mfd-explore-this-pattern.adoc

title	Explore this pattern
weight	20
aliases	/mlops-fraud-detection/mfd-explore-this-pattern/

Table of Contents

• {rhoai} components
  • Kubeflow pipeline
  • Kserve model serving
• Inferencing application

modules/comm-attributes.adoc

{rhoai} components

Most components installed as part of this pattern are available in the {rhoai} (RHOAI) console. To navigate to this page, click the {rhoai} link in the application launcher of the OpenShift console.

Figure 1. The RHOAI Link

Kubeflow pipeline

The pattern installation automatically creates and runs a Kubeflow pipeline to build and train the fraud detection model. To view pipeline details in the RHOAI console, select the Pipelines tab.

Figure 2. The pipelines tab

This tab displays the fraud-detection pipeline deployed as part of this pattern. To view the specific run that trained the initial model, select the Runs tab and then select the job-run item.

Figure 3. The runs tab

The Runs page displays a diagram of the pipeline, which includes the following three major steps:

• Obtaining the training data.

• Training the model.

• Uploading the model to MinIO.

You can view the logs of any stage, such as the training stage, to monitor accuracy changes for each model training epoch.

Figure 4. The job-run pipeline details

Note	The source code for this pipeline run is available in the pattern repository at src/kubeflow-pipelines/small-model.

Kserve model serving

You can view the model deployment in the Model Deployments tab of the RHOAI console.

Figure 5. The model deployment

Inferencing application

The pattern installs a simple Gradio front end to communicate with the fraud detection model. To access the application, click the link in the application launcher of the OpenShift console.

Figure 6. The inferencing application link

You can manually configure transaction details in the form. The application includes two examples: a fraudulent transaction and a non-fraudulent transaction.

Figure 7. Using the fraud example

Important

Due to the non-deterministic nature of the training process, the model might not always identify these transactions accurately.

Note	The source code for the inferencing application is available in the pattern repository at src/inferencing-app.