📊 Meaning of columns
| Column | Description |
|---|---|
| Violation Type | The type of traffic violation committed. Could be: Speeding, Signal Jump, or Drunk Driving. This helps analyze which type of violations are more frequent. |
| Vehicle Type | Type of vehicle involved in the violation: Car, Bike, Bus, or Truck. Useful for studying risk patterns by vehicle type. |
| Location Zone | The area of the city where the violation happened: North, South, East, or West. Helps identify hotspots for violations. |
| Day of Week | The day on which the violation occurred. Useful to see if violations are more frequent on weekdays vs weekends. |
| Fine Amount | The monetary penalty imposed for the violation. Higher fines may relate to more severe violations or repeat offenses. |
| Number of Offenders | Number of people involved in the single violation incident. For example, multiple passengers, riders, or drivers violating together. |
| Violation Time | Time of the day (converted to HH:00 format). Useful to see if violations are more common during rush hour, night, etc. |
| Repeat Offenders Count | Number of people among those involved who have committed prior violations. Helps assess risk and severity. |
Download the dataset here: https://github.com/slidescope/data/blob/master/city_traffic_violation_dataset.csv
🎯 Purpose of this dataset
- To analyze traffic patterns in a city and discover:
- Which violations are most common
- Which areas and times have higher risk
- The impact of repeat offenders
- How vehicle types contribute to violations
- To support traffic management, planning targeted enforcement, and public awareness campaigns.
- Can be used to build visual dashboards in tools like Power BI or Tableau.
- Helps policymakers design better traffic rules and fine structures.
✅ Target field (if used for predictive modeling)
This dataset doesn’t explicitly define a target field, but you could choose one based on your goal:
- If you want to predict risk/severity, you might use Fine Amount as the target.
- If you want to predict the likelihood of repeat offenses, you might use Repeat Offenders Count as the target.
- You could also design a new field like High Risk Violation (binary: Yes/No) based on fine amount threshold or repeat offenders.