GYM CROWDEDNESS ANALYSIS
Given a time of day (and maybe some other features, including weather), predict how crowded the gym will be.Figure out which features are actually important, which are redundant, and what features could be added to make the predictions more accurate.
The dataset consists of 26,000 people counts (about every 10 minutes) over the last year. In addition, I gathered extra info including weather and semester-specific information that might affect how crowded it is. The label is the number of people, which I'd like to predict given some subset of the features. The project aims to tell us the various factors that are important in predcting the best time. By this we hope to regulate crowd.
As expected, there are quite a few fluctations based on day, month and hour. The weekend, summer, and early morning seem to be the less crowded times. According to the plots and t-tests of the binary variables above, data suggest the gym is more crowded during the semester, at the start of the semester, and during the week (versus weekend).
From the EDA we know :
- Weekdays around lunch or in the early afternoon
- Late at night (past 8 pm if your gym is still open)
- Weekends in the mid to late afternoon
If you have a flexible schedule, I would highly recommend going to the gym around mid-day (lunchtime) or late at night, if your gym is open.
If not, you’ll probably be better off with the crowds if you go in the morning instead of the evening. In any case, just be prepared to deal with a little bit of waiting for equipment. Ask to work in, be polite, and mix up your exercises to make sure you can always get in a good workout, no matter how busy things get.