Smartphone Addiction Risk Prediction Using Machine Learning

Developed a machine learning solution to predict smartphone addiction risk based on users' daily usage behavior. This project was completed as part of the NTI Machine Learning Training Program, covering the full machine learning pipeline from data preprocessing to deployment and visualization.

Key Features

Designed and implemented the end-to-end data preprocessing pipeline.

Cleaned and prepared the dataset for analysis.

Performed Exploratory Data Analysis (EDA) to identify patterns and user behavior trends.

Applied preprocessing techniques including encoding, feature scaling, and train-test splitting.

Engineered new features to improve model performance.

Applied SelectKBest for feature selection.

Applied Principal Component Analysis (PCA) for dimensionality reduction.

Tools & Technologies

Python

Pandas

NumPy

Scikit-learn

Matplotlib

Seaborn

Jupyter Notebook

Project Outcome

As part of a collaborative team, we developed and evaluated multiple machine learning models, built an interactive Streamlit web application for prediction, and created a Power BI Dashboard to visualize user behavior, trends, and key insights.

My Role

Focused on data preprocessing, feature engineering, exploratory data analysis (EDA), feature selection, and dimensionality reduction to prepare high-quality data for machine learning models.