Building and Evaluating a Fraud Detection Model with TensorFlow and ONNX

Learning path | 3 resources | Published on August 28, 2024
Alex Krikos Ramakrishna Yekulla

In this learning exercise, we'll focus on training and deploying your trained model with OpenShift AI. To simplify environment management, we'll leverage OpenShift AI's capabilities. By the end of this exercise, you'll gain familiarity with managing and deploying your models effectively using OpenShift AI. We will be fraud detection as the example use case in this exercise.

Try it in our Sandbox

  1. Overview: Building and Evaluating a Fraud Detection Model with TensorFlow and ONNX
  2. Prerequisites and step-by-step guide Page
  3. Additional resources Page

Overview: Building and Evaluating a Fraud Detection Model with TensorFlow and ONNX

Red Hat OpenShift AI image

In the world of Machine Learning (ML), managing trained models effectively is crucial. OpenShift AI provides powerful tools to automate and streamline the ML lifecycle. This learning exercise delves into creating a project, training and testing a fraud model and saving the model.

Let's step through the implementation. Our primary aim in this learning exercise is to thoroughly log all activities within the OpenShift AI. To achieve this, we are focusing on creating, training, and saving the model.