g. Cohort groups = members of the cohort who have downloaded the medical provider app, members of the group who have responded to email communications, members of the group who respond only to phone calls
- Define Goals: Measures that are configured for the mission or KPIs (Key Performance Indicators). The goals reflect how the business objectives for the Campaign will be met using data-driven objective values that can be observed. Each goal targets a specific cohort or cohort group.
- e.g. Over the next 6 months there will be a 20% increase in prostate cancer screenings for the cohort (Male patients over 50 years of age)
- Define Missions:
- Compose interventions or action expressions that are designed to meet the Campaign goals. Interventions are comprised of:
- A descriptive name (so SMEs can understand them at a glance)
- The cost of the action measured on a scale of 0-1 that evaluates factors like effort, financial expenditure, time required to implement, or other factors that must be considered in the decision making process.
- Pre-conditions are the conditions that must be in place before an intervention can be undertaken written as logical or boolean expressions. For example a pre-condition of providing in app alerts is that the software must be developed that have this capability.
- Effects represent the desired end-state for the intervention written as a logical or boolean expressions. For example: 5% of the cohort group makes an appointment after receiving 3 notifications.
- Actions (optional for running simulations) are Skills, Agents, or scripts used to implement interventions.
- The intervention definitions are used to generate models under the covers.
- e.g. Male patients over 50 years of age who have downloaded the medical provider app will receive automated yearly reminders on the medical provider app to schedule a prostate cancer screening; reminders will be issued weekly until a screening appointment is scheduled.
- Run and review simulations of the plans (groups of interventions) to analyze the model results, make decisions that retrain the models, and ultimately identify the plan(s) that you want implement to meet the Campaign goals.
- SMEs can reorder plans and ignore or delete them as part of the review/retraining process.
- Deploy the Mission or Campaign.
- Read the Introduction to Agents in Cortex Fabric
- Begin defining Campaigns.