IBM employs a network of expert analytics consultants for various projects. To help determine how to distribute its bonuses, IBM wants to form groups of employees with similar performance according to key performance metrics. Each observation (corresponding to an employee) in the file BigBlue consists of values for: (1) UsageRate which corresponds to the proportion of time that the employee has been actively working on high priority projects, (2) Recognition which is the number of projects for which the employee was specifically requested, and (3) Leader which is the number of projects on which the employee has served as project leader. Apply k-means clustering with for values of k = 2, 3, 4, 5, 6, 7, 8. Be sure to Normalize Input Data and specify 50 iterations and 10 random starts. How many clusters do you recommend using to categorize the employees if the average distance to each centroid must be less than 0.70 units measured in original units? Why?