HireSmart is an AI-powered Resume Screening and Candidate Ranking System developed to streamline the recruitment process through Machine Learning and Business Intelligence. The project automatically evaluates candidate profiles, predicts whether candidates should be shortlisted or rejected, classifies them into fit levels, and provides actionable hiring insights through an interactive Power BI dashboard.
By automating resume screening and candidate evaluation, HireSmart helps recruiters save time, improve hiring efficiency, and make data-driven recruitment decisions.
Organizations receive thousands of applications for open positions, making manual resume screening inefficient and time-consuming. Traditional recruitment processes often involve repetitive tasks and subjective decision-making.
HireSmart addresses these challenges by leveraging Machine Learning to automate candidate evaluation and Power BI to visualize recruitment insights, enabling recruiters to identify the best candidates quickly and effectively.
- Automate resume screening using Machine Learning.
- Predict whether a candidate should be shortlisted or rejected.
- Classify candidates into High Fit, Medium Fit, and Low Fit categories.
- Rank candidates based on overall suitability.
- Visualize recruitment analytics through an interactive dashboard.
- Support data-driven hiring decisions.
- Python
- Pandas
- NumPy
- Scikit-learn
- Jupyter Notebook
- Microsoft Power BI
- Git
- GitHub
The dataset contains candidate-related attributes including:
| Feature | Description |
|---|---|
| Education Level | Candidate educational qualification |
| Years Experience | Professional experience |
| Skills Match Score | Relevance of candidate skills |
| Resume Length | Resume quality indicator |
| GitHub Activity | Technical engagement score |
| Candidate Score | Overall evaluation score |
| Fit Level | High Fit, Medium Fit, Low Fit |
| Prediction | Shortlisted or Rejected |
Candidate information was collected and organized into a structured dataset.
- Handling missing values
- Data cleaning
- Feature selection
- Label encoding
Relevant candidate attributes were prepared for model training.
The dataset was divided into training and testing sets for model evaluation.
A Machine Learning classification model was trained to predict candidate outcomes.
Candidates were ranked based on their generated candidate scores.
The processed data was visualized using Power BI to provide recruitment insights.
- Total Applications
- Shortlisted Candidates
- Rejected Candidates
- High Fit Candidates
- Applications Processed
- Average Candidate Score
- Fit Level Distribution (Donut Chart)
- Candidate Outcomes by Experience (Line Chart)
- Candidate Score by Education (Column Chart)
- Applicants by Education (Bar Chart)
- Interactive Slicers and Filters
- Candidate Details Table
| Metric | Value |
|---|---|
| Total Applications | 30,000 |
| Shortlisted Candidates | 21,035 |
| Rejected Candidates | 9,000 |
| High Fit Candidates | 19,000 |
| Average Candidate Score | 69.91 |
HireSmart helps organizations:
- Reduce manual resume screening effort.
- Improve recruitment efficiency.
- Accelerate hiring decisions.
- Identify high-potential candidates quickly.
- Support data-driven talent acquisition.
- Resume PDF Parsing
- NLP-Based Resume Analysis
- Job Description Matching
- Candidate Recommendation Engine
- Real-Time Recruitment Dashboard
- Cloud Deployment
- Data Preprocessing using Python
- Machine Learning Classification
- Candidate Ranking Systems
- Business Intelligence Dashboard Development
- Data Visualization Best Practices
- End-to-End Analytics Project Lifecycle
Lubna Shireen R
Student | Data Analytics Enthusiast | Machine Learning Learner
This project is developed for academic and educational purposes.