🧠 Multimodal Fake News Detection (NLP + Computer Vision)
- Built a multimodal fake news detection system combining textual and visual information.
- Designed an independent text pipeline using NLP preprocessing, TF-IDF feature extraction, and machine learning classifiers.
- Designed an independent image pipeline using CNN-based feature extraction for visual representation.
- Implemented late fusion to combine text-based and image-based predictions into a final classification decision.
- Structured the solution as a modular ML pipeline suitable for experimentation and extension.
- Evaluated model performance using standard classification metrics such as accuracy, precision, recall, and F1-score.
Technologies: Python, NLP, Computer Vision, TensorFlow, Scikit-learn
🛒 Customer Segmentation for Online Retail Using Machine Learning (03/2023 – 05/2023)
- Performed customer segmentation using unsupervised learning techniques on online retail data.
- Applied K-Means and Hierarchical Clustering to identify distinct customer groups.
- Used Elbow Method and Silhouette Score to determine optimal cluster count.
- Generated actionable insights to support targeted marketing strategies.
Technologies: Python, Pandas, Scikit-learn, K-Means, Hierarchical Clustering
🔗 View Code
🚲 Bike Sharing Demand Forecasting Using Machine Learning (01/2023 – 03/2023)
- Built machine learning models to forecast daily bike rental demand.
- Performed feature engineering and time-based analysis on historical usage data.
- Trained regression models including Linear Regression, Decision Trees, and ensemble methods.
- Evaluated model performance to support demand planning and operational decisions.
Technologies: Python, Scikit-learn, Pandas, Regression Models
🔗 View Code
📱 Predicting Mobile Price Ranges with Machine Learning Models (10/2022 – 12/2023)
- Developed classification models to predict mobile price ranges from hardware specifications.
- Performed data preprocessing, feature engineering, and normalization.
- Trained and evaluated models including Random Forest and XGBoost.
- Improved model accuracy through hyperparameter tuning.
Technologies: Python, Scikit-learn, XGBoost, Classification Models
🔗 View Code
📊 Exploratory Data Analysis of Hotel Booking Trends (08/2022 – 09/2022)
- Performed exploratory data analysis on hotel booking datasets.
- Analyzed booking trends, cancellation patterns, and customer behavior.
- Created visualizations to derive insights for pricing and occupancy optimization.
Technologies: Python, Pandas, Matplotlib, Seaborn
🔗 View Code
🏥 IoT-Based Patient Monitoring System for Healthcare (09/2020 – 02/2021)
- Developed a real-time patient monitoring system using IoT sensors.
- Collected vital parameters such as heart rate and body temperature.
- Enabled remote monitoring through cloud-based dashboards.
- Implemented alert mechanisms for abnormal health conditions.
Technologies: Arduino, IoT Sensors, Python, Firebase