{"id":25049320,"url":"https://github.com/zuzann18/uber-demand-analysis","last_synced_at":"2025-03-31T03:32:24.776Z","repository":{"id":275409602,"uuid":"925999320","full_name":"zuzann18/Uber-Demand-Analysis","owner":"zuzann18","description":" Uber Demand Analysis in NYC  | Time Series Analysis, Data Visualization, Correlation Analysis, Feature Engineering | Exploring the impact of weather, holidays, and location using Python (Pandas, NumPy, Matplotlib, Seaborn), Jupyter Notebook. ","archived":false,"fork":false,"pushed_at":"2025-02-02T13:43:18.000Z","size":2591,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-10T16:17:11.640Z","etag":null,"topics":["demand-forecasting","time-series-analysis"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zuzann18.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-02T09:43:02.000Z","updated_at":"2025-02-02T13:43:21.000Z","dependencies_parsed_at":"2025-02-02T10:28:29.444Z","dependency_job_id":"30f82b7d-3b97-4438-916f-181743a23669","html_url":"https://github.com/zuzann18/Uber-Demand-Analysis","commit_stats":null,"previous_names":["zuzann18/-uber-demand-analysis"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zuzann18%2FUber-Demand-Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zuzann18%2FUber-Demand-Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zuzann18%2FUber-Demand-Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zuzann18%2FUber-Demand-Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zuzann18","download_url":"https://codeload.github.com/zuzann18/Uber-Demand-Analysis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246413377,"owners_count":20773053,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["demand-forecasting","time-series-analysis"],"created_at":"2025-02-06T08:17:38.630Z","updated_at":"2025-03-31T03:32:24.759Z","avatar_url":"https://github.com/zuzann18.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Uber Demand Analysis\n\n##  Project Overview\nThis project analyzes Uber ride demand in New York City, identifying key factors influencing ride pickups. The goal is to extract actionable insights that can help Uber optimize its operations based on weather conditions, holidays, and location-based trends.\n\n## Objectives\n- Determine the most significant factors affecting demand.\n- Provide recommendations for Uber management to capitalize on demand fluctuations.\n\n## Dataset Description\nThe main dataset initially contained over 10 million observations aggregated per hour and borough. After merging with additional datasets, it resulted in **29,101 observations across 13 variables**, including:\n\n- **pickup_dt**: Date and time of the pick-up.\n- **borough**: NYC borough.\n- **pickups**: Number of pickups in a given period.\n- **spd**: Wind speed (mph).\n- **vsb**: Visibility (miles).\n- **temp**: Temperature (°F).\n- **dewp**: Dew point (°F).\n- **slp**: Sea level pressure.\n- **pcp01**: 1-hour liquid precipitation.\n- **pcp06**: 6-hour liquid precipitation.\n- **pcp24**: 24-hour liquid precipitation.\n- **sd**: Snow depth (inches).\n- **hday**: Holiday indicator (Y/N).\n\n---\n\n## 📊 Key Findings\n\n### 1️⃣ Influence of Weather\n- **Temperature** has a significant positive correlation with ride demand. **Higher temperatures lead to more Uber rides.**\n- **Precipitation (rain \u0026 snow)** negatively impacts pickups. **Bad weather reduces demand due to reduced mobility.**\n- **Visibility** is also a factor—low visibility conditions reduce demand.\n  ![image](https://github.com/user-attachments/assets/bf283d5a-dde8-4fe9-8843-9c4cdf9dd501)\n\n\n### 2️⃣ Effect of Holidays \u0026 Time of Day\n- **Holidays show a clear increase in Uber usage**, likely due to increased travel and reduced availability of public transport.\n- **Peak demand is observed in the evening hours**, especially between 5 PM - 10 PM.\n- **Weekends** see a significant **increase in demand** compared to weekdays.\n![image](https://github.com/user-attachments/assets/618a2695-fb50-499d-9bd5-88528a1ba66c)\n\n### 3️⃣ Borough-Wise Demand\n- **Manhattan has the highest Uber pickup volume.** This is expected due to its high population density and business activity.\n- **Brooklyn and Queens show moderate demand**, but it fluctuates more with weather conditions.\n- **The Bronx and Staten Island have lower overall demand.