Democratizing AI for predictions on the Modern Data Stack. The team behind PyG (PyG.org) has built an end-to-end platform for developing predictions using AI over large scale data warehouses. We believe the future of ML is a seamless integration between modern cloud data warehouses and AI algorithms. Our platform massively simplifies the training and deployment of ML models on complex data.
Kumo utilizes Graph Neural Network (GNN) architectures. GNNs, one of the hottest areas of machine learning now, are a class of deep learning models that generalize Transformer and CNN architectures and enable us to apply the power of deep learning to complex data. GNNs are unique in a sense that they can be applied to data of different shapes and modalities.
Kumo can be used for a variety of use cases:
-New customer acquisition
-Customer loyalty and retention
-Personalization, next best action
-Entity resolution, search/retrieval
-Abuse detection
-Financial crime detection
-Forecasting and planning
-ML features for data scientists