Pranveer Singh Institute of technology β’ 2026
What I'm good at
Showcase of Work
This project presents a comprehensive data analysis framework aimed at uncovering how technical skills, experience levels, job roles, and industry sectors influence salary outcomes within the data science and technology domains. Its central purpose is to help professionals understand which skills yield the highest compensation, how experience affects income growth, and which combinations of competencies offer the greatest market value. The framework implements a complete end-to-end data pipeline that efficiently transforms raw salary data into meaningful, data-driven insights. The process begins with data preparation, where raw CSV datasets containing salary and skill-related information are processed, cleaned, and standardized. The system can automatically import data from Kaggle or generate synthetic data if required. It further extracts key features, normalizes salary information, and prepares analysis-ready datasets. In the statistical modeling phase, the project employs regression-based techniques to quantify the impact of various skills, experience levels, and industry factors on compensation. These models assign measurable values to specific skills, providing an interpretable understanding of their influence on salary variations. The next stage, insight generation, produces detailed analytical reports, model summaries, and visual outputs including correlation matrices, salary-by-skill comparisons, and coefficient impact charts that highlight high-value skill sets. To make insights more accessible, the project incorporates an interactive dashboard built using Dash, which allows users to filter results dynamically by skill, job title, industry, or country and visualize customized insights through engaging, data-rich charts. The projectβs structure reflects strong software engineering practices with a clear separation of modulesβcore data processing and modeling scripts reside in the src directory, visual components in the dashboard directory, datasets in the data folder, and reports in the reports section. Exploratory research and experimental notebooks are also available for deeper exploration. Designed for simplicity and extensibility, the framework allows one-command execution for data preparation, modeling, and dashboard deployment. It supports both sample and custom datasets with comprehensive documentation to assist users in expanding the analysis. Ultimately, this project serves as an intelligent career intelligence platformβempowering data professionals, recruiters, and job seekers to make informed, evidence-based decisions about skill development and salary expectations in the evolving technology landscape.