Auto-Insurance-Fraud-Detection
This research goal is to build binary classifier model which are able to separate fraud transactions from non-fraud transactions.
- 26
- HTML
- 3 y ago
This research goal is to build binary classifier model which are able to separate fraud transactions from non-fraud transactions.
Developed and evaluated machine learning and deep learning models for detecting financial fraud.
Machine learning model for predicting the drone deployment for the smart agriculture use case. Developed in collaboration between University College Dublin (UCD) and Augmenta (acquired by CNH Industrial) for the EU MLSysOps project.
Data Science Challenge from Coursera Project : Loan Default Prediction
Data Science Challenge from Coursera Project : Churn Prediction
This project explores the Framingham Heart disease dataset with the objective to predict its risk in 10 years. Various methods for handling missing values and outliers are explored as iterations. After analysing the dataset, important and necessary features are selected. Seven ML models are implemented, with evaluation on the basis of Test Recall.
Train CatBoost & XGBoost on 59K data to predict the probability that an online transaction is fraudulent
LedgerGuard: Neo-bank Fraud Detection and Transaction Categorisation System || Tech Stack: Python 3.11, Django, pandas, scikit-learn, Matplotlib, sentence-transformers (MiniLM), PyTorch, LightGBM, XGBoost, imbalanced-learn, pytest, factory_boy, GitHub Actions, Docker, Gunicorn, Render
This script creates a ML model, utilizing an XGBoost classifier, to predict the likelihood of an individual developing cervical cancer. The script asks the user for their age, smoking status, age of first sexual intercourse, number of pregancies, and IUD status and then predicts their risk of cervical cancer based on the model output.
Exploring a collection of Jupyter notebooks showcasing a variety of Natural Language Processing (NLP) projects.