Predicting user intents
The problem: Apple's default Clock app, if opened from the app switcher menu (the one you see when swiping from the bottom of the screen upward), always shows the Timer tab. I personally use this app mostly for one reason every day—to set an alarm clock, which is in a different tab. By knowing the day of the week and time of the day, it's easy to make the app smarter (and less annoying) by opening the proper Alarm tab when needed and default tab otherwise. For this, we will need to collect historical records on what time we usually set an alarm on different days.
Let's formulate the task more precisely:
- Input data: The day, hour, and minute when the user had opened the application
- Expected output: The probability that the user wants to set up an alarm
The task is of binary classification, which makes logistic regression a perfect candidate for the solution.
Handling dates
The straightforward way to transform dates and time into numerical features is by replacing them with...
