Uber Demand Gap Study

This project analyzes 6,745 Uber ride requests collected over a 5-day period (July 11–15, 2016). The objective was to uncover patterns behind ride cancellations, unfulfilled requests, peak demand periods, and driver availability issues.

The analysis combines:

* Excel Dashboarding
* Python (Pandas) Exploratory Data Analysis (EDA)
* SQL Business Queries
* KPI & Trend Analysis
* Business Recommendations

## Business Problem

Uber was experiencing a significant number of ride failures due to:

* Driver cancellations
* No cars available
* Supply-demand imbalance
* Poor driver distribution between Airport and City locations

The goal was to identify:

* Why ride requests fail
* When failures occur
* Where operational inefficiencies exist
* How business performance can be improved

## Dataset Information

| Attribute | Details |
| ---------------- | --------------------- |
| Dataset Size | 6,745 Ride Requests |
| Time Period | July 11–15, 2016 |
| Pickup Locations | Airport, City |
| Drivers | 300 Unique Drivers |
| Analysis Tools | Excel, SQL, Python |
| Records Analyzed | 100% Original Dataset |

### Columns

Request ID, Pickup Point, Driver ID, Status, Request Timestamp, Drop Timestamp

### Engineered Features

Request Hour, Request Date, Day of Week, Time Slot, Trip Duration (Minutes)

## Tools & Technologies Used

### Excel

* Interactive Dashboard
* KPI Cards
* Pivot Tables
* Charts & Visualizations
* Conditional Formatting

### Python

* Pandas
* NumPy
* Datetime Operations

### SQL

* SQLite
* Aggregations
* GROUP BY Analysis
* Business Queries

## Key Findings

### Overall Ride Status

| Status | Count | Percentage |
| ----------------- | ----: | ---------: |
| Completed | 2,831 | 41.9% |
| Cancelled | 1,264 | 18.7% |
| No Cars Available | 2,650 | 39.3% |

### Critical Insight

Only 41.9% of ride requests were successfully completed.

More than 58% of requests failed due to:

* Driver cancellations
* Lack of available cars

## Demand Pattern Analysis

### Morning Rush (5 AM – 9 AM)

**Primary Issue: Driver Cancellations**

Drivers frequently cancelled City-to-Airport trips because they anticipated difficulty finding return passengers from the airport.

### Evening Rush (5 PM – 10 PM)

**Primary Issue: No Cars Available**

Airport passengers struggled to find rides due to insufficient driver presence at the airport.

## Pickup Point Analysis

### Airport

* Total Requests: 3,238
* Completion Rate: 41.0%
* Major Issue: No Cars Available

### City

* Total Requests: 3,507
* Completion Rate: 42.9%
* Major Issue: Driver Cancellations

## Peak Demand Hours

| Hour | Requests |
| ---- | -------: |
| 6 PM | 510 |
| 8 PM | 492 |
| 7 PM | 473 |
| 9 PM | 449 |
| 8 AM | 423 |

Peak demand occurs during commuting and airport travel periods.

## SQL Business Analysis

The project includes 7 SQL business queries covering:

* Completion Rate by Pickup Point
* Peak Demand Hours
* Top Cancellation Hours
* No Cars Available Analysis
* Average Trip Duration
* Daily Demand Trend
* Most Active Drivers

## Root Cause Analysis

### Problem 1: Airport Supply Shortage

**Cause:** Drivers avoid waiting at the airport after completing drop-offs.

**Impact:** Large number of evening ride failures.

### Problem 2: Morning Trip Cancellations

**Cause:** Drivers cancel airport-bound trips to avoid being stranded at the airport.

**Impact:** High cancellation rates during morning commute hours.

## Business Recommendations

### Airport Incentive Program

* Introduce surge pricing for airport pickups.
* Offer guaranteed return-trip matching.

### Anti-Cancellation Strategy

* Apply peak-hour cancellation penalties.
* Provide bonuses for airport-bound trips.

### Driver Reallocation

* Deploy more drivers in the City during mornings.
* Deploy more drivers at the Airport during evenings.

### Fleet Expansion

**Current Driver Fleet:** 300

**Recommended Fleet Size:** 420–450 Drivers

### Expected Outcome

* Completion Rate > 65%
* Reduced cancellations
* Better customer experience

## Dashboard Features

The Excel dashboard contains:

### Sheet 1: Cleaned Dataset

* All processed ride records
* Status-based formatting

### Sheet 2: KPI Dashboard

* Total Requests
* Completion Rate
* Cancellation Rate
* No Cars Available %

### Sheet 3: Hourly Analysis

* Demand by Hour
* Completion Trends

### Sheet 4: Time Slot Dashboard

* Problem Rate Analysis
* Peak Demand Visualization

### Sheet 5: Pickup Point Analysis

* Airport vs City Comparison

### Sheet 6: SQL Insights

* Query Outputs
* Business Findings

### Sheet 7: EDA Results

* Statistical Summaries
* Trend Analysis

## Dashboard Preview