For many ML use-cases, organizations rely solely on tabular data and tree-based models like XGBoost and LightGBM. This is often because deep learning is hard: frameworks like PyTorch and Tensorflow require experts to write thousands of lines of complex code and determine how to operationalize models. As a result, teams miss out on valuable signals hidden within unstructured data like text and images.
Fortunately, Predibase—the leading low-code declarative ML platform—along with popular open-source project Ludwig make it easy to build multi-modal deep learning models in < 15 lines of code. In this session, we’ll deep dive into building a customer review prediction model leveraging text and tabular data using Ludwig and Predibase.
- Rapidly train, iterate, and deploy a multi-modal model for customer review prediction,
- Use low-code declarative ML tools to dramatically reduce the time to build multiple ML models,
- Leverage unstructured data just as easily as structured data with Ludwig and Predibase.