Team Members

• Ifeoluwa Kayode
• Avinesh Agrawal
• Ashutosh Misra

Problem Description + Focus

For our project, we have chosen the Stack Exchange API. It has been found that, at times, users experience issues with longer response times. Our project aim is to utilize data from the Stack Exchange API and analyze question posting times in correspondence to their respected response times.

Analytics Plan

• Concerning this issue, we aim to utilize machine learning models within H2O AutoML to predict the maximum time users may wait for responses. With these predictions, estimations can be made and further recommendations to allay user expectations.

• Data will be gathered from diverse endpoints on the Stack Exchange API from which a data frame will be constructed. Cleaning and pre-processing of the data
  will be conducted for the sake of insights, adhering to tidy principles using tidyverse.

Evaluation Plan

• Ggplot 2 will be implemented to visualize the data, thus facilitating comprehension of variable relationships and distributions. Finally, different data modeling techniques will be employed to predict outcomes, i.e. time duration of user response.

• The data set will be partitioned into training and testing subsets to compare predicted outcomes against actual results. For the sake of evaluation, criteria such as precision, root mean squared error (RMSE), R-squared, and the like will enable us to gauge the model’s effectiveness.