Systems and methods for measuring the effectiveness of an agent coaching program

1. A method for measuring the effectiveness of an agent coaching program, the method comprising:

retrieving, by a processor, from a performance management database, Key Performance Indicator data for a first agent;

based on the retrieved data, calculating, by the processor, executing a recommender engine, a rate of change in a first Key Performance Indicator for the first agent in a first coaching program during a period of time;

selecting, by the processor, executing the recommender engine, a control group of agents, wherein agents in the control group of agents have not been exposed to the first coaching program;

calculating, by the processor, executing the recommender engine, an average rate of change in the first Key Performance Indicator for the control group of agents during the period of time;

calculating, by the processor, executing the recommender engine, a first coaching impact of the first coaching program on the first Key Performance Indicator for the first agent relative to the average rate of change in the first Key Performance Indicator for the control group of agents during the period of time;

calculating, by the processor, executing the recommender engine, a coaching effectiveness score, wherein the coaching effectiveness score reflects the first coaching impact of the first coaching program compared to the period of time;

identifying, by the processor, executing the recommender engine, a set of boosting factors, wherein the set of boosting factors fit a learning curve with respect to a rate of change of a given agent's first Key Performance Indicator during the period of time;

boosting, by the processor, executing the recommender engine, the coaching effectiveness score based on a position of the first agent on the learning curve; and

selecting, by the processor, a coaching program from a plurality of coaching programs for a worker.

2. The method as in claim 1 , further comprising normalizing the coaching effectiveness score.

3. The method as in claim 1 , wherein calculating the first impact is calculated by subtracting the average rate of change in the first Key Performance Indicator for the control group of agents during the period of time from the rate of change in the first Key Performance Indicator for the first agent during the period of time.

4. The method as in claim 1 , wherein the coaching effectiveness score is calculated by dividing the first coaching impact by the period of time.

5. The method as in claim 1 , wherein boosting the coaching effectiveness score based on the position of the first agent on the learning curve further comprises: multiplying the coaching effectiveness score by a boosting factor of the set of boosting factors that is commensurate with the position of the first agent on the learning curve.

6. The method as in claim 1 , wherein the period of time is the time invested in the first coaching program.

7. The method as in claim 1 , wherein selecting a control group of agents comprises:

receiving attribute information for the first agent and for each agent in a pool of agents;

generating a respective vector representation for the first agent and for each agent in the pool of agents; and

adding to the control group of agents each agent whose vector has a distance that is below a predefined threshold distance from the vector of the first agent.

8. A system for measuring the effectiveness of an agent coaching program, performed on a computer having a processor and memory, and one or more code sets stored in the memory and configured to execute in the processor, and which, when executed, configure the processor to:

retrieve, from a performance management database, Key Performance Indicator data for a first agent

based on the retrieved data, calculate, executing a recommender engine, a rate of change in a first Key Performance Indicator for the first agent in a first coaching program during a period of time;

select, executing the recommender engine, a control group of agents, wherein agents in the control group of agents have not been exposed to the first coaching program;

calculate, executing the recommender engine, an average rate of change in the first Key Performance Indicator for the control group of agents during the period of time;

calculate, executing the recommender engine, a first coaching impact of the first coaching program on the first Key Performance Indicator for the first agent relative to the average rate of change in the first Key Performance Indicator for the control group of agents during the period of time;

calculate, executing the recommender engine, a coaching effectiveness score, wherein the coaching effectiveness score reflects the first coaching impact of the first coaching program compared to the period of time;

identify, executing the recommender engine, a set of boosting factors, wherein the set of boosting factors fit a learning curve with respect to a rate of change of a given agent's first Key Performance Indicator during the period of time;

boost, executing the recommender engine, the coaching effectiveness score based on a position of the first agent on the learning curve; and

select a coaching program from a plurality of coaching programs for a worker.

9. The system as in claim 8 , further comprising normalizing the coaching effectiveness score.

10. The system as in claim 8 , wherein the processor is configured to calculate the first impact by subtracting the average rate of change in the first Key Performance Indicator for the control group of agents during the period of time from the rate of change in the first Key Performance Indicator for the first agent during the period of time.

11. The system as in claim 8 , wherein the coaching effectiveness score is calculated by dividing the first coaching impact by the period of time.

12. The system as in claim 8 , wherein the processor is configured to boost the coaching effectiveness score based on the position of the first agent on the learning curve by multiplying the coaching effectiveness score by a boosting factor of the set of boosting factors that is commensurate with the position of the first agent on the learning curve.

13. The system as in claim 8 , wherein the period of time is the time invested in the first coaching program.

14. The system as in claim 8 , wherein the processor is configured to:

receive attribute information for the first agent and for each agent in a pool of agents;

generate a vector representation for the first agent and for each agent in the pool of agents; and

add to the control group of agents each agent whose vector has a distance that is below a predefined threshold distance from the vector of the first agent.