The Benefits Of Automating Your Job With Analytics


office collaboration tablet web

Automation and robotics are becoming increasingly capable of taking over at least aspects of many jobs. Some people are concerned that their entire job will replaced. However, there is good news if you’re among those concerned about losing their jobs to robot overlords – researchers at McKinsey found that only roughly five percent of current US jobs could be completely automated using existing technology.

If automation and robotics won’t replace your job, they will certainly change significant parts of your job, mostly for the better.

The McKinsey researchers examined the benefits to automating parts of a job by surveying 2,000 tasks commonly found in American jobs. They estimate that in 60 percent of current US jobs, 30 percent or more of the work activities could be automated using existing technology. That equals 1.5 days in your work week. Not only would this work be taken off your workload, it’s likely the work would get done more accurately or to a higher level of quality.

Unfortunately, this likely won’t be mean shorter work weeks anytime soon. But, it does mean that you can spend more time doing tasks that people do well, such as setting strategy, creating content, supervising and mentoring.

Take the example of an average marketing manager. Marketing managers are often highly skilled and highly compensated workers. The organization needs them doing the work for which they are best or uniquely suited. Roughly 10-15 percent of tasks in such a job could be automated, such as reviewing pricing decisions, estimating material costs for product production, and surveying industry literature for trends and competitive information. Automating these tasks could free up roughly half a day per week for a marketing manager.

An extra half-day per week equals more than 20 work days per year. That time could go to new product research, increased sales training, additional product promotions, and other activities that directly impact the bottom line, provide job satisfaction and benefit from a human touch.

Analytics provides the brains behind automating job tasks. First, analytics build lists of tasks through anomaly detection, failure analysis, root cause analysis and other techniques. Tasks might include maintenance work, repairs, corrective steps, scheduled activities, etc. Next, these tasks are then scored according to complexity, criticality, urgency, cost impact, risk of danger, likelihood of human error, and other characteristics.

Depending on these scores, tasks might be done automatically, done pending review of a human, initiated only after gaining permission from a human, or left to humans to do. The tasks needing human permission, review or labor are presented in a prioritized list to facilitate decision making and resource allocation.

By sorting work in this way, and then carrying out some of the work, analytics become a powerful assistant to workers striving to serve customers better while optimizing organizational performance.


(Image courtesy of nd3000 / 123RF Stock Photo)


Using Analytics To Improve Workplace Safety: 3 Steps


You likely have a bunch of different spreadsheets, reports, and databases related to safety scattered across your organization. These data sources are compiled by various people in different departments. For example, HR may have information about driver certifications, while customer support keeps records of complaints about drivers and fleet operations holds maintenance records. You might not even know all the sources of possible data pertaining to accidents and injuries, of them, even if your job title contains the word “safety”.

Your organization’s safety record is probably pretty respectable. After all, accidents on the job are decreasing, as described in this news release from the Department of Labor. Check out this chart from the news release:

Safety trend chart
Occupational injuries and illnesses have been declining for more than 10 years

Still, there is no room for complacency. The National Safety Council cites nearly $200,000 in direct and indirect costs associated with a workplace injury that results in a doctor or hospital visit.

How do you apply those disparate and scattered sources of data to reducing the risk of accident and injury in your organization? There are three simple steps to using your data to improve workplace safety.

The first step is bringing together your using existing safety-related data using visual analytics. Just seeing your spreadsheets and databases correlated into intuitive visualizations that everyone can share delivers significant gains in safety. Creating a picture of your data clarifies relationship between data, puts data into a familiar context, and identifies potential problems in data quality.

For instance, the historical safety data for a trucking company may show which drivers were involved in accidents in the last five years. You could find that information easily by sorting a table of data. Placing that same tabular data on a map and a timeline tells you much more about exactly where and when those accidents occurred.

