Posted by: Grant Stanley on April 13th, 2012 Leave a Comment

Predictive Analytics allows people to make better decisions about how to spend their limited time, energy and money. The potential impact of predictive analytics on business will be similar to the personal computer, relational database and Internet. The power of predictive analytics is that it is a scientific business process improvement method that can be used to model complicated and hard to measure actives, such as why people buy something or which employees are likely to leave. Many business executives understand this potential and are excited about applying predictive analytics to their businesses.

CAN has 4 years of experience helping 200+ companies realize the benefits of predictive analytics. We have developed a 6 stage process for applying predictive analytics to our clients’ businesses that maximizes our clients return on investment, increases their chances for success, and makes sure that the results of our research are applied.

 

Six Steps to Applying Predictive Analytics

The first stage is to define the company’s mission, vision and values. We want to know why the company was started, and why it exists. We want to know what they want to accomplish in the future. Most importantly we want to know how they do business; what values they have that are unique and perminant even when the strategy changes. This understanding set the priorities and filters that guide future discussions.

The second stage is to define the company’s goals. Unlike mission, vision and values, goals have clear beginnings and ends and typically can be accomplish in less than a year. Companies typically have one to three goals. Goals should be in alignment with the company’s vision for the future, and should be accomplished in a way that adheres to the company’s values.

The third stage is to define the business question to be answered. The business question is about business process improvement, and should not involve technology or research questions. When answered a business questions should have a noticeable impact on at least one of the three parts of a business; sales, operations and administrative support.

The Business Question

The fourth stage is to determine what resources are available. Resources include political approval, availability of necessary data, and determining research methodology. It is important to note that we only determine research methodology once we have defined the business question. If we don’t have the necessary resources to answer the business question, we go back to stage 3 and try to refine the business question to fit the available resources.

It is also during this stage that we determine which of CAN’s resources are best for the client. There are two basic options; custom solution or CAN’s products. If possible we try to answer the business question using one of CAN’s 5 products. This allows us to minimize cost while increasing chances for success. Our 5 products are designed to answer 5 key business questions that the majority of business owners have:
1. Tracker: Who is most likely to purchase my product next?
2. Capture: Where and when should I spend my marketing budget?
3. Pulse: How do I attract and retain my best customers?
4. Beacon: Which employees are most likely to leave and why?
5. Terrain: What sales are likely to be next quarter?

If a business question can’t be answered using one of CAN’s products, we offer custom solutions. Many of CAN’s clients leverage our custom solutions to develop a competitive advantage in predictive analytics. When developing custom solutions it is essential that we become apart of our clients team and fully understand their business, goals and resources. Before committing to any custom projects, CAN requires that we build a proof of concept. The purpose of the proof of concept is to make sure that we fully understand what we need to build and that we have all the necessary resources.

The fifth stage is to determine how the models will be implemented. While our research is complex, we make sure that our work is easy to understand and use, because that is how it gets implemented. We use 4 methods to implement our research, and often combine multiple methods depending on what the client’s goals are.

Reporting Predictive Analytics

1. Formal Reports help our clients understand the nuances and details of our research. Formal reports are most useful when the results of our research will influence a company’s strategy, will be used by a small and specialized audience, and frequent updates are not required.

2. Marketing Summaries provide our clients with colorful and easy to understand summaries of our research. Many of our clients use these summaries as marketing pieces to communicate quickly with large and unspecialized audiences about research that impact future strategy. Marketing pieces go beyond executive summaries because they can be used be used to inform executives, employees, customers and the community.

3. Dashboards help our clients quickly get the up to date information that need to run their operations. While formal reports and marketing summaries often include data visualizations, dashboards are unique because they can be quickly updated and display key information on a single screen that can be monitored at a glance. Dashboards are typically used by a small and specialized audience that is trained to understand and use the information on the dashboard. Dashboards can also be very useful for sensitive information, because administrators can control access by user on a need to know basis.

4. Workflow Integration provides our clients with the ability to use our research to impact the activities and operations of large number of people through the systems they are currently using. Workflow integration is useful because users don’t have to learn or get in the habit of using a new system. The predictive models and coefficients that CAN develops act as a filter to the current database and either users are presented with familiar data fields or if need new fields.

The method that we choose depends on who the audience will be and how they will use the results. The fewer the people that need access to our research the more important security and control becomes. If the use of our research is for strategy development then we typically publish a formal report. However if the use of our research is to optimize operations then we publish it as a dashboard, marketing piece, or integrate it into the software you are currently using.

The sixth step is to evaluate the model. As part of developing models we run tests to make sure that they are statistical robust. However, it is important to further evaluate a model before and after we implement it. The first evaluation criteria is does the model answer the intended business question. The second criteria is does the model produce results that reflect reality. While the model might be statistical robust, it is useless if it produces misleading results that the experts in your business know aren’t true. The third evaluation criteria is once implemented does the model produce the expected results.

