Predicting Company Quitting From Online Social Enterprise Activity

ABSTRACT

Modeling and predicting attrition in organizations has real-world business significance. In this paper, we take a novel approach of analyzing a corporate social network (Yammer) to predict if people are likely to quit their company. Via a data-driven approach, we compute a rich set of features derived from graph structure, content, and work practice characteristics derived from Yammer. Our experiment shows that the proposed data-driven approach can be used to predict employee quitting with a fair accuracy of approximately 68% and a moderately high recall rate of 62%. Given the difficulty of the quitting prediction problem, these accuracy and recall rates are fairly encouraging.

References

1. L. Backstrom, D. Huttenlocher, J. Kleinberg, and X. Lan, "Group formation in large social networks: membership, growth, and evolution," in Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ser. KDD '06. New York, NY, USA: ACM, 2006, pp. 44--54. {Online}. Available: http://doi.acm.org/10.1145/1150402.1150412
2. A. Patil, J. Liu, B. Price, H. Sharara, and O. Brdiczka, "Modeling destructive group dynamics in on-line gaming communities," in Proceedings of the 6th International AAAI Conference on WebBlogs and Social Media (ICWSM). AAAI, 2012, pp. 290--297.
3. A. Patil, J. Liu, and J. Gao, "Predicting group stability in online social networks," in Proceedings of the 22nd International Conference on World Wide Web. ACM, 2013, pp. 1021--1030.
4. Association for Psychological Science, "Happy employees may be the key to success for organizations," www.sciencedaily.com/releases/2010/08/100813121920.htm, 2010.
5. Infosecurity Magazine, "50% job leavers steal confidential company data," http://www.infosecurity-magazine.com/view/26986/50-job-leavers-steal-confidential-company-data-/.
6. A. Patil, J. Liu, J. Shen, O. Brdiczka, and J. Gao, "Modeling attrition in organizations from email communication," in Proceedings of the International Conference on Social Computing (SocialCom). IEEE, 2013.
7. G. Gavai, K. Sricharan, J. Liu, O. Brdiczka, and J. Hanley, "Predicting quitting on yammer: An online social enterprise space," Learning, Inference and Data Solutions group, Palo Alto Research Center, Palo Alto, California, Tech. Rep. PARC-00-11, July 2014.
8. Yammer, https://www.yammer.com.
9. J. C. E. Aumayr and C. Hayes, "Reconstruction of threaded conversations in online discussion forums," in the Fifth International AAAI Conference on Weblogs and Social Media, 2006.
10. T. Joachims, Learning to Classify Text Using Support Vector Machines. Kluwer Academic Publishers, 2001.
11. T. Wilson, J. Wiebe, and P. Hoffmann, "Recognizing contextual polarity in phrase-level sentiment analysis," in Proceedings of HLT-EMNLP, 2005, pp. 347--354.
12. K. Toutanova, D. Klein, C. D. Manning, and Y. Singer, "Feature-rich part-of-speech tagging with a cyclic dependency network," in Proc. of NAACL '03, 2003, pp. 173--180.
13. V. R. Carvalho and W. W. Cohen, "On the collective classification of email "speech acts"," in Proc. of the 28th SIGIR, 2005, pp. 345--352.
14. T. M. Cover and J. A. Thomas, Elements of Information Theory. New York, NY: John Wiley and Sons, Inc., 1991.
15. L. Breiman, "Random forests," Machine Learning, Volume 45, Issue 1, pp 5--32, 2001.