Job loyalty prediction for Randstad

The data of Randstad is a strategic asset. Xomnia enables us to unleash its business value.
Martijn Imrich, Product Owner Market Exploration and Forecasting at I-bridge, a Randstad company.

Xomnia developed a solution for Randstad to determine if a person's job loyalty can be predicted based on a resume. This is conducted in three steps. First, resumes are converted to one uniform file format. Next, an algorithm extracts a broad range of features from each CV. This is accomplished in two dimensions: features related to the style of the document (e.g., number of spelling errors, word diversity, word count) and features related directly to the person. Think about an applicant's educational or professional background and general information (e.g., age, gender, etc). Lastly, machine learning techniques are applied and bench marked on a historic dataset to test the predictive value of these features towards loyalty. We have proven that there is predictive value hidden in these resumes. Most importantly, we have shown it is possible to extract a new recruitment feature: a job loyalty indicator.