Talent analytics: an approach to model the impact of the work environment on staff turnover

Project Details


In Colombia, companies periodically send information to the National Administrative Department of Statistics (DANE) on employability, and autonomously carry out measurements of the work environment each year, and eventually participate in salary surveys carried out by private institutions and family compensation funds, however , the use of these data can be seen subject exclusively to the use for which they were collected, when they could potentially be used to explain/predict the behavior of employees within the organization, if there are descriptive, mathematical and robust models that allow do it. Deloitte's 2016 Global Human Resources Trends Survey, based on information provided by 7,096 business and HR leaders in more than 50 countries, reveals that companies are using talent analytics to predict business performance from analytics of the data of the labor force, so according to this, what this research project intends is, from an approach to the use of talent analytics, to propose a methodological structure that allows companies to take advantage of the data they have about their employees to study the impact that the most representative work environment variables have on staff turnover, in such a way that it is possible for them to mesh the findings with their retention strategies.


Study the impact that leadership, training and organizational structure have on staff turnover in a company.

Expected results

A methodology that allows, at a business level, to model the impact of work environment variables on staff turnover. It is an approach to the use of analytical tools in the area of human resources, which has been relatively little explored in Colombian companies. the data collection, storage and processing methodology could be adopted by the human resources area of any type of company
Short titleAnalítica del talento
AcronymAnalítica del talento
Effective start/end date16/01/1728/11/19


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.