Using Big Data Analytics To Predict Crime Patterns
Police departments have long been using data to understand crime pattern. But With access to more personal data than ever before, police is using big data analytics to solve crimes more quickly.
Take for example, the Indian Police force, that is revamping its investigation procedures by using Big Data and Artificial Intelligence.Delhi police have recently partnered with the ISRO to develop an analytical system—Crime Mapping, Analytics and Predictive System (CMAPS). CMAPS helps Delhi police to ensure internal security, controlling crime, and maintaining law and order through analysis of data and patterns.
According to a senior official in Delhi police, “Each one in the force will be equipped with Personal Digital Assistant device, which will be connected to a central system, and will contain records of more than two lakh criminals.”
Similarly, the Jharkhand police force is trying to implement an analytical system, with the help of IIM Ranchi, which would evaluate criminal records, date and time of crime occurrences, and location to predict crime-prone zones. The system is built on sophisticated algorithms and behavioral science, which will accumulate crime related data from all over the country.
From public records to social media information to informant tips, Indian police force has access to an expansive amount of data, which is spread over its legacy systems. Therefore, it becomes extremely important for Indian police across different states to adopt easy-to-operate analytical tools to utilize this vast intelligence.
In other words, the technology will collect data on ordinary citizens including information on their jobs, hobbies, consumption habits, and other behaviors and will flag unusual behavior that could signal a potential terrorist.
Predicting crime pattern
In many countries, the authorities are not just using data to understand past criminal activities, but are also trying to predict the future crime pattern. The Chinese government is working closely with the China Electronics Technology Group to develop technology, similar to that used in the sci-fi thriller “Minority Report.” The objective is to predict acts of terrorism before they occur based on the large amount of surveillance data.
According to a BBC iWonder post, a few years ago, police in both Los Angeles and Manchester ran similar trials using a computer algorithm to predict where crime would take place. Their aim was to find patterns in criminal behavior by analyzing large amounts of crime data in order to to prevent crime through a method called “predictive policing.”
Likewise, the Chinese government is leveraging “predictive policing” capabilities in recent times. It has funded research into machine learning and other artificial intelligence technologies to identify human faces in surveillance video.
Jeffrey Brantingham, anthropology professor at UCLA and partner to the LAPD research team, believes predicting crime before it takes place therefore is no longer like a science fiction. The police can test if by analyzing large amounts of crime data, also known as ‘big data’, they could spot patterns in the way criminals behaved. Then they’d deploy their resources in the areas the computer predicted crime would strike. “It is not about predicting the behavior of a specific individual. “It’s about predicting the risk of certain types of crimes in time and space,” she explained.
Christopher Beam, author of the Slate article said that predictive policing is based on the idea that some crime is random, but a lot isn’t. “For example, home burglaries are relatively predictable. When a house gets robbed, the likelihood of that house or houses near it getting robbed again spikes in the following days. Most people expect the exact opposite, figuring that if lightning strike once, it won’t strike again,” said Beam.
In a paper slated for publication in the Journal of the American Statistical Association, the team of UCLA researchers working with the LAPD compares this kind of repetitive crime to earthquakes. The initial crime is the first tremor. Subsequent crimes follow like aftershocks. We don’t know exactly where or when the after-crimes will occur or if they’ll occur at all. But we can create a predictive model based on probabilities. Police departments can then feed real-time crime data into these models and organize patrols based on the likelihood of certain crimes occurring in certain places.
The researchers argue, this doesn’t mean police can prevent every kind of crime. “These are for only the more predictable kinds, like burglary or auto theft. But predictive policing could reduce crime on the margins,” according to the UCLA researchers.
Combating cyber crime
According to Gartner, the police force now has access to mature big data storage platforms such as Hadoop, NoSQL etc, which allows them to store years’ worth of structured digital content and unstructured data within the same platform, and analyze them along with the incoming real time data to understand crime patterns within their jurisdictions. It also uses predictive analytics to develop models using machine learning to know which areas are most prone to crime, and which individuals to keep on its watch list.
In a blog post, Avivah Litan, VP and distinguished analyst at Gartner stated that even cyber criminals are rapidly evolving their hacking techniques, and are attacking quickly, making timely security and fraud analytics more critical than ever. Big data analytics can give police departments and intelligence agencies faster access to their own and relevant external information.
Data experts argue that if big data can be used to predict weather patterns, then why would it be surprising to forecast crime in the near future? As noted columnist and critic Mark Gibbs mentioned in his blog, “This is the world of predictive analytics; the scientific version of a crystal ball. Instead of peering into a glass globe you peer into (ideally) massive amounts of data and using Big Data mining techniques such as statistics, modeling, and machine learning you look for patterns that are indicative of current or future behavior.”
- Top Fintech Trends That Will Dominate This Year
- Employees Not Bothered About Company’s Security: Study
- Data Felon’s Next Target: Insurance Firms
- 2018: The Year Of Demystifying Unstructured Data
- The Key Security Factors In Aadhaar Authentication
- Is It Time To Say 'Goodbye' To Passwords?
- SMB Guide To Effectively Deploy Salesforce CRM
- Top 10 Customer Experience Trends in 2018
- How Big Data Is Changing Banking And Finance
- Microsoft, Accenture Team Up To Help Start-Ups