Hello there!

I’m a data scientist with a unique background in human psychology. I have extensive experience working with product teams to make better decisions through metrics, experiments, and quantitative user insights. I am proficient with statistical / ML modeling, causal inference, data visualization, and designing ETL pipelines. I like to work at organizations that are mission-driven and aim to make the world a better place.

I currently work at Prodigy Education where I use data science to make learning more fun for kids.

My latest blog posts

Using GPT-4 for classification

In this post, I use GPT-4 to classify US grant-funding agencies into 10 categories using government agency names. Then I summarize funding by category.

Oct 8, 2023

Tyler Burleigh

Encoding high cardinality features with “embeddings”

In this post I show how the performance of an ML model can be improved by encoding high cardinality features using “embeddings”, a method that uses deep learning to represent categorical features as vectors. I compare the performance of embedding encoding with other common categorical encoding methods: one-hot, label, frequency, and target encoding.

Sep 19, 2023

Tyler Burleigh

Using random forest based outlier detection to clean a training dataset

In this post, I explore whether a random forest model can be improved by using random forest based multivariate outlier detection and imputation methods, and by reducing feature multicollinearity. Supporting the common wisdom that random forest models are robust to outliers and multicollinearity, these data cleaning steps led to only marginal improvements in out-of-sample model performance.

Sep 8, 2023

Tyler Burleigh