| Field | Details |
|---|---|
| Project Name | US Visa Approval Prediction |
| Prepared By | Md. Alahi Almin Tansen |
| Revision Number | 1.0 |
| Last Revision Date | 02-09-2025 |
| Revision | Date | Changes Made | Author |
|---|---|---|---|
| 1.0 | 02-09-2025 | Initial Draft | Md. Alahi Almin Tansen |
- Requirements
- Anaconda
- Git
- VSCode
- Problem Statement Understanding
- Solution Understanding
- Code Understanding & Walkthrough
- Deployment Understanding
- Predict US visa approval status.
- Features considered:
- Continent, Education, Job Experience, Training, Employment, Age, etc.
- Goal: Predict whether an application will be Approved or Rejected.
- Continent → Asia, Africa, North America, Europe, South America, Oceania
- Education → High School, Bachelor’s, Master’s, Doctorate
- Job Experience → Yes / No
- Training Required → Yes / No
- Number of Employees → 15,000 – 40,000
- Region of Employment → West, Northeast, South, Midwest, Island
- Prevailing Wage → 700 – 70,000
- Contract Tenure → Hour / Year / Week / Month
- Full-Time Position → Yes / No
- Age of Company → 15 – 180
- Helps US visa applicants evaluate their chances.
- Provides insights on what features improve approval chances.
- Machine Learning Classification Algorithms
- Train, Validate, Test on visa application data
- Docker → Containerize application
- Cloud Services → Host ML model & API
- Self-hosted Runner → Automate deployment
- Workflows → CI/CD pipeline
-
Project Workflow
Loadingflowchart TD A[Problem Statement] --> B[Features Dataset] B --> C[Solution Approach: ML Classification] C --> D[Model Training & Evaluation] D --> E[Deployment] E --> F[Docker Container] E --> G[Cloud Services] E --> H[CI/CD Workflows] F --> I[End User Access] G --> I H --> I