https://github.com/omkarpattnaik8080/employeeretentionprediction

"This machine learning project predicts employee retention, employing Python and scikit-learn. Utilize AWS for model deployment, ensuring scalability and reliability. Explore predictive analytics to identify factors influencing employee turnover, facilitating proactive retention strategies for organizational stability and growth."
https://github.com/omkarpattnaik8080/employeeretentionprediction

aws data-science machine-learning matplotlib numpy pandas seaborn

Last synced: 1 day ago
JSON representation

"This machine learning project predicts employee retention, employing Python and scikit-learn. Utilize AWS for model deployment, ensuring scalability and reliability. Explore predictive analytics to identify factors influencing employee turnover, facilitating proactive retention strategies for organizational stability and growth."

• Host: GitHub
• URL: https://github.com/omkarpattnaik8080/employeeretentionprediction
• Owner: omkarpattnaik8080
• Created: 2024-03-03T15:03:22.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-04-08T13:59:22.000Z (7 months ago)
• Last Synced: 2024-04-08T14:59:25.496Z (7 months ago)
• Topics: aws, data-science, machine-learning, matplotlib, numpy, pandas, seaborn
• Language: Jupyter Notebook
• Homepage:
• Size: 5.21 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Employee-Retention-Prediction

----

- Employee Retention Prediction using Machine Learning

### Project Abstaction

- Project's main is to predict that whether an employee will stay in the current organization or will left the organization by processing on given inputs.

- RanmForest Classification and XGBoost these algorithms are use to train the model.

- XGBoost gives the best model prediction from both algorithms.

- Model is exposed using the REST API which is constructed in Flask and Python.

- Project also process on old and failed data and it will create archive files on those datasets.

- Prediction and Training logs can be visualized using the ELK + Filebeat.

- Matrices from projects can be visualized through the Prometheus and Grafana.

### Project's Tools and Technology

- **Programing Language:** Python

- **Web Development Framework:** Flask

- **Machine Learning Libraries:** Scikit-Learn, Pandas, Numpy, Matplotlib, XGBoost

- **Machine Learning Algorithm:** KMeans, Random Forest and XGBoost

- **Container Technology:** Docker

- **Log Management System:** ElasticSearch, Logstash, Kibana, Filebeats

- **Metrics Monitoring System:** Prometheus, Grafana

- **Database:** SQLite3

### ELKStack Pipline in Brief

- Filebeat will collect the prediction and training logs from project and will transfer the logs to logstash.

- Logstash will process those logs and forward to ElasticSearch.

- At ElasticSearch, I have created index name as `logstash-*` which will give us the logs.

- Kibana is used to visualize logs from above index.

### Running the Project

- Create virtual environment

- Install dependancies from `requierments.txt`

    `pip install requirements.txt`

- Run `python main.py` inside App folder.

- You can also run project as Docker Container by building docker image.

    `docker build -t  .`

### Thank You!