This is a project to predict the demand for shared bikes using multiple linear regression, assisting Boombikes in regaining financial stability after COVID-19 pandemic.
Boombokes is a bike sharing service in United States, experienced challenges to maintain steady revenue due to covid-19 pendemic. To recover from the financial setbacks and rebuild profitability it aims to better understand the dynamics behind bike rental demand. By analysing historical rental patterns, it tried to seek insights which will guide them in optimizing their operations, attracting more customers, and boosting profitability in the post-pandemic era.
Here the target variable is cnt(total rental count), represents the sum of total casual and registered users for each day. Predictor variables include temperature, humidity, wind speed, season, month , working day or holiday ect.
Goal: Use the insights to develop predictive models that accurately estimate future rental demand based on given conditions
- The demand for shared bikes is influenced significantly by weather conditions, temperature, and seasonality.
- Higher demand is observed on working days compared to holidays.
- The trend shows an increasing demand over the years, highlighting the growing popularity of shared bikes.
- Key predictors like
yr,temp, andweathersitcan guide effective business strategies.
- Python: Programming language for data analysis and modeling.
- Pandas: For data manipulation and analysis.
- NumPy: For numerical computations.
- Matplotlib & Seaborn: For data visualization.
- Scikit-learn: For implementing the linear regression model and evaluating performance.
Give credit here.
- References:
- The dataset was provided by BoomBikes.
Created by [@githubusername] - feel free to contact me!