Advancing Anomaly and Churn Prediction Performance

Our researchers have applied state-of-the art techniques to improve the performance of machine learning defect detection, fraud and churn prediction. Our work on ODE-RNNs has yielded significant improvements in model performance when working with extremely large, sparse and irregular time-series data. This work has delivered millions of dollars in savings to clientsAs companies look to improve the accuracy and ROI in fraud prediction, defect and anomaly detection, client churn and other time-series problems, controlling run-time, processing costs and reliability will be at the core of these efforts.This research has yielded a massive 40X improvement in performance of ODE-based neural networks, allowing us to train on larger data sets, without a loss in accuracy.We believe sharing our findings with our community will lead to further progress from our efforts. Congratulations to our team on publishing this paper https://arxiv.org/abs/2207.05708.