One AI Recipes Overview

One AI Recipes make creating a predictive model as easy as choosing the outcome you want to predict and answering a series of questions.

 

One AI Recipes were created to bridge the gap between the way data is modeled for a people analytics platform and the way it is modeled for machine learning. They make creating a predictive model from your people data as easy as choosing the outcome you want to predict and answering a series of questions about the data you would like to leverage to make the predictions. The end result is a predictive model based on robust, clean, and properly structured data. This result is achieved without having to engage a Data Engineer or a Data Scientist.

 

Video Overview of One AI Recipes

 

 

Steps to Use a One AI Recipe to Create a Predictive Model

 

  1. Select One AI from the top navigation bar

  2. Select the + Add Machine Learning Model button

  3. Give the model a name. Please note that models cannot be re-named once they are saved

  4. Select the One AI Recipe option from the Using Data From section and Configure One AI Recipe

  5. Select a recipe from the What are you interested in predicting? dropdown

    Note: Until you make selections in a recipe, you can switch between recipes. Once you begin making selections, you can only switch to "Custom / Advanced Model"

  6. Answer each of the questions using the inline help for guidance if necessary

  7. Select the Save icon

  8. Scroll to the bottom of the Augmentation Configuration screen and select Create
    Note: Do not forget this step or you will lose all of the selections you made

     

Available Recipes:

Voluntary Attrition Risk

Description: One AI will help you predict the likelihood of a person in a selected population voluntarily terminating within a selected period of time. In order to do this, One AI will consider a number of attributes and will train the model on the population at a defined point in the past.

Algorithm Type: Classification (Binary)
Objective: Drivers and Predictions

Involuntary Attrition Risk

Description: One AI will help you predict the likelihood of a person in a selected population involuntarily terminating within a selected period of time. In order to do this, One AI will consider a number of attributes and will train the model on the population at a defined point in the past.

Algorithm Type: Classification (Binary)
Objective: Drivers and Predictions

Binary Promotion Analysis

Description: One AI will help you predict the likelihood of a person in a selected population being promoted within a selected period of time. In order to do this, One AI will consider a number of attributes and will train the model on the population at a defined point in the past.

Algorithm Type: Classification (Binary)
Objective: Drivers and Predictions

New Hire Success / Failure

Description: One AI will help you predict the Success or Failure at a specified amount of time after the hire date of employees hired during a specified time period.  In order to do this, One AI will consider a number of attributes and will train the model on the hires from a time period prior to the prediction data.

Algorithm Type: Classification (Binary)
Objective: Drivers and Predictions

High Performer

Description: One AI will help you predict whether an employee will be a high performer during a specified amount of time into the future. In order to do this, One AI will consider a number of attributes and will train the model on the population at a defined point in the past.

Algorithm Type: Classification (Binary)
Objective: Drivers and Predictions

Group Attrition Regression

Description: One AI will help you predict the amount of attrition within a selected period of time for groups defined by a dimension level. To make these predictions, One AI will leverage a regression algorithm and will consider a number of generative attributes from a time period prior to the prediction data.

Algorithm Type: Regression
Objective: Drivers and Predictions

Was this article helpful?

0 out of 0 found this helpful

Comments

0 comments

Please sign in to leave a comment.