Aspiring Data Scientist

Hello, I'm Khadeeja

Data Science graduate student at Aligarh Muslim University with hands-on experience in machine learning, deep learning, and NLP. Skilled in Python, R, and the full ML stack from data preprocessing to model evaluation. Passionate about building reliable, data-driven solutions to real-world problems.

View Projects Download CV

About Me

Building practical machine learning solutions

I am currently pursuing an M.Sc. in Data Science at Aligarh Muslim University. My work blends statistics, machine learning, deep learning, NLP, and data visualization to solve real-world analytical problems with clarity and rigor.

Education

M.Sc. Data Science
Aligarh Muslim University, 2024 - 2026

B.Sc. (Hons) Statistics
Aligarh Muslim University, 2021 - 2024

Experience

Data Analyst Intern
Green Genius Enviro Solutions | Mar 2025 - Jun 2025

Engineered IoT data pipelines, improved data quality through preprocessing and feature extraction, and created 5+ interactive Tableau dashboards for environmental assessment insights.

Technical Skills

Skills & Tools

Languages

Python, R, SQL

ML & Deep Learning

Scikit-Learn, TensorFlow, Keras, XGBoost, Random Forest, SVM, Logistic Regression, Naive Bayes, ANN, KNN

Data Engineering

Pandas, NumPy, SMOTE, Feature Engineering, Data Cleaning, Preprocessing, MySQL

NLP

Text Preprocessing, Tokenization, TF-IDF, Word Embeddings, Text Classification, Transformers, LLMs

Visualization & Tools

Tableau, Matplotlib, Seaborn, Jupyter Notebook, Google Colab, Git/GitHub, VS Code, Excel, LaTeX

Projects

Featured Work

Multimodal Fake Review Detection System [In Progress]

Designing a multimodal deep learning pipeline to detect fake reviews by jointly processing textual review content and associated product images. Uses BERT for text understanding and ResNet-50 for visual feature extraction, followed by fusion through a neural network classifier.

Parkinson's Disease Detection - Multi-Model ML Pipeline

Engineered and benchmarked 7 machine learning classifiers on biomedical voice measurements for early Parkinson's detection. Applied SMOTE for class imbalance and achieved top performance with ANN: 97% accuracy, 100% precision, 97% recall, F1-score 0.98, and ROC-AUC 0.98.

Impact of Social Media on Student Mental Health - Statistical Study

Conducted a stratified random sampling survey of 200 students at Women's College, AMU. Built structured questionnaires, analyzed the findings in R, and identified statistically significant impacts on academics, loneliness, sleep, focus, and emotional well-being.

Get In Touch

Contact Me

Location

Aligarh, India

Resume

Download CV

I am open to internships, research collaborations, and data science opportunities involving machine learning, analytics, NLP, and applied statistics.

""" out = Path("/mnt/data/index_updated.html") out.write_text(html, encoding="utf-8") print(f"Saved: {out}")