Using Machine Learning to Reduce Human/Medical costs Associated with Diabetes

The aim of this analysis is to build machine learning models to mitigate the medical and human costs associated with diabetes. This is carried out in a three-tier approach listed below: 

1. Is a non-diabetic person at risk of diabetes based on the person's lifestyle choices? 

2. Is a diabetic individual at risk of getting re-hospitalized?

 3. Will the diabetic individual at risk of being re-hospitalized be hospitalized in less than 30 days or more than 30 days?

Deploying Machine Learning Model Using Heroku and Flask App

The aim of this project is to build an interactive web app by deploying a machine learning model using Heroku and a Flask App.

BrainStation - Canada Goose Hackaton 2022.

Participated in the BrainStation - Canada Goose Hackaton to create a new user experience interface that increases customer engagement in the online store.

Big Data Wrangling With Google Books Ngrams

Performed ETL on google n-gram data using AWS, PySpark and Hadoop.


Natural Language Processing of Hotel Reviews

Performed text analysis using natural language processing, count vectorizer, KNN, Decision Tree, and Logistic Regression. Achieved best model accuracy of 89.6%.

Statistical Analysis of the Incidence of West Nile Virus in Chicago

In this project, data from 2008 to 2019 taken at Chicago was analyzed to understand the relationship between the different independent variables and the number of mosquitos, as well as the probability of finding West Nile Virus (WNV) at any particular time and location.


LinkedIn
GitHub