Michael Harmon

Data: NYC Open Data
Techniques: Polars, DuckDB, SQL, Docker, AWS
Date: July, 2023

Data: JFK Library Website
Techniques: Tensorflow, Keras, Gate Reccurent Units (GRUs), Recurrent Neural Networks
Date: April, 2023

Data: JFK Library Website
Techniques: Web Scraping, BeautifulSoup, Google Cloud
Date: Dec, 2022

Data: arxiv.org
Techniques: Deep Learning, CNN, NLP, Tensorflow, Keras, Optuna
Date: Nov, 2022

Data: Synthetic
Techniques: K-Means clustering, NumPy, Scikit-Learn
Date: May, 2022

Data: Synthetic
Techniques: Scala, Py4J, PyMC3, Maximum Likelihood & Bayesian Methods
Date: May, 2021

Data: arxiv.org
Techniques: FastAPI, Bootstrap, Docker, Google Cloud Run
Date: Oct, 2020

Data: NYC Mayor's Office Of Sustainability
Techniques: Scikit-learn, XGBoost, MLflow, Docker, Google App Engine
Date: April, 2020

Data: NYC Mayor's Office Of Sustainability
Techniques: Scikit-learn Imputers, BigQuery, K-Nearest Neighors.
Date: Feb, 2020

Data: arxiv.org
Techniques: Natural Language Processing, Hyperparameter tunning
Date: Jan, 2020

Data: arxiv.org
Techniques: Naive Bayes, Imbalanced-Learn, Weighted Support Vector Machines
Date: Jan, 2020

Data: NYC Mayor's Office Of Sustainability
Techniques: Regression, Alternating Least Squares, Cholesky & Singular Value Decomp.
Date: Dec, 2019

Data: Twitter
Techniques: Sentiment Analysis, Apache Spark, ML Pipelines, Google Cloud
Date: May, 2019

Data: Twitter
Techniques: Extract-Transform-Load, Apache Spark, MongoDB, PyMongo
Date: April, 2019

Data: NYC Mayor's Office Of Sustainability
Techniques: Exploratory data analysis, outlier removal, isolation forests
Date: May, 2018