AI & Analytics Engine Tutorial 1/4: Creating A ML Project

To help you get started with The Engine,  we have written 4 easy-to-follow tutorials. This article is 1/4, and details how you can create a free trial account and start your first project. 

In recent years, data has grown to be treasured as one of the most valuable business assets. Regardless of industry, putting data to work can have a tremendous impact on the success of the endeavor. 

The Engine at PI.EXCHANGE - lowers the barrier to entry into the AI and Analytics space so those starting out on their data journey can begin to leverage The Engine and derive new insights from data without having to learn a line of code.

Step 1: Sign Up For Your Free Trial

Get started with a  free trial to acquaint yourself with the platform. All the core features are still accessible within the free trial. For more information visit the Sign Up page.

Step 2: Creating Your First Project

Once you've logged into the web Graphical User Interface (GUI), A dashboard displaying all the organizations you've created (Note: You'll be provided with a default organization when you've registered). 

When you click on the organization, you'll be provided with further details of the organization.

To create a new project, you simply click the "+" sign in the bottom right corner and select "New Project" - You may notice that my example [below] already has an existing project. 

Selecting "New Project" will open a dialogue box where you are asked to: 

1. Provide a project name
2. Provide a detailed description of your project [optional] 
3. Select the organization you'd like to create the project under. 

The next steps are easy;

1. Give your project a name then,
2. Select "Next". You'll be provided with the option to add further users to your project and define the roles of each user - i.e. "Owner", "Editor", or "Viewer". In the example above, we skipped this process by selecting "Create Project". 

Next Step - Creating a Dataset

The dataset creation process involves two steps that will be detailed in the next blog article:

1. Importing raw data by connecting to a data source or uploading a file, and
2. Preparing your data source into a dataset using multiple options, one of which is to create a new data preparation recipe.

Go on to Part 2 on Data Preparation 

Ready to start your first machine learning project?