In the August 16, 2011 edition of the New York Times there was an interesting article about the use of predictive analytics by police departments. Entitled “Sending the Police Before There’s a Crime,” the article explores how the Santa Cruz, California police department optimizes the use of limited resources by anticipating where crimes are more likely to occur so they can deploy police there in advance. How does it do this? According to the article:
“Santa Cruz’s method is more sophisticated than most. Based on models for predicting aftershocks from earthquakes, it generates projections about which areas and windows of time are at highest risk for future crimes by analyzing and detecting patterns in years of past crime data. The projections are recalibrated daily, as new crimes occur and updated data is fed into the program.”
This may sound like science fiction technology, but the model Santa Cruz is using is exactly what neural networks do. Neural networks are an artificial intelligence data analysis technique that identifies patterns from historical data and uses those patterns to predict new outcomes when presented with current partial data.
It’s the same technology that shuts off your credit card when it’s stolen and someone uses it to buy ten 60-inch TVs in another country. In that case, the credit card company has established spending patterns from your purchasing history, and when a transaction appears that falls outside that pattern, a neural network assesses the probability of fraud. If the probability is high enough, the card is blocked.
The applications for neural networks are limitless. They have been used for medical diagnosis, commodities price prediction, patient load forecasting in hospital, and much, much more. You can read examples of examples of interesting neural network applications using NeuralTools, a leading neural networks tool for Excel, here.
Santa Cruz’s efforts are being monitored and copied by other major metropolitan forces such as the Chicago and Los Angeles police departments. Such analytics could prove to be a major tool in the resource-strapped battle against crime for years to come.