Frequently Asked Questions

Welcome to our Frequently Asked Questions (FAQ) area where we will attempt to answer all of your questions about the Daily Crime Forecast. Expect this section to grow as we will continue to add content on a regular basis!


What is the Daily Crime Forecast?

The Daily Crime Forecast is an innovative software program that, based on historical data, provides a daily prediction of where and when crime is most likely to occur.

What are the features of the Daily Crime Forecast?

The Daily Crime Forecast has the following features:
  • Effectively predicts where AND when crime is likely to occur
  • Fully automated
  • Intuitive and easy to use
  • Uses the latest crime data to model forecasts
  • Allows for easy visualization of crime risk by time of day
  • Can use any existing data sources from a Records Management System or Computer Aided Dispatch System
  • Ensures the optimal distribution of limited police/security resources based on available proactive patrol hours

How is the Daily Crime Forecast different than existing hot spot clustering routines?

The Daily Crime Forecast (DCF) varies significantly from current hot spotting routines in that it is predictive instead of retrospective. Specifically the DCF is different in the following ways:

Spatial clustering routine: The DCF utilizes an innovative clustering methodology that:

  • Can be generated automatically without user input
  • Ensures that the size of clusters are fixed to allow efficient coverage (target areas are not too big or too small)
  • Will not produce clusters that overlap
  • Will accurately identify ‘linear’ risk areas
  • Instead of providing 'hot spots' areas based on user-chosen parameters as in most spatial hot spotting routines, the DCF builds its risk areas based on available resources

Evaluates Spatial and Temporal attributes: The DCF uses a novel methodology that uses machine learning algorithms to capitalize on the spatial and temporal distribution of crime by effectively assessing the relevance of attributes within the data. Using several relevant temporal and spatial factors together, a better and more accurate prediction can be made to predicts times and locations where crime is likely to occur.

Adjusts for current temporal conditions: Instead of showing crime hot spots for the last weeks or months as in existing methodologies, the DCF ensures that it evaluates the current temporal conditions before generating a forecast. Intuitively we know that the propensity for crime will vary not only by location but also by day of week, month or even day of month. The DCF takes into account the temporal conditions of the day being predicted in generating its forecast. This allows for the DCF to output a new and optimized forecast for every day of the year.

Automation: The DCF is fully automated and can produce a daily crime forecast without user interaction or the need for pre or post analysis. The DCF will fetch the required data, then generate and output the forecasts to a secure web portal automatically for every day of the year. That means that your analysts can concentrate other projects knowing that patrol deployments are taken care of in the most efficient manner. This also means that the forecasts will also be generated on weekends and holidays.

How accurate is the Daily Crime Forecast?

In tests performed on existing historical crime data, the Daily Crime Forecast was shown to be about 2 times more accurate than hot spot methodologies and 9 times more accurate than randomly deployed police resources. This means that police officers utilizing the Daily Crime Forecast are 9 times more likely to be at the right place and at the right time to deter a crime or apprehend a criminal than when utilizing random patrols.

What is the percentage of actual crimes that can be accurately predicted? This percentage cannot be determined without bias as the results will vary significantly based on a subjectively chosen test criteria. For example, 100% accuracy can be achieved simply by choosing a city wide area and a 24 hour time span as your test area. Certainly a crime will occur somewhere and sometime during a day in a big metropolitan city. Although the prediction would always be correct, its usefulness in deploying resources is rather limited. On the other hand, if the criteria were to be a street corner and a 1 minute time span, the results would likely be a 0% prediction rate, as this would be almost impossible to predict. Any other area/time span selection would produce similarly biased findings.

A better measure is to compare apples to apples as in the ratios explained in the first paragraph. No matter what size of target or time span is chosen, a direct comparison to existing methods can be made in an unbiased manner. If a police agency is currently using crime hot spots to direct its patrols, it can become twice as effective using the Daily Crime Forecast. If it uses random patrols it can become 9 times more effective.

Will using the Daily Crime Forecast help reduce crime?

Edmonton Transit Security (Edmonton, Alberta, Canada) has employed the Daily Crime Forecast since 2006 to deploy its resources. Although the overall crime count within the Edmonton Transit System has gone up to coincide with the agency’s expanded scope, the way the agency is dealing with its incidents has changed drastically. Since the introduction of Daily Crime Forecast, Edmonton Transit Security has seen its number of proactive incidents -- where officers are on scene before trouble happens -- go up 159 per cent. Reactive events -- where officers respond to an incident after it happens -- have gone down by 52 per cent.

The results of a systematic review by Braga (2007), supported the assertion that focusing police efforts at high activity crime places can be effective in preventing crime (Braga 2002; Eck 1997, 2002; Skogan and Frydl, 2004; Weisburd and Eck 2004). Seven of nine selected evaluations reported noteworthy crime and disorder reductions.

Get in Touch

Storm Analytics Corporation
Edmonton, Alberta
This email address is being protected from spambots. You need JavaScript enabled to view it.