NPS Order Date Predictions
- Category: Python Machine Learning and Data Mining Application
- Client: Graduate Level Data Mining Project
- Project date: 08/22 - 12/22 (4 months)
- Project URL: https://colab.research.google.com/drive/1qyeKkiBjqFPgz-oxBNxtWDC-kweA90ZW?usp=sharing
Project Stack
- Python - Project was developed using Python for ML
- pandas - Data manipulation used to format and organize raw data from data mining
- scikit-learn - ML library used to apply machine learning models to data
- seaborn - Data visualization tool used to visualize data
- Linear Regression, K-Nearest Neighbors, Random Forest Classification
My Role
Machine Learning and Data Engineer
I performed the following duties:
Brainstormed idea for unique machine learning project idea, took lead role for data mining technique of retrieving raw data (~20 million data points) from NPS website. Teamed up with other team member to perform machine learning models on our data.
Data Mining Lead: Took the lead position of retrieving roughly 20 million rows and 200 columns of raw data from the National Park Service website and parsed the information to useable useful data to model from.
Machine Learning Engineer: Applied machine learning techniques by performing a supervised linear regression model (80/20 split) in attempts to predict campground reservation order dates.