| Attribute | Description |
| ID_Number | Unique identifier assigned to each individual. |
| Name Surname | Full name of the individual. |
| Gender | The individual's gender. |
| Age | The current age of the individual. |
| The individual's email address. | |
| Phone | The individual's contact phone number. |
| City | City of residence. |
| District | District within the city of residence. |
| Rol_Category | The category of the job role. |
| Rol | Specific job position. |
| Years_of_Experience | Total number of years the person has worked professionally (float). |
| Title | Combined seniority and role. |
| Education_Level | Highest level of education attained (e.g., Bachelor's, Master's, Ph.D.). |
| Field of Education | The field or major studied. |
| Graduation Year | Year the individual completed their most recent degree. |
| Start Date | Date the individual started their current job. |
| Last Promotion Date | Date of the most recent promotion in their career. |
| Company | Name of the company where the person works. |
| Company Size | Classes such as Startup, Small, Medium, Corporate. |
| Industry | Sector or industry the company operates in. |
| Work Style | Mode of working (e.g., full time, part time). |
| Remote Work Rate | Percentage of time worked. |
| Technologies Used | List of tools the individual uses. |
| Main Programming Language | The primary programming language they work with. |
| English Level | Proficiency in English (e.g., Beginner, Intermediate, Advanced, Native). |
| Other Languages | Any other languages the individual speaks and their proficiency. |
| Certifications | Professional certificates earned. |
| LinkedIn Profile | URL to their LinkedIn account. |
| GitHub Profile | URL to their GitHub account or portfolio. |
| Total Number of Projects | Count of completed or contributed projects. |
| Annual Leave Days | Number of leave days allotted per year. |
Table 1: Attributes and their descriptions
| Attribute | Description |
| Salary | Current annual or monthly salary. |
| Seniority | Level of experience or seniority. |
| Birth_year | The year the individual was born. |
| Technical Skill Score | 0-100 points based on experience and certification. |
| Soft Skill Score | 0-100 points based on role and seniority. |
Table 2: Derived attributes and their descriptions
| Column | Description |
| Seniority | Intern (0) → Director (7) |
| Education_Level | High School (0) → PhD (4) |
| English_Level | Beginner (0) → Native Language (4) |
| Gender | Female (0), Male (1) |
Table 3: The converted categories and their numerical values
| Models | Hyperparameter ranges |
| Voting | RR (“Alpha”: [0.1])RF (“N_Estimators”: [100],“Random_State”: [42])CatBoost (“Depth”:[4]“Iterations”:[100]“Learning_Rate”:[0.1]) |
| Stacking | RR ( “Alpha”: [0.1])RF (“N_Estimators”: [100], “Random_State”:[42])CatBoost(“Iterations”:[500], “Learning_Rate”:[0.1], “Depth”:[6], “Verbose”: [0], “Random_State”: [42]) |
| Ridge | “Alpha”: [0.1 - 10] |
| DT | “Max_Depth”: [2 – 10] “Min_Samples_Split”: [2 – 10] |
| RF | “N_Estimators”: [50 - 150]“Min_Samples_Split”: [2]“Max_Depth”: [4 - 10]“Leaf_Node”: [250] |
| Grid Search CV (for RF) | “N_Estimators”: [50 - 150] “Max_Depth”: [4 - 8] “Min_Samples_Split”: [2 - 10] |
| SVM | “C”: [0.1 - 10]“Epsilon”: [0.01 - 0.2] |
| CatBoost | “Iterations”: [100 – 500]“Learning_Rate”: [0.01 – 0.3]“Depth”: [4 – 10]“I2_Leaf_Reg”:[3]“Random_State”: [42]“Verbose”: [0]“Early_Stopping_Rounds”: [50] |
| AdaBoost | “Max_Depth”:[4]“N_Estimators”:[100]“Learning_Rate”:[1.0]“Random_State”:[42] |
Table 4: The hyperparameter ranges of the models
| Model | MAE | MAPE | R^2 |
| LR | 2300 | 9.31% | 0.936 |
| RR | 2150 | 9.28% | 0.936 |
| DT | 0 | 0 | 0.1000 |
| RF | 1820 | 2.60% | 0.993 |
| AdaBoost | 2400 | 10.31% | 0.937 |
| Voting | 1400 | 5.66% | 0.973 |
| Stacking | 1000 | 4.00% | 0.975 |
| CatBoost | 1450 | 6.10% | 0.910 |
| SVM | 1900 | 8.80% | 0.890 |
Table 5: The MAE, MAPE and R^2 values of the developed models
| Model | Model Training Runtime (ms) | Explainability |
| LR | 170 ms | High |
| RR | 185 ms | High |
| DT | 190 ms | Intermediate (Overfit) |
| RF | 2350 ms | Intermediate |
| AdaBoost | 3250 ms | Low |
| Voting | 5650 ms | Intermediate |
| Stacking | 5000 ms | Intermediate |
| CatBoost | 9700 ms | High |
| SVM | 19500 ms | Low |
Table 6: The Model Training Runtime (ms) and Explainability values of the developed models
Tables at a glance