Safety table map
Visualizing data correlations is more effective than hunting for correlations in a table of data

The next step is moving from viewing historical data to responding to today’s events by applying diagnostic analytics to alert users about current unsafe conditions. In the trucking example, adding alerts to a visualization of historical accident data can tell dispatchers when a driver is entering an area of frequent accidents. With that information, the dispatcher might caution the driver to reduce speed and drive carefully.

The third step in using data to improve workplace safety moves beyond the past and present to look into the future. Predictive and prescriptive analytics, based on your historical and real-time data, calculate the likelihood of future hazardous events and locations. The power to predict is the power to avoid or mitigate consequences.

Keeping with our trucking company scenario, predictive and prescriptive analytics may take the form of a prioritize list of tasks to perform to reduce risk and avoid accidents. For example, the dispatcher may change a driver’s rout to avoid areas with frequent accidents.

Safety prescriptive
Analysis of risks leads to recommended actions for lowering risk

The journey from scattered spreadsheets to ubiquitous prescriptive analytics requires dedication, funding, and a vision of a safer workplace. Traveling the full journey may not make sense for every organization. Even so, stepping beyond simple spreadsheets and databases offers value for your employees and the organization as a whole.




Could ‘Pokémon Go’ Inspire Enterprise Productivity?



The world is going crazy for Pokémon Go. Nintendo’s stock value is making huge gains while masses of people are out hunting little ‘holographic’ critters. The technology isn’t new. Yelp has had a similar functionality out for 4 years called monocle. Yet this ‘Pokemon Go’ has made a ginormous splash. How? They used a technology to solve a pain point which is evidenced by their profitability so I don’t want validate that product vision here. Instead I’d like to answer another question which is “How can Augmented Reality help Enterprise on the same scale as the B2C market?”

The first part of the answer is that the motive to introduce AR to enterprise should not be about making a lot of money but rather helping a lot of brilliant people attain more.  Guy Kawasaki says, “The genesis of great companies is answering simple questions that change the world, not the desire to become rich.” The same applies within an organization eyeing new product offerings.

The second part of the answer is more involved so first I’ll discuss proof that Augmented Reality indeed helps brilliant people dive into a use case and then highlight some good User Experience design principles stemming from neuroscience that will make the use case come to life.

Augmented Reality (AR) is a technology that registers digital aspects onto the physical world around us. A stop light could be considered primitive Augmented Reality (AR). AR on Mobile Devices isn’t new but neither was the tablet before Apple made mountains of cash by designing it the right way. After Google Glass, there was a healthy dose of skepticism that everyday people would enjoy using Augmented Reality. Many would assume that if people don’t want it on their glasses with their hands free then why would they want to use a hand to hold the same information that they didn’t find useful?

Even as AR is in its technological infancy, Market guru Greg Babb explains how Augmented Reality reduced errors and time to complete task for wing assembly study presented by Paul Davies in conjunction with Iowa State and Boeing.


The chart above shows that wing assembly took significantly less time than traditional methods of assembly. There tends to be a major drive in Enterprise AR use cases to build applications for field crews and those assembling things. Meta CEO Meron Gribetz is on the record of saying he expects to throw away all the monitors in his office by next year and just work with AR headsets. This is compelling because Meta consists of developers, designers and scientists. That means knowledge workers would be using AR at their desk. This is either crazy or prophetic.

So what would an enterprise application look like? Well lets look at it through the lens of situational intelligence. Let’s consider the following use case:

Wind Turbine Use Case

A scientist at an energy company needs to run some prescriptive analytics for wind turbines. Government compliance and regulations have just been reformed and costly repairs and updates to the machinery has to be implemented on an accelerated pace. Heavy fines will be instituted for safety violations. Our scientist wants to use Matlab to run simulations on existing wind turbines to predict which turbines have a greater risk of breaking down, overheating or malfunctioning. He is think she can get more longevity out of gearboxes for yearly use within certain confidence levels.

