Dark Mode
Employee Retention Factors Dataset
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is designed for predicting employee turnover, focusing on an individual's risk of quitting. It was originally used for a Survival Analysis Model, a method considered highly important for predicting employee attrition, especially for long-term situations, contrasting with more common but potentially less effective short-term methods like Logistic Regression. The dataset aims to provide valuable insights for understanding and addressing employee retention challenges.
Columns
- stag: Represents the employee's experience, measured in time (duration).
- event: Indicates employee turnover, with a value of 1 typically representing turnover and 0 indicating no turnover.
- gender: Specifies the employee's gender, either female (f) or male (m).
- age: Records the employee's age in years.
- industry: Denotes the industry in which the employee works, with categories such as Retail, Manufacture, and other specific industries.
- profession: Describes the employee's profession, including categories like HR, IT, and other professional roles.
- traffic: Explains how the employee joined the company, such as direct application (advert), friend recommendation (recNErab, referal), job site application (youjs, empjs), recruiting agency (KA), or direct invitation by the employer (friends, rabrecNErab).
- coach: Indicates the presence of a coach or training during the probation period (e.g., 'no', 'my head', 'other').
- head_gender: Specifies the gender of the employee's supervisor (head), either male (m) or female (f).
- greywage: Describes the salary payment scheme, distinguishing between 'white' (minimum wage compliant) and 'grey' (salary not fully declared to tax authorities, often found in Russia or Ukraine).
- way: Refers to the employee's primary mode of transportation, such as bus or car.
- extraversion: Represents the employee's score on an extraversion scale (ranging from 1 to 10).
- independ: Represents the employee's score on an independence scale (ranging from 1 to 10).
- selfcontrol: Represents the employee's score on a self-control scale (ranging from 1 to 10).
- anxiety: Represents the employee's score on an anxiety scale (ranging from 1.7 to 10).
- novator: Represents the employee's score on a 'novator' or innovation scale (ranging from 1 to 10).
Distribution
The data file is typically in CSV format, named
turnover.csv, with a size of 83.24 kB. The dataset contains 16 columns and consists of 1129 valid records across most columns, indicating a complete set of entries without missing or mismatched data points for these attributes.Usage
This dataset is ideal for various analytical applications, including:
- Predicting Employee Churn / Employee Turnover: Identifying employees at risk of leaving the organisation.
- Employee Survival Analysis: Modelling the duration of employee tenure and predicting the likelihood of an employee remaining with the company over time.
- Uplift Modelling: Determining the causal effect of interventions on employee retention.
- Uplift Survival Analysis: Combining survival analysis with uplift modelling to assess the impact of specific actions on employee tenure.
Coverage
The dataset is a real-world collection of employee data. While specific geographic and time range details are not explicitly provided, the 'greywage' column description hints at a context potentially involving Russia or Ukraine. No specific notes on data availability for certain demographic groups or years are detailed beyond the general distribution of values within columns like age, gender, and industry.
License
CC BY-NC-SA 4.0
Who Can Use It
This dataset is valuable for:
- Data Scientists and Analysts: For developing and testing predictive models related to human resources.
- HR Professionals and Management: To gain insights into factors influencing employee retention and to inform strategic workforce planning.
- Researchers: Studying organisational behaviour, employee dynamics, and survival analysis in a business context.
- Organisations: Looking to proactively identify and address potential employee turnover risks.
Dataset Name Suggestions
- Employee Turnover Prediction Data
- Workforce Attrition Analysis Dataset
- HR Survival Analysis Data
- Employee Retention Factors Dataset
Attributes
Original Data Source: Employee Retention Factors Dataset
QUALITY