Displaying "AI" articles (40)
Contextual Multi-Armed Bandits Meets Causal Inferencing
The Multi-Armed Bandits problem is a classic reinforcement learning problem that demonstrates the exploration–exploitation tradeoff dilemma. To correctly estimate the causal effect of price changes or different financial product bundle offers on consumers’ purchasing decisions, the standard methodology is to perform a randomized controlled trial (RCT). However, RCTs could be expensive, and financial institutions are often reluctant to conduct them for the required period of time.
Mastering Product Personalization via Data Innovation
Gain a deeper understanding of what Product Personalization is, its value, and what data is most critical to fully automate in the Product Personalization process.
Real-Time Banking Pricing Decisions. Big Time Results
Through its real-time pricing solution, Earnix gives banks the power to deliver pricing and personalization - faster than ever before. A solution that is capable of complex modeling, analytically driven automation, testing and deployment.
Fully Automated Insurance Pricing Process Webinar
The insurance industry has invested millions of man-hours refining the underwriting, claims, and customer service processes. But what about the pricing process? What percent of the pricing process can we automate?
Leveraging Scenario Based Analytics and Preparing for the Unexpected with Capgemini
Join Earnix & Capgemini on a discussion on how the use of scenario-based analytics can shrink time-to-insight, time-to-value, and time-to-impact so organizations can optimally respond to both threats and opportunities.
Personalization in the world of Insurance Webinar
Join Earnix for a webinar on the past, present, and future of personalization in the Insurance industry.
Brochure: Earnix Advanced Analytics - The Future
It’s safe to say that most insurers today see the real potential in using much more business data to develop innovative new pricing offers their customers will love. Yet the majority of them simply don’t have an effective way to collect, manage, and model the mountains of data at their disposal in a meaningful way.