Finding donors using supervised learning

Spring 2021 - Automation of Scientific Research - course project

Boston Crime Analisys test.

Gradient Boosting Classifier on the Titanic dataset

I applied supervised machine learning models (Decision Trees, Gradient Boosting, Support Vector Machines) on data collected for the US census to help CharityML (a fictitious charity organization) identify/predict people most likely to donate to their cause.

Predicting mammalian taxonomic order based on ecological, geographic, and life-history traits

Fake News Detection Engine using Natural Language Processing and Machine Learning

Detect Fraudulent Credit Card transactions using different Machine Learning models

This project uses machine learning to predict whether a loan applicant will repay their loan. The project uses a dataset of historical loan data from PeerLoanKart, a peer-to-peer lending platform.

Predicting whether a customer will carry out a transaction or not for Santander group

Supervised learning project using Gradient Boosting Classifier

The Office of Foreign Labor Certification is facing a dramatic increase in work visa applications, but is hampered by a sluggish review system. It needs to improve the process by developing a way to quickly, accurately identify applications likely to be accepted or rejected so their processing may be prioritized.

The model should predict whether is it going to rain the next day coming or it isn't. The models that have been deployed were TensorFlow Sequential, Random Forest Classifier and GradientBoostingClassifier. The best model on both training and test set was achieved with Gradient Boosting Classifier with 95.2% and 85.5% accuracy on the train and test.

TOP13% solution for the Titanic-Kaggle competition using a Gradient Boosting Classifier. Moreover, implementation of a Streamlit App to play with the models.

Predicting short-term IPO returns. Course work for CSCI-B351 at Indiana University.

Comparative Analysis of Decision Tree Algorithms in Number Classification: Bagging vs. Random Forest vs. Gradient Boosting Decision Tree Classifiers

Final project for Data Modeling & Machine Learning course

Our project utilizes machine learning models to predict cardiovascular diseases (CVDs) by analyzing diverse datasets and exploring 14 different algorithms. The aim is to enable early detection, personalized interventions, and improved healthcare outcomes.

Utilizing machine learning models including logistic regression, random forest, gradient boosting, and neural networks to identify fraudulent credit card transactions. Dataset, consisting of PCA-transformed features and unbalanced classes, required precision-recall metrics for accurate evaluation. Developed in Python using TensorFlow and scikit.

Repository for SLC projects