Yulu is India's leading micro-mobility service provider, offering eco-friendly and convenient vehicles for daily commutes. With a mission to eliminate traffic congestion, Yulu provides shared, solo, and sustainable commuting solutions through a user-friendly mobile app.
Yulu zones are strategically located near metro stations, bus stands, residential areas, office spaces, and other key locations to make first and last-mile connectivity smooth, affordable, and convenient.
Recently, Yulu has faced significant revenue dips and has engaged a consulting team to identify the factors driving the demand for their shared electric cycles in the Indian market.
The primary goals of this analysis are to:
- Identify significant variables that influence the demand for shared electric cycles.
- Evaluate how well these variables explain the overall demand.
The dataset contains data on daily electric cycle rentals and related environmental and seasonal factors.
Key Features:
datetime: Date and time of observation.season: Season of the year (1: Spring, 2: Summer, 3: Fall, 4: Winter).holiday: Whether the day is a holiday (0 = No, 1 = Yes).workingday: Whether the day is a working day (0 = No, 1 = Yes).weather: Weather conditions categorized as:- 1: Clear, Few Clouds, Partly Cloudy
- 2: Mist, Cloudy, or Few Clouds
- 3: Light Snow or Rain
- 4: Heavy Rain or Snow
temp: Temperature in Celsius.atemp: Perceived temperature in Celsius.humidity: Humidity percentage.windspeed: Wind speed.casual: Count of casual (non-registered) users.registered: Count of registered users.count: Total rental bike count, including both casual and registered users.
- Visualized relationships between demand (
count) and features likeseason,weather,temp, andwindspeed. - Performed Bi-Variate Analysis to uncover trends and correlations.
- 2-Sample t-Test: Compared means of bike rentals across different groups (e.g., holidays vs. working days).
- ANOVA: Assessed differences in bike demand across seasons.
- Chi-Square Test: Evaluated relationships between categorical variables such as
weatherandseason.
- Seasonal variations significantly impact demand, with higher rentals observed in fall and summer.
- Weather conditions have a noticeable effect, with clear weather driving higher demand.
- Working days tend to see more registered users, while holidays attract more casual users.
-
Seasonality in Demand:
- Rentals peak during favorable weather conditions (fall and summer seasons).
-
Weather Influence:
- Clear weather positively correlates with increased bike rentals, while heavy rain or snow significantly reduces demand.
-
User Behavior:
- Registered users contribute consistently higher rentals on working days, while casual users drive demand on holidays.
This project utilized the following tools:
- Python:
Pandasfor data manipulation.MatplotlibandSeabornfor data visualization.ScipyandStatsmodelsfor statistical testing.
- Jupyter Notebook: For interactive analysis and documentation.
data/: Contains the dataset used for analysis.notebooks/: Jupyter Notebooks documenting the analysis process.visualizations/: Saved plots and charts.README.md: Overview of the project (this file).
Future work could include:
- Feature Engineering: Derive new features (e.g., lag variables or rolling averages) to enhance predictive insights.
- Predictive Modeling: Use machine learning models to forecast bike demand.
- Deep Dive into User Segments: Analyze behavioral patterns across casual and registered users for targeted marketing strategies.
- Dataset Source: Provided by Scaler for this analysis.
- Python Libraries: Thanks to the open-source Python community for providing versatile data analysis tools.
This project is licensed for educational and non-commercial use only. If utilizing any part of this repository, please credit the author.