Skip to main content

Custom AI Models

Ziggy can build and integrate custom models that are trained on your own data to perform many tasks to make your operations more efficient. Integrate them with any front end, including Slack, Teams, ChatterBox and your own front end for instant results on an individual record. Perform database operations to update data and systems so your analytics tools can utlilize results across entire datasets.

Use Cases

Typical use cases are

  • Sales & Marketing - Churn predictions, CLV, CAC etc., Next purchase / reorder probability, Deal close probability, Lead scoring & prioritization, Upsell / cross-sell recommendations
  • Customer Support - Ticket triage & routing models - department routing and urgency, Proactive support alerts, Resolution time prediction, Sentiment analysis
  • Operations & Supply Chain - Demand forecasting, Inventory optimization - optimal quantities, reorder points, Predictive maintenance - linked to sensor and maintenance history
  • Finance - Credit risk modeling, Fraud detection, Forecasting & budgeting
  • HR & Talent - Candidate screening, Employee attrition prediction Shift staffing prediction, Training effectiveness modeling
  • Product R&D - Feature adoption prediction, Usage pattern clustering, Quality defect prediction,

Below is a video that shows ChatterBox searching for a customer and then checking various predictive indicators.

Training Models

We can train models for you that you can plug into Ziggy. You can also train your own models and load them into Ziggy.

Bulk Updating

You can create Flows that load any platform or database with current predictive indicators. These values can then appear in your CRM, ERP or other platforms and systems.

Below is an example Flow that does this.

Churn Update

Incremental Updating

Rather than perform a large bulk load every time you want to bring your data up to date, you can trigger a Flow that calculates the indicators on single records whenever the underlying data for those records has changed.

Services

Please contact us if you would like to discuss model training and implementing Flows.