Skip to content

Latest commit

 

History

History
109 lines (61 loc) · 3.12 KB

README.md

File metadata and controls

109 lines (61 loc) · 3.12 KB
Raw

Tax-Prediction-using-AutoAI

This tutorial guides you through training a model to predict taxes for different houses based on locations, house types, etc. It uses Cognos Dashboards and AutoAI in IBM Watson Studio, which makes it possible for you to:

  • Automate your AI lifecycle management
  • Enable one-click deployment with Watson Machine Learning
  • Build better models faster and go live using the skill sets you have
  • Scale experimentation and deployment processes
  • Monitor and de-bias AI outcomes with Watson OpenScale
  • Increase trust and transparency in AI/ML development

AutoAI is a great way to get started even if you have no idea which model to use. All you do is give it data!!

Prerequisites

  1. Sign up for an IBM Cloud account.

Estimated time

This tutorial takes about 20 minutes to complete if you already have an IBM cloud account set up.

Steps

  1. Create an instance of the Watson Studio
    • Go to the Watson Studio page in the IBM Cloud Catalog.
    • Click Create.

  • Click Create a Project > Standard

  • Add Project name

  • Add the dataset into the project.

Demo

  • Add to Project > Dasboard > Create by uploading the file: taxes.json

Demo

These visualizations are created to get insights into the data.

Next, we begin by making our predictive model.

  • Add to Project > AutoAI Experiment

AutoAI automates:

  • Data preparation
  • Model development
  • Feature engineering
  • Hyper parameter optimization

Demo

  • Give it a name and click Create

  • Select from Project > taxes.csv

  • Select the column to predict: taxable_value

Selected Prediction by AutoAI

Demo

AutoAI Experiment in Progress

Demo

Run Finished

Demo

Pipeline Leaderboard

Demo

  • Watch and compare the top performing models on the leaderboard. Save the pipeline with rank 1, as a model.

Demo

  • Go to deployments tab > Create a new deployment

Demo

  • Name it

Demo

  • Once the status of the deployment is ready, click on it.

Demo

  • Click on the Test Tab to test your model with the following input.
  {"input_data":[{
        "fields": ["neighborhood","building_type","year_built","volume_interior","volume_other","lot_size"],
        "values": [["Rijkzicht","Townhouse", 1987, 303,75,91]]
}]}
  • Click Predict.

Demo