Machine Learning Engineer
Other Industry Projects ⭐💡
Support Mails Classification Project-(Oct-2023)
- Utilizing the Imap-tools Python module, this project involves logging into a support mailbox, downloading emails, and extracting attachments. The emails will be classified into four categories based on their subjects.
- The classified emails will then be organized into their respective categories, and automatic forwarding and replies will be implemented.
- Using Plotly, Dash, matplotlib, and seaborn libraries to make interactive visualizations and create dashboard as web application with a REST API as a data source, performed data wrangling with Pandas, and deployed web application on a cloud server.
- Libraries Used: Plotly, Dash, matplotlib, seaborn
Implementing Face Recognition for Member Authentication process-(Sept-2023)
- FastAPI used to build APIs for registering member faces and conducting authentication checks.
- MediaPipe employed for face detection, and the face-recognition module utilized for face Recognition.
Create a Windows Desktop App for Automation-(May-2023)
- Created application for quick task automation. Developed an application to pattern-based file path retrieval, copying files to specified destinations from an Excel reference. Integrated PySimpleGUI for an attractive GUI and used pyinstaller module for creating a desktop executable.
Machine Learning Projects 🎰💡
Real Estate Property Price Prediction | GitHub
- Technologies Used: Machine Learning, NLP, Statistics
- Developed a machine learning model for real estate price prediction using ensemble methods, with preprocessing and feature engineering applied to text features through NLP techniques.
- Created and deployed a FastAPI web application to serve the model as an API service for real-time price estimates.
Vehicle Insurance Cross-Sell Prediction | GitHub
- Executed data preprocessing, exploratory data analysis, feature selection, and hyperparameter tuning.
- Trained and tested various statistical and tree-based machine learning algorithms.
Credit Default Risk Prediction Model | GitHub
- Developed a predictive model using LightGBM to identify loan defaulters and minimize loss risk based on credit history, employment, and demographic data.
- Optimized model parameters and performed feature importance analysis and model explanation to ensure robust and interpretable predictions.
Credit Card Default Prediction Using Machine Learning | GitHub
- Developed a classification model to predict future serious delinquencies in borrowers using logistic regression and tree-based algorithms such as RandomForest, LightGBM, and XGBoost.
- Conducted feature importance analysis and hyperparameter tuning. Selected LightGBM as the optimal model based on superior recall. Enhanced model interpretability using SHAP and LIME.
Legitimate claim detection system | GitHub
- Data collection, Data Preprocessing and Exploratory data analysis. Feature Engineering, Feature Selection and Feature transformation, Hyperparameter tuning and deploy best performing ML model.
- Predict the legitimacy of insurance claims.
NLP Projects 🔉💡
Medical Embeddings and Clinical Trial Search Engine | Github
- Technologies Used: Python, Gensim, Word2Vec, FastText, Streamlit
- The Project aims to train SkipGram and FastText Models on COVID-19 Clinical Trials Dataset and builds a Search Engine where user can type any COVID-19 related keyword and it presents all the top n similar results from the dataset
Computer Vision Projects 🖥️🤖
Python Projects ⭐💡
- Technologies Used: Python, Regex, OpenCV, Pytesseract, FastAPI
- Python backend was built using pytesseract, OpenCV, Regular expressions and FastAPI as a web serving framework