Predictive Analytics Tools Can Help State and Local Governments Save Money and Lives

What Is Predictive Analytics Software?

For years, government agencies have employed traditional statistical analytics software (SAS) to build predictive models, but those workers were usually sequestered into back rooms without access to policymakers, notes Churchill. “But now data science is in vogue and it’s the cool job,” he says.

The most basic way to understand predictive analytics is to ask, “How do I take what I can clearly see is happening and begin to, through trained models, describe what will happen based on the variables that we are feeding the machine?” Churchill says.

Mohan Rajagopalan, senior director of product management at Splunk, notes that predictive analytics involves the ability to aggregate data from a variety of sources and then predict future trends, behaviors and events based upon that data. That can include identifying anomalies in data logs and predicting failures in data centers or machines on an agency’s network. It can also be used to forecast revenues, understand buying behaviors and predict demand for certain services.

“The outcome of predictive analytics is the prediction of future behaviors,” Rajagopalan says.

Adilson Jardim, area vice president for public sector sales engineering at Splunk, says that predictive analytics exists on a spectrum. On one end are basic statistical or mathematical models that can be used to predict trends, such as the average of a certain type of behavior. On the other end are more advanced forms of predictive analytics that involve the use of machine learning, in which data models are asked to infer different predictive capabilities, Jardim says.

Some customers are ingesting up to five petabytes of data per day, and that data can be used to not only understand what has happened but what could or is likely to happen, he says.

Predictive analytics can be applied across “a broad range of data domains,” Churchill says. 

MORE FROM STATETECH: Discover why agencies need to analyze Big Data effectively to improve citizen services.

How Predictive Analytics Works

The first component of predictive analytics is the data itself, according to Rajagopalan. One of the big challenges state and local government agencies and other organizations face these days is the volume, variety and velocity of data.

“A model in the absence of trustworthy, validated and available data doesn’t yield much of a result,” Churchill adds. “Beyond that, it varies by use case.”

Another core element of the process is algorithms. Yet another is the model that is used to define how the data will be processed, Rajagopalan says. The algorithms can be as simple as rules applied to understand a particular situation or to understand data in the context of a particular scenario. There are also supervised algorithms and models that use machine learning techniques to build hypotheses around trends in the data and constantly refine themselves based on the data they are presented with. 

The models that are fed the data are the key, Churchill says. “For us, that technology should be a little bit fluid,” he says. “When you think about how fast things are evolving every year that passes, whether that’s the technologies or methods, availability of compute, cloud into GPU or Big Data things, the opportunities are progressing so fast. For us, it’s about making that opportunity agnostic to what sits behind it.” 

Finally, IT leaders have the outputs of the model, such as a visualization, report or chart.

Before, Rajagopalan says, agencies had specialized units to apply SAS, but those models were expensive to create. The democratization and consumerization of data and of analytics tools has made it easier to create simple and succinct summaries of data that visualize outputs.

READ MORE: Find out how state and local governments can overcome Big Data challenges.

Predictive Analytics Use Cases in Government

There are numerous uses for predictive analytics software in state and local government. For example, agencies can use predictive analytics tools to detect fraud in public benefits programs such as Medicaid.

“A predictive analytics strategy can help payers determine which providers have a history of fraud activity and which provider behaviors likely indicate increased fraud risks,” the website HealthPayerIntelligence notes.

Jardim notes that Splunk works with several state and local customers on fraud detection using predictive analytics. The company helps them spot the factors that could indicate nefarious activity. For example, how often has a region, doctor’s office or medical provider submitted claims that look above average? That data can be compared geographically and demographically to see if it is higher or lower than average. Data analytics tools can also look at reimbursement codes for specific healthcare services and examine whether that is the type of care that is typically delivered in that region or from that provider. 

“Payers need both visualization and predictive analytics tools to learn about providers with history of fraud and abuse, patterns related to overpaid claims, and if fraud-centric behaviors are emerging within provider organizations,” HealthPayerIntelligence notes.

Before the novel coronavirus outbreak, the opioid crisis was the biggest public health emergency on state and local governments’ radars. Cities and states have been using predictive analytics to save lives. In Cincinnati, Ohio, city officials “began analyzing EMS response data to identify trends and geographic ‘hotspots,’ helping public safety identify key areas for strategically deploying personnel and medical resources,” according to the city.

Churchill noted that in Vancouver, Canada, authorities there “truly brought the power of predictive analytics to the fight” against opioid abuse. Authorities there were able to use predictive analytics tools to predict trends of where strong opioids would be sold and where overdoses were likely to occur, based on just a few 911 calls, Churchill says.

The city began to forward deploy first responders in those areas so they could respond to overdoses more quickly. “It’s an incredible story of how predictive analytics can be brought down to the masses,” he says.

Municipalities with vehicle fleets can also use predictive analytics for predictive maintenance. The model can ingest data such as the weather and operating conditions of vehicles, not just how many hours they have been running, to determine when they will break down, Churchill says.

Jardim noted that Splunk worked with a public transportation provider to monitor the air pressure in tires on buses via sensors. If a bus has low air tire pressure, it needs to be taken off the road for safety reasons, which affects the efficiency and profitability of the public transport operation. Predictive analytics tools were used to predict when a bus would need to be brought in to have its tires serviced for low air pressure and send it out more efficiently.

If a bus were to break down, it would have “a massive ripple effect” across that city, Jardim notes. The transportation provider would need to reroute bus stops, accelerate pickups of passengers or try to find another bus to put into service, which might not be available. It can also have a “significant downstream impact” on that transportation providers’ ability to meet service-level agreements with the city, he says.

“It becomes a big financial and public services problem, not being able to incorporate how you remediate and orchestrate a change in your operations,” Jardim says.

Predictive analytics does not mean humans do not have to make critical decisions, but it allows them to make more informed decisions. “I would classify the real opportunity with predictive analytics as augmenting human decision-making,” Churchill says.