The goal of this project is to build a machine learning model that automatically classifies emails as spam (unwanted) or ham (legitimate). The model will be trained on a labeled dataset and use features extracted from the email content to predict whether an email is spam or not.

Machine Learning project for Kaggle’s Titanic: Machine Learning from Disaster competition. Achieved 0.76555 public leaderboard score using advanced feature engineering and Random Forest Classifier.

Machine Learning System Development - Diabetes Prediction

In this project, I use several different classification algorithms to predict whether a patient has breast cancer or not. This project uses K-fold cross validation, logistic regression, LDA, QDA, SVM, and model tuning techniques to achieve a 96% accuracy rate. This project was completed via R Markdown and LaTex.

this project was inspired by Aurélien Géron's Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, where he performs detailed analysis on the Housing dataset. Motivated by that, I explored and applied similar machine learning techniques on the Student Habits and Academic Performance dataset to predict exam scores.

Basic iterative hyperparameter search algorithm for custom models and training loops.

This project develops a machine learning model to detect fraudulent bank account applications using synthetic financial data, identifying key fraud indicators like device_os_windows and applicant residency history. Dataset Source: https://www.kaggle.com/datasets/sgpjesus/bank-account-fraud-dataset-neurips-2022

King County Housing Price Predictions is a start-to-finish regression project which concludes with a stacked model.

Build deep learning model for detecting hand gestures for Smart TVs using CNN and RNN

Comprehensive implementation of an Applied Machine Learning model for Diabetes Prediction. The project aims to leverage machine learning techniques to predict the likelihood of an individual developing diabetes based on various health and lifestyle factors.

The project was accomplished by employing supervised learning, ensemble modeling, and unsupervised learning techniques to build and train a prediction model to identify Pass/Fail yield of a particular process entity for a semiconductor manufacturing company.

Model Tuning: Collaborated with "ReneWind," a company focused on enhancing wind energy production through machine learning. Analyzed sensor data on turbine generator failures, developed and tuned various classification models, and evaluated their performance to select the most accurate one for predicting failures and minimizing maintenance costs.

In this project we're going to explore a workflow to easily compete in the Kaggle Titanic competition, using a pipeline of functions to reduce the number of dimensions you need to focus on.

This repository performs automated parameter optimization to maximize calcium Ca2+ influx in the trunk of a CA1 pyramidal neuron model while minimizing calcium influx in oblique dendrites, using the Optuna framework for hyperparameter tuning.

Applied reinforcement learning to build a simulated vehicle navigation agent. This project involved modeling a complex control problem in terms of limited available inputs, and designing a scheme to automatically learn an optimal driving strategy based on rewards and penalties.

Machine learning prediction project, R studio, 2019.

This linear regression model tuning is an exercise for a Data Science Online Bootcamp.

Recommender Systems 2021/2022: Content Based Recommenders Project

Built an algorithm to identify canine breed given an image of a dog. If given image of a human, the algorithm identifies a resembling dog breed.