What it does
This project explores the use of machine learning techniques to predict the noise levels based on their frequency, angle of attack, chord length, free-stream velocity and suction side displacement thickness.
How we built it
The project involves data visualization, exploration, and preprocessing, followed by the splitting of the dataset into training and test sets. The performance of the gradient boosting model is evaluated using rsme and r2 score, with results compared to other models such as linear regression and gradient boosting.
Challenges we ran into
The project also faced several challenges during the modeling process, such as low RSME, skewness of data and outliers. However, the team was proud of the accomplishments achieved, including the successful implementation of gradient boosting to achieve better performance.
Accomplishments that we're proud of
Through the project, the team gained valuable insights into the workings of gradient boosting, linear regression and grid search as well as the importance of data preprocessing.
What's next
The next steps may involve exploring other machine learning models, experimenting with different hyperparameters, or conducting additional feature engineering to improve model performance.
Log in or sign up for Devpost to join the conversation.