Methods and systems for predicting job seeking behavior

• US 8,352,406 B2
• Filed: 11/04/2011
• Issued: 01/08/2013
• Est. Priority Date: 02/01/2011
• Status: Active Grant

• Current Assignee: Bullhorn Incorporated
• Original Assignee: Bullhorn Incorporated
• Inventors: Daniels, Leah Nicole, Moore, Matthew Thomas, Costa, Philip, Siebert, Philip Chase
• Primary Examiner(s): RIFKIN, BEN M
• Application Number:
  US13/289,168
• Publication Number:
  US 20120197835A1
• Time in Patent Office: 431 Days
• Field of Search: 706/52, 706/50
• US Class Current: 706/50
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/1053 Employment or hiring
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Embodiments of the present invention analyze information available from social-media websites to predict the likelihood that a prospective candidate will become an active recruitement candidate.

Claims

1. A computer-implemented method for identifying active candidates for recruitment, the method comprising:

repeatedly searching for information from at least one social media website regarding a prospective candidate over a predetermined time period, the information including (i) updates to the prospective candidate'"'"'s end user profile during the predetermined time period, (ii) recommendations posted during the predetermined time period, (iii) social-media connections established during the predetermined time period, and (iv) text phrases indicative of recruitment potential introduced during the predetermined time period;

analyzing the information for a pattern indicative of whether the prospective candidate is or is likely to become an active recruitment candidate; and

computationally predicting, based on the obtained information, whether the prospective candidate is or is likely to become an active recruitment candidate.

2. The method of claim 1 wherein the information comprises signals and weights associated with the signals, and the pattern comprises at least one of (i) a minimum number of signals within the predetermined time period and (ii) a minimum aggregate signal weight within the predetermined time period.

3. The method of claim 1 wherein the information comprises false-positive indicators.

4. The method of claim 3 wherein the false-positive indicators comprise an indication that the prospective candidate has begun new employment within the past three months.

5. The method of claim 1 wherein the computational prediction step comprises computing, from the information, a quantitative score indicative of the likelihood that the prospective candidate is or will become an active recruitment candidate.

6. The method of claim 1 further comprising computationally initiating an action based on a positive prediction that the prospective candidate is or is likely to become an active recruitment candidate, the action comprising at least one of (i) alerting a user to the positive prediction, (ii) adding identifying information for the prospective candidate into an active candidate database, (iii) sending a message to the prospective candidate, or (iv) telephoning the prospective candidate.

7. A system for identifying active candidates for recruitment, comprising:

(a) a database for storing information regarding prospective candidates; and

(b) a processor for executing;

(i) an information module for

(A) repeatedly searching for information from at least one social media website regarding a prospective candidate over a predetermined time period, the information including (1) updates to the prospective candidate'"'"'s end user profile during the predetermined time period, (2) recommendations posted during the predetermined time period, (3) social-media connections established during the predetermined time period, and (4) text phrases indicative of recruitment potential introduced during the predetermined time period, and

(B) storing the information in the database; and

(ii) a prediction module for scanning the database, analyzing the information for a pattern indicative of whether the prospective candidate is or is likely to become an active recruitment candidate, and predicting, based on the analyzed information, whether the prospective candidate is or is likely to become an active recruitment candidate.

8. The system of claim 7 wherein the information comprises signals and weights associated with the signals, and the pattern comprises at least one of (i) a minimum number of signals within the predetermined time period and (ii) a minimum aggregate signal weight within the predetermined time period.

9. The system of claim 7 wherein the information comprises false-positive indicators.

10. The system of claim 9 wherein the false-positive indicators comprise an indication that the prospective candidate has begun new employment within the past three months.

11. The system of claim 7 where the prediction module computes, from the information, a quantitative score indicative of the likelihood that the prospective candidate is or will become an active recruitment candidate.

12. The system of claim 7 further comprising an action module for generating reports of predictions made by the prediction module.