Johannesburg - A software company in Cape Town is hoping to predict crime before it happens through machine-learning, artificial intelligence and data capturing.
Solution House Software has launched a new artificial intelligence (AI) module designed to predict and map potential crimes before they happen.
Solution House Software director Tiaan Janse van Rensburg told Fin24 that the module collates data from 50 types of crimes, from rapes to hijackings to house breakings.
"Using data such as weather patterns and other reported crimes, we are able to predict the likelihood of a specific crime taking place, on a particular day at a particular time," he told Fin24.
He said the Incident Desk Predictive Analysis module will initially focus solely on crime, but future versions may be expanded to include other industries such as facility management and maintenance.
“For the time being we’re launching this new and very exciting technology with a very narrow focus, which allows us to achieve better results and hone the AI engine even further to apply it to other incident management areas,” said Janse van Rensburg.
Incident Desk uses a multi-tenant model which combines numerous customer areas, properties and buildings into one solution.
This includes urban areas, central improvement districts, neighbourhood watch initiatives, estates, shopping malls and even schools.
“Because Incident Desk is built on a multi-tenant model, it allows us to develop this type of technology and make it available affordably across the user base,” he said.
“The other advantage is that, because we’re multi-tenant at almost every site, we get to use many different data feeds that make this type of technology much more predictable and accurate,” he added
One of the biggest problems currently plaguing public safety and security is the ‘islands of data’ that are not being shared or centralised, which makes it difficult to data mine and analyse.
The Incident Desk Predictive Analysis module uses machine learning technology developed by Solution House, together with aggregated data from multiple information sources to determine the likelihood of different types of criminal activity in the Incident Desk management area.
“With the module installed, Incident Desk generates 7- and 30-day forecasts as heat maps based on crime types and incident probabilities that managers can use to optimise their finite security resources,” said Janse van Rensburg.
“Crime is notoriously difficult to predict, but given that Incident Desk can access so many different types of data – including weather patterns and forecasts and historical data – the results are based on fairly accurate and proven trending algorithms,” he added.
Incident Desk is a universal service request and incident mapping and management platform that provides facility, security and urban managers – along with their organisations, partners and customers – with real-time incident alerts.
This allows for the recording and live reporting of incidents with a unique smartphone app that makes it one of the only fully mobile-enabled incident management systems on the market today.
"The good news is that we’re planning to launch to all our current customers for free on a trial basis, after which we’ll phase in a subscription model for long-term use,” said Janse van Rensburg.
The Incident Desk Predictive Analysis module will be available to all current South African multi-tenant customers towards the end of this month.