Seoul_Bike_Sharing_Demand_Prediction Currently Rental bikes are introduced in many urban cities for the enhancement of mobility comfort. It is important to make the rental bike available and accessible to the public at the right time as it lessens the waiting time. Eventually, providing the city with a stable supply of rental bikes becomes a major concern. The crucial part is the prediction of bike count required at each hour for the stable supply of rental bikes.
Attribute Information:
1.Date: The date of each observation in the format 'year-month-day'
2.Hour: Hour of the day
3.Temperature: Temperature recorded in the city in Celsius (°C).
4.Humidity: Relative humidity in %
5.Wind speed: Speed of the wind in m/s
6.Visibility: measure of distance at which object or light can be clearly discerned in units of 10m
7.Dew point temperature: Temperature recorded in the beginning of the day in Celsius(°C).
8.Solar radiation: Intensity of sunlight in MJ/m^2
9.Rainfall: Amount of rainfall received in mm
10.Snowfall: Amount of snowfall received in cm
11.Seasons: Season of the year (Winter, Spring, Summer, Autumn)
12.Holiday: Whether the day is a Holiday or not (Holiday/No holiday)
13.Functional Day: Whether the rental service is available (Yes-Functional hours) or not (No-Non functional hours)
14.Rented Bike count: Count of bikes rented at each hour (target variable)
Conclusions:
-
Bike rental count is mostly correlated with the time of the day as it is peak at 8 am morning and 6 pm at evening.
-
We observed that bike rental count is high during working days than non-working day.
-
We see that people generally prefer to bike at moderate to high temperatures and when little windy.
-
It is observed that highest number bike rentals counts in Autumn & Summer seasons & the lowest in winter and spring season.
-
We observed that the highest number of bike rentals on a clear day and the lowest on a snowy or rainy day and also increasing humidity, the number of bike rental counts decreases.