An approach for modeling alternative customer actions like loyalty sign-ups, credit card enrollment, or gift giving
Predictive marketing analytics has traditionally focused on the main revenue generating activities of a business, e.g. purchases in retail or bookings in hospitality. While it’s true that these activities have the most direct impact on customer lifetime value (CLV), they’re not the only moments in the customer journey that have an impact CLV.
Investing in Clojure to support core secret engine infrastructure
One of our summer interns, Danny Rassaby, describes his summer project in the Amperity infrastructure and how core Clojure features and help to organize his abstractions in our open-sourced vault client.
Creating a new CLV modeling paradigm that extracts the most value out of customer data
Predicting customer lifetime value is the cornerstone of modern marketing analytics. Yet the same modeling approach has been the gold standard for over fifteen years. Amperity's data science team recently introduced a new regression-based ensemble that leverages a vast amount of unified customer data, outperforming the baseline model in both CLV and customer churn prediction.
Amperity leverages data science to ensure operational reliability of a complex system, finding an elegant solution to a thorny systems problem. Anomaly Detection automates the process of understanding a given workflow’s “normal operation”.
At Amperity, every day our services process terabytes of data across dozens of customer accounts. To make sure data is processed quickly and in a cost effective way, we leverage scheduled workflows, which run automatically and are monitored closely to ensure all data is processed correctly in every run.
Or ... how to sneak Clojure into your Java codebase
Outside of a few notable holdouts, most engineering teams recognize the immense value in testing software to improve code quality. Isolated unit-testing has become an increasingly common practice, with JVM libraries to help more complex unit-testing patterns such as dependency injection or mocking in testing libraries.