Build a machine learning regression model using Findability Platform Predict Plus

Summary

This developer code pattern uses Findability Platform (FP) Predict Plus operator from Red Hat® Marketplace to predict customer spending using historical data and demonstrates the automated process of building models.

Description

Machine learning is a large field of study that overlaps with and inherits ideas from many related fields, such as artificial intelligence. The focus of the field is learning — that is, acquiring skills or knowledge from experience. Most commonly, this means synthesizing useful concepts from historical data. As such, there are many types of learning you may encounter as a practitioner in the field of machine learning from whole fields of study to specific techniques.

Regression in machine learning and statistics is a supervised learning approach in which the computer program learns from the data given to it to make new observations or predictions. In this technique, the target variable has continuous values ranging from zero to infinity. Examples of regression problems with given historical data include:

  • Predicting the temperature
  • Predicting sales
  • Predicting the house price
  • Predicting customer spending

We will focus on predicting customer spending using historical data and demonstrate the automated process of building models using FP Predict plus operator from Red Hat Marketplace. We will use the FP Predict Plus operator from Red Hat Marketplace to solve this use case.

When you have completed this pattern, you will understand how to:

  • Quickly set up the instance on OpenShift® cluster for model building.
  • Ingest the data and initiate the FP Predict Plus process.
  • Build models using FP Predict Plus and evaluate the performance.
  • Choose the best model and complete the deployment.
  • Generate new predictions using the deployed model.

Flow

Flow

  1. User logs into the FP Predict Plus platform using an instance of FP Predict Plus operator.
  2. User uploads the data file in the CSV format to the Kubernetes storage on the platform.
  3. User initiates the model-building process using FP Predict Plus operator on OpenShift cluster and creates pipelines.
  4. User evaluates different pipelines from FP Predict Plus and selects the best model for deployment.
  5. User generates accurate predictions by using the deployed model.

Instructions

Find the detailed steps for this pattern in the README file. The steps will show you how to:

  1. Add the data
  2. Create a job
  3. Review the job details
  4. Analyze results
  5. Download the Results & Model file
  6. Prediction using new data
  7. Create predict job
  8. Check job summary
  9. Analyze results of predict job
  10. Download predicted results