**\n![image](https://github.com/user-attachments/assets/e6d43dff-ba32-4d3a-b0b9-5bd2ed1b2018)\n\n\nIn the context of the data used in the Uber analysis, **borough** refers to the five main districts of New York City:\n\n- **Manhattan**\n- **Brooklyn**\n- **Queens**\n- **The Bronx**\n- **Staten Island**\n- **EWR (Newark Liberty International Airport)**\n\nThese boroughs and the Newark airport are crucial for analyzing Uber ride demand, as each has distinct travel patterns, traffic conditions, and transportation needs.\n\nFor example:\n- **Manhattan** has the highest number of rides due to high business and tourist activity.\n- **Brooklyn and Queens** are significant for commuters traveling to work.\n- **The Bronx and Staten Island** have lower ride volumes but may experience demand spikes during specific hours or weather conditions.\n- **EWR (Newark Liberty International Airport)** is a major travel hub, with high demand for rides to and from the airport, especially during peak flight hours.\n\nWhen analyzing the data, it is essential to consider how ride volumes fluctuate across different boroughs and EWR based on weather factors, peak hours, and weekdays.\n\n\n\n  ![image](https://github.com/user-attachments/assets/ce4cbb85-1285-4da5-89c4-983ed6871237)\n\n\n### Seasonal Decomposition\n\n  ![image](https://github.com/user-attachments/assets/c6fe7123-fac8-40f1-b3c0-dd85b4be2241)\n\n\n### Monthly Uber Pickups by Day Type\n\n- **Working Days:**  \n  - There's a general upward trend in total pickups from January to June.  \n  - This indicates increasing demand throughout the period, possibly due to seasonal factors, increased Uber adoption, or other external influences.  \n\n- **Non-Working Days:**  \n  - The trend is similar to working days but with generally lower total pickups.  \n  - This is expected as there are fewer non-working days in a month.  \n\n### Key Insights from Time Series Analysis\n- **Weekly Seasonality**: Uber demand fluctuates based on weekly cycles, with higher demand on weekends.\n- **Trend Growth**: There is a clear upward trend in ride demand over time.\n- **Weather Effects**: Rain and snow events cause temporary dips in demand.\n- **Holiday Spikes**: Demand significantly increases during holidays.\n \n\n\n---\n\n## 📌 Recommendations\nBased on these findings, we propose the following business strategies:\n\n### 🚀 Dynamic Pricing \u0026 Driver Allocation\n- Implement **surge pricing based on real-time weather and holiday data** to optimize revenue.\n- Increase **driver availability in high-demand areas during peak times** (evenings, weekends, and holidays).\n- Reduce driver allocation in **low-visibility conditions or heavy rainfall**, as demand tends to drop.\n\n### 📍 Location-Based Adjustments\n- Focus **marketing efforts on outer boroughs (Brooklyn, Queens)** to improve demand in those regions.\n- Increase **Manhattan coverage** during peak evening hours to maximize trip efficiency.\n\n### 📈 Service Enhancements\n- Offer **incentives to drivers** for working in high-demand periods.\n- **Introduce promotions for rides booked in bad weather**, encouraging more usage even during low-mobility conditions.\n\n---\n\n## 📜 Conclusion\nThis analysis reveals that **weather, holidays, and borough location significantly impact Uber ride demand.** By leveraging these insights, Uber can implement strategic pricing, optimize driver availability, and enhance user experience. \n\nApplying **data-driven strategies** can lead to increased efficiency, better customer satisfaction, and higher revenue.\n\n---\n\n## 🛠️ Technologies Used\n- **Python** (Pandas, NumPy, Matplotlib, Seaborn)\n- **Jupyter Notebook** for analysis and visualization\n\n---\n\n\n## Data Source\n\nThis dataset originates from **Kaggle**: [NYC Uber Pickups with Weather and Holidays](https://www.kaggle.com/datasets/yannisp/uber-pickups-enriched?utm_source=chatgpt.com).\n\n\n##  How to Use the Project\n\n### Clone the Repository\n```sh\ngit clone https://github.com/your-username/uber-demand-analysis.git\ncd uber-demand-analysis\n```\n\n### 🛠 Install Dependencies\n```sh\npip install pandas numpy matplotlib seaborn jupyter\n```\n\n### ▶️ Run the Notebook\n```sh\njupyter notebook Uber_Case_Study-1.ipynb\n```\n\n---\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzuzann18%2Fuber-demand-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzuzann18%2Fuber-demand-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzuzann18%2Fuber-demand-analysis/lists"}