Bike Sharing Prediction

A Linear regression machine learning model to predict the growth of Bike sharing market for Boom Bikes.

Bike-sharing Service

The bike-sharing system is a service in which bikes are made available for shared use to individuals on a short-term basis for a price or free. Many bike share systems allow people to borrow a bike from a computer-controlled dock, where a user can enter the payment information for the system to unlock it. The user can further return the bike to any other computer-controlled dock belonging to the same system.

Case of BoomBikes

BoomBikes is a US-based bike-sharing provider. It has recently suffered considerable dips in its revenues due to the ongoing Corona pandemic and is finding it very difficult to sustain itself in the current market scenario. They have decided to align their future business with a Machine Learning based model to recover from the current business scenario once lockdown ends. They aspire to understand the demand for shared bikes among the people after the quarantine situation ends. They have planned this to prepare themselves to cater to the people’s needs once the situation gets better all around and stand out from other service providers and make huge profits.

Project Goal

With this project, we will try:

  1. To understand the factors on which the demand for these shared bikes depends.
  2. To identify the variables that are significant in predicting the demand for shared bikes.
  3. To understand how well a variable describes the bike demands if a Variable is significant.

Business Goal:

With this Machine Learning project, we will try to model the demand for shared bikes with the available independent variables.

This model can be used by the management to understand how exactly the demands vary with different features. They can accordingly manipulate the business strategy to meet the demand levels and meet the customer’s expectations. Further, the model will be a good way for management to understand the demand dynamics of a new market.

Final Model

  1. The user count is highly dependent on Teperature or Apparent Temperature.
  2. The number of bike user has increased relatively from past year, evident that the business have a better opportunity in coming years.
  3. The business needs to improve their strategy, towards end and start of the year, considering the weather and season factor, the business is hit on this part of the year.
  4. The business on holidays are relatively better than on a workingday, the working day business can be improved with the docks being built near office permises.
  5. The windspeed and light rain weathers are quite impacting the business, and boom bike needs to look for improvements in this area.

- The R2 score of training and test data are 83.6 and 81.6 respactively, which is quite good.

Overall we have a decent model showing a positive growth as we see the increase in business up the coming years, though it is understandable that some external factors like pandemic after effect, entry of low budget vehicles will impact the business in future.