KPI & Optimization

KPI-Based Optimization empowers business leaders to define and optimize models based on anything — and everything — that is measurable in the customer profile, campaign, and engagement ecosystem.

Key Benefits

Optimize to the most precise business metrics — such as revenue, profit, conversions and time-on-page — and identify the specific objectives to train models against. Measure actual results, re-feed model performance against goals with the rgOne™ platform’s Automated Machine Learning (AML) module, and automatically retrain each model to enhance performance. And the whole while, use A/B/n testing to select your best performing models. And to fully optimize your results.

KPI-driven results.

Link machine-learning models to business KPIs — to always deliver the best possible decisions to seize on your business goals.

Easy model feedback.

Automatically push decision results back to the machine-learning module for measuring and retraining models.

Fully verified testing.

Test with confidence when you compare performance against other models, human rules, and default offers.

Key Highlights

Business-aligned models.

You drive customer engagement by relevant interactions. And those interactions are driven by marketing decisions — such as offer selection, treatment, channel and message that are most relevant for every customer at every moment.

rgOne uses measurable KPIs as machine-learning goals in guiding these very decisions. With a wide range of models, you can perform classifications, predict customer value, and choose products for recommendations and offers.

  • With KPIs as targets, models are created to best drive results against business goals
  • Easily define and execute experiments for sustained optimal performance

Seamless orchestration.

rgOne’s AML module continually improves models, runs new models and retrains with live data against target KPIs. New data refreshes models at scheduled times or by business events — and newly trained models are swapped in automatically, as old ones lose their effectiveness. AML constantly monitors model performance and, if predictive power falls below pre-defined tolerances, new training is automatically triggered for retraining.

  • A/B/n testing
  • Monitoring and measuring model success against original KPIs
  • Constant data feedback for model retraining

Related Solutions

Get Started on Getting Ahead

Schedule a conversation and learn how Redpoint can put your goals within reach.

Get Started on Getting Ahead

Schedule a conversation and learn how Redpoint can put your goals within reach.