- Ahmedabad traffic e-challan data taken as case study
- Repeat offenders tend to default on paying fines
- Payment of smaller fines preferred
- Inputs can be used by authorities to make system more effective
Hyderabad: One would be left baffled on coming to know of the amount that is due to the Gujarat State government after issue of challans to traffic violators. It stands at a mindboggling Rs 59,24,30,400 as of August 22.
This was among several interesting findings during a survey conducted by researchers from International Institute of Information Technology, Hyderabad (IIITH) with specific relevance to e-challans data pertaining to Ahmedabad traffic.
Working on a uniquely conceptualized research paper titled ‘Don’t Cross That Stop Line: Characterizing Traffic Violations In Metropolitan Cities’, under the guidance of Prof Ponnurangam Kumarguru, an Associate Professor at Indraprastha Institute of Information Technology, New Delhi, the IIITH team comprising Aanshul Sadaria, Kanay Gupta, Shashank Srikanth, Hiimanshu Bhatia, and Pratik Jain, presented their classroom project as the last semester research paper for ‘Big Data and Policing’ elective course. The research paper has been submitted for review at an ensuing conference.
The researchers found some interesting patterns in motorists’ behaviour, both in terms of repeat offences as well as payment of fines. The purpose of the study was to ascertain on how best digitized data on traffic violations could be analysed, which, in turn, could be used as first-hand on-the-ground feedback for improving the system on more scientific lines.
“With more and more cities moving to e-governance, we wanted to come up with insights that could help achieve fool-proof governance and policing,” says Aanshul Sadaria, one of the researchers.
Incidentally, the topic was not something that just cropped up. It takes its roots to Aanshul’s personal experiences over the years. A native of Ahmedabad, he was at the receiving end of traffic challans having recorded a few transgressions that he explained after some self-analysis and retrospection.
“There was a pattern to how the e-challans had been recorded. They were invariably at 3 pm and at a particular location because that was when I used to rush to attend classes, through a particular route. Typically being late to class, I was prone to committing the offense of jumping a red light. That’s when a brainwave struck me. I thought we could use data available on the Ahmedabad e-challan website and find similar interesting patterns for the benefit of the general public,” he points out, while talking of the topic was decided.
Team member Kanay Gupta explains, “Not only did the Ahmedabad police have the most robust kind of a system, but it was far easier to access data online here compared to other metropolitan cities where data was secured through captcha”.
Researchers from IIIT Hyderabad analyse Ahmedabad traffic e-challans data and discover interesting patterns in motorists’ behaviour both in terms of repeat offences as well as fine payment. https://t.co/JdHTWJn6g8#iiith #iiithyderabad #bigdata
— IIIT Hyderabad (@iiit_hyderabad) November 12, 2019
As part of the research, they collected data on all kinds of traffic challans generated from September 2015 to August of this year.
“While Gujarat has a GJ prefix and Ahmedabad city number registered as 01, we brute-forced through all possible combinations of vehicle registration numbers from AA00 to ZZ99 to find information about challans generated, if any, against every single vehicle registered there,” says Aanshul adding that a dataset of over 3 million e-challans was generated.
Every documented e-challan has information about location, time, date, type of traffic violation, amount of fine levied and whether it has been paid or not.
The research team segregated the number of paid versus unpaid challans from the total number of e-challans found in the dataset. That is when they found that an astonishing amount of Rs 59,24,30,400 was outstanding on August 22.
Challans were characterised based on the type of offense committed – red light violation, riding without a helmet, improper parking, stop line violation, driving without a seatbelt and so on. It was found that jumping a red light accounted for the most number of violations. The researchers also discovered a pattern of higher or lower incidences of violations corresponding to celebrations in the city such as festivals or other similar events by analyzing the date and time of issuance of challans. It was near-zero during events like Rath Yatra as police personnel were on bandobast duty.
However, during other festivals such as Ganesh Chaturthi and Navratri, there was a notable rise in the number of challans issued. A spatial analysis also revealed certain hotspots in the city where violations were more likely to occur.
With the aim of predicting repeat offences, the team trained a machine learning model based on the history of registered vehicles getting challans.
“Similar to how big data is being used in policing of big crimes, we attempted to predict how a traffic offender is likely to repeat the offence. We achieved 95% accuracy in predicting violations,” says Kanay.
The researchers could narrow down on features that could predict a vehicle owner’s tendency to repeat an offense aka ‘recidivism’. They included unpaid number of challans: the higher the number of such challans, the greater the chances of repeat offenses, number of days since the last challan was issued, among others.
A team of researchers handed over the insights from this study to the Ahmedabad police, who requested a similar analysis for Rajkot city. “With these kinds of findings, the police can get a sense of the violations that are taking place and the locations where they are happening. It will help in dispatching teams to conduct checks. In fact, I foresee that this kind of data can even be used for city planning. The answer to the question of how do I design my roads can actually come from this,” says Prof. Kumarguru.
Researchers believe that with the new Motor Vehicles Act (Amendment) 2019, which came into effect from September 1, and its focus on enhancement of penalties for driving errors as well as violating other road regulations, such analysis would be crucial.
Similarly under the recent road-rationing scheme introduced by the New Delhi government where vehicles with odd-numbered license plates are allowed to ply on the roads on certain days and even-numbered license plates on other days, patterning trends in traffic e-challans would be beneficial, say researchers.
“It would be nice to see the data before and after implementation in order to show the effectiveness of the rules” observed Prof. Kumarguru.