Income Prediction App Using Machine Learning with Python

Income Prediction Using Machine Learning

Project Overview

Developed a Machine Learning project to predict whether an individual's annual income is above or below $50,000 based on demographic and employment-related information. The project focuses on applying data preprocessing, feature engineering, and classification techniques to build a predictive model.

The project uses a dataset containing personal and employment-related attributes. Data preprocessing techniques were applied to prepare the dataset for training, including categorical encoding, feature scaling, and target variable transformation.

Several classification models were explored and evaluated, including Logistic Regression and Support Vector Machine (SVM), to compare their performance and identify a suitable approach for salary prediction.

The project also explores classification threshold adjustment and SMOTE to better handle class imbalance and improve the detection of individuals earning more than $50,000.

A Streamlit interface was developed to make the model easier to interact with by allowing users to enter relevant information and receive a salary prediction.

Technologies Used

Python, Machine Learning, Pandas, NumPy, Scikit-learn, Streamlit, Jupyter Notebook, Data Preprocessing, Feature Engineering, and Model Evaluation.

Project Objective

The goal of this project was to gain practical experience in the complete machine learning workflow, from preparing raw data and training classification models to evaluating their performance and building a simple interactive application.

Role: Machine Learning Developer

Project Type: Income Classification and Prediction