This repository is a project in progress of the union of six data science projects in various departments of a company (each project has its own documentation).
The main objectives of this project are:
- For the Human Resources department, forecasting whether an employee will leave the company;
- For the Marketing department, perform market segmentation;
- For the Sales department, predict future sales;
- For the Medical department, the diagnosis of respiratory diseases using images;
- For the Public Relations department, sentiment mining in texts;
- For the Production and Maintenance department, the classification of images of defective products.
Kalf's company wants to avoid hiring costs and the reasons will be mentioned below. I, as a data scientist, along with this department, aim to predict which employees are likely to leave the company.
This forecast is important for the following reasons:
- Hiring and retaining employees are extremely complex tasks that require capital, time and skills;
- "The average company loses between 1% and 2.5% of its total revenue in the time it takes to train a new employee";
- It costs an average of $7645 to hire a new employee (in a company with approximately 500 employees);
- There is still the money you need to invest in onboarding and training new employees. It takes about 52 days for an employee to actually occupy their new position;
Source: Toggl hire