Predictive analytics is a very new field. While the technology is exciting, it is predictive analytics ability to answer hard to answer or previously impossible to answer business questions that is most exciting. What separates CAN from our competition is our focus on making sure that we answer our clients’ business questions, instead of being enamored by the technology. Our hope is that we can help our clients apply predictive analytics to their businesses, and that our 6 stage process helps them maximize their return on investment, increase changes for success, and makes sure that the results of our research are applied.

Category: Predictive Analytics | No Comments » Tags: , ,

Posted by: Grant Stanley on April 2nd, 2012 Leave a Comment

Contemporary Analysis, Omaha, NE

It is time to take a break, and celebrate our 4th Birthday!  We want to celebrate everything we have accomplished, and kick off all the great things that are going to happen.  In 2012 we will launch 5 web applications, expand our offices from 1098 square feet to 3850 square feet, and training 20 new employees to support all of our new clients.  Join us for an open house on April 18th from 4:00 to 6:00pm.  We will have free food and drinks.  You can meet our expanding staff, take a tour of our offices and learn more about what we are working on.  Please RSVP at http://can4thbirthday.eventbrite.com.

Category: Uncategorized | No Comments »

Posted by: Grant Stanley on March 28th, 2012 2 Comments

When hiring new people, we primarily look for four things; People that just build things, use learning as a tool, pursue the truth and are passionate about our vision.

First, it is important that they just build things. We don’t care about people that love to build things. Everyone on our team just builds things. They get an idea for a product, process, business or experience, and they just build it. We are very interested to know what people have built and why. We are looking for their ability to identify a need, scope the solution, and organize the resources necessary to develop the solution. We expect every CAN employee to be an executive, because they are expected to make decisions everyday that impact the future of the organization.

Second, they must use learning as a tool. We don’t care about people who love learning. At CAN the ability to learn almost anything is essential to success. When we get a new client or encounter a new problem, we figure out what needs to be done, learn how to do it, and then do it. Working at CAN would be very frustrating for someone that uses knowledge as a tool. We don’t pay people for what they know, we pay people for what they can learn.

Third, they must pursue the truth. We need people that not only pursue that truth, but embrace it without hiding from uncomfortable facts. Our clients pay us to change their organizations to help them work smarter. Often, CAN’s research uncovers uncomfortable truths about our client’s business, and it is our job to expose that truth. More often than not this is very uncomfortable, and our people must be able to confront these truths while operating with an executive level of consideration.

Fourth, they need to be passionate about our vision. CAN’s vision is to develop simple systems to help all companies work smart.  We do not need technicians that are in love with technology. We need people that see technology as a tool, and are passionate about building simple tools that everyone can use. Also, we need people that are passionate about business.

These criteria apply to every position, and are internal to the culture of CAN.  Having clearing defined what we look for when hiring people allows us to hire people based on their alignment to our culture, instead of their specific skills or education.  While this makes finding the right people very difficult, it has created an environment that is rife with creativity and original ideas.  Everyone is pursuing the same goals with same culture and different skills, experiences and education.

CAN is not for everyone, but we don’t need everyone.

Category: Job Board, Video | 2 Comments » Tags: ,

Posted by: Grant Stanley on March 21st, 2012 Leave a Comment

Security is very important to CAN since we work with our clients’ most sensitive information and provide them insights that are essential to the future of their organizations.  Our clients trust us with their most valuable information including business plans, intellectual property, financial and customer data.  We work daily to respect that trust.  The following is an introduction to how CAN maintains the security of all of our systems, sensitive data, and Contemporary Analysis.

1. Sensitive Data
The first step to protecting CAN’s sensitive data is to limit any unnecessary data. We require CAN’s clients to scrub any sensitive data that is not needed to build models. For example we can often build robust models without having to have access to names or addresses.  A CAN Navigator and Data Scientist can help you determine what data is necessary and how to scrub any unnecessary sensitive data.

The second step to protecting CAN’s sensitive data is classifying data by type, security level, and access permissions. All sensitive information is labeled by client, project, and security level. CAN employees are provided only the data required to fulfill their job description. CAN classifies our data into three major categories, each with a default type, security level and access permissions.
1. Public data is not sensitive and is accessible to everyone at CAN. Public data is information that is available on the Internet and is widely available to people outside of CAN and CAN’s clients.
2. Internal data is sensitive and is accessible to only executives at CAN, and as needed. Internal data is data that is used to operate CAN’s business.
3. CAN Client data is sensitive and is only accessible on a project basis to the data scientists, sales executives and navigators that are working. Permission to the data is removed as soon as the project is completed. CAN client data is any information that we receive from a client, and includes temporary data files that CAN uses to generate deliverables and also deliverables for clients.

