Abstract ▼ AI-Helper

In this paper, we employ machine learning to predict the performance of Jupyter notebook on JupyterHub. We show that the notebook's CPU profile, the notebook's RAM profile, number of users and average delay between cells are crucial features that impact the performance of the machine l...

In this paper, we employ machine learning to predict the performance of Jupyter notebook on JupyterHub. We show that the notebook's CPU profile, the notebook's RAM profile, number of users and average delay between cells are crucial features that impact the performance of the machine learning models to accurately predict the performance of Jupyter notebook in term of the response time. We characterize the performance of our model to predict the notebook's response time in terms of the mean absolute error (MAE) and mean absolute percentage error (MAPE). Results show that the random forest model yields strongest performance to predict the performance of Jupyter notebook with MAPE equal to 9.849% and MAE equal to 13.768 seconds. with r-square equal to 0.93.