Overview

How an HR firm prioritized open roles to minimise time taken to filled open roles.

​

A leading European firm struggles to prioritise the open roles that they work at a given time, resulting higher vacant positions. The agents pick any opening randomly and the hire rate was very bad as compared to the competitors.

A simple Python based analytical model was put into place providing ranking to each open vacancy to be worked upon.

The Challenge

 

The recruitment firm was not having any prioritisation algorithm to work on open positions resulting in poor customer satisfaction.

One of the leading recruitment firm of Europe with offices in 3 continents is aggressive on increasing its market share. Recruitment agents used to fill roles which are primarily segmented into 3 levels:

1. Executive Level Roles

2. Contract Roles

3. Permanent Roles

But there was no mechanism that workflow managers can use to guide the team around how to prioritise from a big list.

 

 

“Solution”

 

Historical data was analysed to understand the time taken to fill open roles based on various characteristics like the level of the role, location of the role and location of the office managing the open role. A regression model was fitted on the data. Out of time and Out of sample testing was done to gain confidence on the predictive power of the model. The ultimate solution showed clear bifurcation on the behaviour of different segments. 

Workflow managers who allocate the cases to the recruitment agents were given an excel based dashboard where they can find out which top positions they should work on based on simple data inputs.

The Project

Details

Project type - Predictive Modelling 
Industry - Recruitment
Technology - Python
Delivery Time - 2 weeks

Consultants worked - 01