  • He first speaks out loud saying,”Show me wind farms in central California.”
  • He sees a 3D map of several wind farms that he spins with his hands
  • The length of time he gazes at a certain region makes it slowly expand
  • He sees temperature on 4 wind farms with a high failure prediction
  • He increases severity of wind velocity changes in his data set and sees gearbox 4 fail
  • His gaze on the fourth gearbox chart line causes a line to appear animating towards the holographic turbine
  • He picks up the turbine, swipes the outer shell away and sees the motor spinning
  • He dictates notes about the turbine and recommends replacing the gearbox sooner than others


Our scientist is able to work faster in a more implicit manner without opening various files and programs with a mouse. He has more visual real estate and can now work with depth rather than just up and down dimensions. He is more productive, which makes his company more money.

Neural Interface Design

Pictorial Cues are an important aspect of good user experience that make a scene more realistic in AR. Some of these can be:

  • Occlusion – One object blocking part of another
  • Relative Size – Equal sized objects taking less area within our field of vision when their distances from us vary
  • Shadows – Objects that casts shadows seem more real
  • Accretion – Aspects of an object appear as a user moves in the physical world

Another aspect to design for in AR is binocular disparity as it assists with depth perception. Studies show that the neurons in our visual cortex fire optimally when there is a amount of specific disparity with a stimulus. So that is why you see one wind turbine moved to the right of another in the wireframe.

So maybe you won’t get to go hunting Pokémon at work if your company is smart enough to outfit you with one but you will definitely feel like a Jedi when manipulating the world around you with your senses. You will love sharing this world with your co-workers. Augmented Reality unleashes you imagination. The next couple years show some exciting times ahead for Reality Computing!

Special thanks to JulianHzg for making a great Wind Turbine in Blender at  that I recolored and used in my wireframe.



Use Visual Analytics to Get Started with the IIoT


Industrial IoT (IIoT) applications bring about many opportunities to increase operational efficiency by presenting personnel with timely insights into their operations. Visualizing IIoT data using visual analytics is a proven way to facilitate insight-driven decisions. So at the very least your IIoT initiative will start off by integrating IIoT connectivity, visual analytics and other system components. To best ensure early and ongoing success it is recommended that you follow the best practice of starting small, attaining quick wins and then increasing scope and/or scale.

The first step is to connect devices and systems and use visual analytics to create a simple visualization of your IIoT data. If the IIoT devices are mobile or geographically separated, then an appropriate visualization would be to display the location of the devices on a map such as shown above. This is an effective way to verify connections and validate successful integration.

The second step is to collect and intuitively visualize your IIoT data. At this point you can identify issues to make operational efficiency improvements.  As an example, a freight trucking business can see a map with the locations and times of where their trucks are moving at slower than expected speeds. This information is used to change the routes on the fly to maximize on-time deliveries. As this example highlights, connecting to IIoT data streams and visualizing the data facilitates operational efficiency improvements.

The third step is to correlate data from different systems and data sources, including time series data from devices at different locations. Visualizing data correlated by time and location makes it possible to create comprehensive big picture views that reveal details about what happened and is happening, where, when, why and how. Using the trucking example, areas where driving speeds are consistently slower than expected are highlight by the red lines on the map above. This information is used to refine future routes, schedules and delivery commitments.

The fourth step is to apply advanced analytics to the IIoT data to generate insights for inclusion into the visualizations. Returning to the trucking example, advanced analytics will recommend the optimal average truck speed to minimize fuel costs based on the weight of the load they are carrying. Visualizing each truck using color coding to highlight the biggest offenders makes the analytics results actionable at-a-glance so that operations managers and drivers can improve driving efficiency. In the image above it is easy to see the truck icons colored yellow and red that represent the trucks that are traveling outside of the optimal speed range.

Having completed these steps you are positioned to leverage your IIoT infrastructure and expand on your competency by combining visual analytics, data correlation and advanced analytics in innovative ways to address business problems and facilitate operational efficiencies that would not otherwise be possible. Future blog posts will cover such combinations and the corresponding operational efficiencies.