Salifort Motors project
This random forest model helps predict whether an employee will leave the company and identify which factors are most influential. These insights can help HR make decisions to improve employee retention.
Projects
Tik Tok project
TikTok videos receive a large number of user reports for many different reasons. Not all reported videos can undergo review by a human moderator. Videos that make claims (as opposed to opinions) are much more likely to contain content that violates the platform’s terms of service. TikTok seeks a way to identify videos that make claims to prioritize them for review.
Automatidata project
The New York City Taxi and Limousine Commission seeks a way to utilize the data collected from the New York City area to predict the fare amount for taxi cab rides. I used two different modeling architectures and compared their results. Unfortunately, neither approach delivered strong predictions.
Wase project
To obtain a model with the highest predictive power, I developed two different models to cross-compare results: random forest and XGBoost. To prepare for this work, the data was split into training, validation, and test sets. Splitting the data three ways means that there is less data available to train the model than splitting just two ways. However, performing model selection on a separate validation set enables testing of the champion model by itself on the test set, which gives a better estimate of future performance than splitting the data two ways and selecting a champion model by performance on the test data.
