Methods and systems for providing predictive metrics in a talent management application

1. A computer-implemented method, comprising:

receiving, by a computing device, data relating to a plurality of employment positions, wherein the data relating to the plurality of employment positions is received from a plurality of employment position sources;

pre-aggregating, by the computing device, the data relating to the plurality of employment positions received from the plurality of employment position sources;

converting the pre-aggregated data into a set of sparse vectors from one or more sequence file formats;

applying a machine learning technique to train a classifier data model using the set of sparse vectors, wherein the classifier data model is configured to determine an output employment source through which a job seeker will most likely be hired for an input employment position, and wherein the output employment source is determined based on an average number of applications per hire through the output employment source for similar employment positions to the input employment position;

receiving a user input from the job seeker corresponding to an user-selected employment position; and

applying the classifier data model to the user-selected employment position to determine the employment source through which the job seeker will most likely be hired for the user-selected employment position.

2. The method of claim 1 , wherein the method further comprises:

determining, based on the pre-aggregated data, one or more statistics based on the data relating to the plurality of employment positions; and

generating one or more predictive metrics relating to the plurality of employment positions using the one or more statistics.

3. The method of claim 2 , wherein the one or more predictive metrics includes a source effectiveness value of one or more employment position sources, wherein the source effectiveness value indicates a predicted effectiveness of the one or more employment position sources.

4. The method of claim 3 , further comprising:

receiving, by the computing device, input corresponding to an indication of a particular employment position;

determining a source effectiveness value for each of the one or more employment position sources for the particular employment position; and

ranking the one or more employment position sources based on the source effectiveness value of each employment position source for the particular employment position.

5. The method of claim 2 , wherein the one or more predictive metrics includes an effectiveness value of one or more employment position source types, wherein the effectiveness value indicates a predicted effectiveness of each of the one or more employment position source types.

6. The method of claim 2 , wherein the one or more predictive metrics includes a position difficulty metric indicating a difficulty of filling an employment position.

7. The method of claim 6 , wherein the position difficulty metric indicating the difficulty of filling the employment position is determined based on one or more of a time period indicating how long was required to fill the employment position, a time period indicating how long was required to hire a candidate for the employment position, a hiring rate for the employment position, or an offer acceptance rate for the employment position.

8. The method of claim 2 , wherein the one or more predictive metrics includes a hiring process effectiveness value of one or more hiring processes, wherein the hiring process effectiveness value indicates a predicted effectiveness of the one or more hiring processes.

9. The method of claim 2 , wherein the one or more predictive metrics includes a candidate difficulty metric indicating a difficulty of finding an employment position candidate with one or more particular attributes.

10. A talent recruiting system, comprising:

a memory storing a plurality of instructions; and

one or more processors configured to access the memory, wherein the one or more processors are further configured to execute the plurality of instructions to:

receive data relating to a plurality of employment positions, wherein the data relating to the plurality of employment positions is received from a plurality of employment position sources;

pre-aggregate the data relating to the plurality of employment positions received from the plurality of employment position sources;

convert the pre-aggregated data into a set of sparse vectors from one or more sequence file formats;

apply a machine learning technique to train a classifier data model using the set of sparse vectors, wherein the classifier data model is configured to determine an output employment source through which a job seeker will most likely be hired for an input employment position, and wherein the output employment source is determined based on an average number of applications per hire through the output employment source for similar employment positions to the input employment position;

receive a user input from the job seeker corresponding to an user-selected employment position; and

apply the classifier data model to the user-selected employment position to determine the employment source through which the job seeker will most likely be hired for the user-selected employment position.

11. The system of claim 10 , wherein the one or more processors are further configured to execute the plurality of instructions to:

determine, based on the pre-aggregated data, one or more statistics based on the data relating to the plurality of employment positions; and

generate one or more predictive metrics relating to the plurality of employment positions using the one or more statistics.

12. The system of claim 11 , wherein the one or more predictive metrics includes a source effectiveness value of one or more employment position sources, wherein the source effectiveness value indicates a predicted effectiveness of the one or more employment position sources.

13. The system of claim 11 , wherein the one or more predictive metrics includes a position difficulty metric indicating a difficulty of filling an employment position.

14. The system of claim 11 , wherein the one or more predictive metrics includes a hiring process effectiveness value of one or more hiring processes, wherein the hiring process effectiveness value indicates a predicted effectiveness of the one or more hiring processes.

15. The system of claim 11 , wherein the one or more predictive metrics includes a candidate difficulty metric indicating a difficulty of finding an employment position candidate with one or more particular attributes.

16. A non-transitory computer-readable memory storing a plurality of instructions executable by one or more processors, the plurality of instructions comprising:

instructions that cause the one or more processors to receive data relating to a plurality of employment positions, wherein the data relating to the plurality of employment positions is received from a plurality of employment position sources;

instructions that cause the one or more processors to pre-aggregate the data relating to the plurality of employment positions received from the plurality of employment position sources;

instructions that cause the one or more processors to convert the pre-aggregated data into a set of sparse vectors from one or more sequence file formats;

instructions that cause the one or more processors to apply a machine learning technique to train a classifier data model using the set of sparse vectors, wherein the classifier data model is configured to determine an output employment source through which a job seeker will most likely be hired for an input employment position, and wherein the output employment source is determined based on an average number of applications per hire through the output employment source for similar employment positions to the input employment position;

instructions that cause the one or more processors to receive a user input from the job seeker corresponding to an user-selected employment position; and

instructions that cause the one or more processors to apply the classifier data model to the user-selected employment position to determine the employment source through which the job seeker will most likely be hired for the user-selected employment position.

17. The non-transitory computer-readable memory of claim 16 , wherein the plurality of instructions further comprise:

instructions that cause the one or more processors to determine, based on the pre-aggregated data, one or more statistics based on the data relating to the plurality of employment positions; and

instructions that cause the one or more processors to generate one or more predictive metrics relating to the plurality of employment positions using the one or more statistics.

18. The non-transitory computer-readable memory of claim 17 , wherein the one or more predictive metrics includes a position difficulty metric indicating a difficulty of filling an employment position.

19. The non-transitory computer-readable memory of claim 17 , wherein the one or more predictive metrics includes a hiring process effectiveness value of one or more hiring processes, wherein the hiring process effectiveness value indicates a predicted effectiveness of the one or more hiring processes.

20. The non-transitory computer-readable memory of claim 17 , wherein the one or more predictive metrics includes a candidate difficulty metric indicating a difficulty of finding an employment position candidate with one or more particular attributes.