The next big problem was an increased number of drop-offs. To address this risk, the recruiting team needed an intelligent solution to understand the joining propensity of candidates. Early warnings on risk helped develop a more realistic model for risk mitigation in the talent supply processes. Hyreo had a data science-backed approach for measuring candidate joining risk with an in-built recruiter alert mechanism to enable quicker action.

Propensity analysis in Hyreo employed state-of-the-art machine learning algorithms, including Logistic Regression, Random Forest, and Gradient Boosting. By analyzing a candidate's historical behavior and interactions, the system calculated the likelihood of a candidate accepting an offer.

Sentiment detection using NLP helped to continuously understand candidate sentiments based on data from candidate email correspondences, CSATs, and interaction history, indicating doubts, hesitations, or uncertainties about joining. Should the system detect a risk of a candidate declining an offer, recruiters were promptly alerted with insights on risk parameters and strategies for effective engagement.

With over 50+ behavior and interaction parameters, such as date of joining change, low satisfaction of job role or compensation, hiring manager interactions, BGV documentation, etc., the system could understand and decode the intricate web of outcomes and their overall impact.