How High Performance is Predicted

You can use system-generated performance predictions to validate your assessments of employees. Let's try and reduce voluntary terminations by looking at performance and voluntary termination predictions.

Settings That Affect Performance Predictions

Performance predictions are based on data from all employees. The Collect Data and Perform Data Mining for predictions process collects relevant data and generates the predictions. You can manage predictive models using the Manage Predictive Models task in the Setup and Maintenance work area.

Did you know that you can perform data collection either for the enterprise or for a specified manager assignment? The data-mining stage of the process is always performed on the latest available data.

To get accurate results when the volume of relevant transactions in your enterprise (such as hires, terminations, and promotions) is high, we recommend you schedule the process weekly. The process has no default schedule. Remember to schedule the process when there's less activity to avoid any impact on performance.

How Performance Is Predicted

.

1. For all employee work relationships, the process collects the values of a large set of attributes, such as:

   • Time in grade

   • Current job

   • Latest salary increase

   • Performance rating

   • Number of sickness absences in the previous year

   You're interested in the attributes which show a correlation with high performance. In some cases, simple values, such as manager name are required; in others, such as percentage increase in sickness leave, the process calculates the values. Most of these attributes are held at the assignment level; therefore, for work relationships with multiple assignments, multiple values are collected.

   Don't forget that contingent worker and nonworker work relationships are excluded.

   The collected attribute values are passed to Oracle Data Mining, which identifies patterns and relationships in the data and builds a model for predicting employee performance.

2. Oracle Data Mining makes performance predictions for current employees according to the predictive model. For example, if performance is high in a particular job and grade, current employees with that job and grade are more likely to perform higher than workers in other jobs and grades.

   Each prediction relates to an employee assignment. If an employee reports to a single manager in multiple assignments, the manager sees multiple predictions for that employee.

Performance predictions are available for both teams and individual assignments.

• Apart from showing the average predicted performance for the team, team predictions shows the percentage of employee assignments for which the factor is the main contributory factor.

• Individual predictions show the predicted performance for the employee assignment. The values of relevant factors, such as previous performance, and the relative contribution that each factor makes to the prediction, also appear.