Problem

We wanted to develop a predictive model for a particular restaurant dataset that could help identify which factors were most strongly correlated with negative reviews or positive reviews. However, we also knew that developing an accurate model would be challenging given the complexity of the data and the large number of potential variables.

Solution

To address this challenge, we developed various models using libraries such as NumPy, Pandas, and Scikit Learn. We gathered data on customer reviews from various sources and identify key variables that might be driving negative ratings.

We then conducted a comparative analysis of the performance of the machine learning models, including simple linear regression, random forest, neural networks, gradient boosted trees, and AdaBoost, in order to determine to best model. Ultimately, we determined that Random Forest, Neural Network, and Gradient Boost model performed best.

Simple Linear Regression

Random Forest

Neural Network

Gradien Boosted Trees

AdaBoost

Team

Ysee Duras, Angele Dutilleul, Amaury Faivre, David James Wei Liang Scuba, Maylee Tan, and Kayla Hoang Le

Prediction of Restaurant Rating