2. Data Management

CAN stores all data in a central location and also carefully manages devices and people that have access to specific types of information.  All of our data is stored in a secure and encrypted hosted environment.  Our IT infrastructure is designed so that in case that a device goes missing or is compromised, CAN can identify the location of that device, terminate access to CAN’s network and data files, and remove the encryption key to the hard drive.

CAN has also increased the simplicity and security of our data management policy by not permitting the use of USB powered drives and other external hard drives. With the state of CAN’s network and technology, USB powered drives and external drives are unnecessary and a major threat to the fidelity of CAN’s network and data management. When possible CAN uses SFTP, “SSH File Transfer Protocol”, when transferring data within and outside CAN’s network.

All data transferred between CAN and Client requires a encrypted USB drive or secure FTP. CAN requires that only new encrypted USB drives are used, and that the drive is either shredded after the transfer or stored in a locked container at CAN HQ.

3. Encryption
We use encryption on all disks and devices to add an additional level of security.  Even if someone was able to get a hold of a CAN device or break into CAN’s network without access to the encryption key it impossible to use the data stored on a device.

CAN uses disk encryption on laptops, desktops, mobile devices, and servers. CAN also encrypts data in motion between laptops, desktops, mobile devices, and servers. In addition to device level encryption, each client’s data is stored on encrypted virtual drives. This keeps each client’s data separate, and keys are only provided to the data scientists, sales executives and navigators that are responsible for that specific project. Only data scientists are provided the encryption key to the client’s raw data.

In the event of a security breach CAN is able to revoke the disk encryption key of all of CAN’s laptops, desktops, mobile devices and servers as soon the device is connected to the Internet. In addition, the encryption key is automatically removed and the disk erased after 10 failed attempts to access a device. Once the disk encryption key is removed the data is unreadable.

4. Authentication
It is important that the right people are accessing the right information. CAN uses password, software, and physical access control to protect against unauthorized access. We require that every device used by CAN employees or contractors used when performing their job responsibilities require passwords to access, lock out for 10 minutes after 3 unsuccessful log-in attempts, and after 10 unsuccessful log-in attempts remove encryption key and start erasing the disk. User are required to change their password every 90 days, and will be promoted automatically. Passwords on phones and tablets will have 4 numbers, and passwords on other devices will require 12 minimum characters, and use at least 2 different character classes.

We control physical access to CAN’s facilities. When our facilities are not occupied by CAN employees and contractors an alarm system is used. We are also investing in more advanced access control. In the future, employees and contractors use RFID badges to enter CAN HQ, individual floors, as well as the server room. Each door will also monitored by a camera. Each time a door is opened the badge id and a brief video clip will be recorded. These records will be reviewed once a month, and as needed.

5. Data and Disk Destruction
Disks and drives are stored securely at CAN HQ until properly shredded or destroyed.  All employees and contractors are provided two trashcans, one for paper, disks and drives, and one for other materials. Trash is removed daily, and either stored or properly disposed of.

6. Training
CAN’s employees and contractors are required to help CAN maintain effective security.  Employees and contractors receive security training when they start at CAN, and are required to participate in training each year.  All employees and contractors are required to report any suspected or real security threat or breach.

7. Visitors and Guests
CAN has a lot of people that visit our offices.  All guests sign-in and sign-out at the front desk of Suite 200.  They use their drivers license or photo ID to sign-in.  All guests are provided with a visitor badge.  They are met at the front desk and their host escorts them until they leave the office.  CAN also maintains a separate WiFi network outside of CAN’s firewall for guests and employees that bring their own devices to work.  Occasionally, depending on the nature of a guest’s visit they are asked to leave their devices and bags at the front desk in Suite 200.

8. External Devices
CAN’s employees and most of CAN’s vendors, clients and contractors enjoy technology and are constantly investing in the latest and greatest consumer technology. CAN allows our employees, clients and contractors to bring external devices into our facilities.  However, external devices are not allowed behind CAN’s firewall, and are required to follow CAN’s security policies, including monitoring and management by CAN IT and security staff.

9. Network Security
The fidelity of CAN’s network is essential to protecting ourselves, our sensitive information, and our clients and partners’ networks.  We record and monitor all devices that connect to our network and their activity.  Logs are reviewed monthly and as often as necessary.  We also require that devices, including mobile, tablet, laptop, desktop and servers, use software to protect and identify malware and spyware attacks.

10. Disaster Recovery
CAN’s IT and Security infrastructure allows CAN to respond quickly to national, local, company, and individual disasters.  We maintain copies of all key systems in multiple locations, including static backups at CAN’s facilities.  All key systems, files, and applications are hosted and managed in a professional managed environment.  Using hosted solutions allows CAN to leverage state of the art providers with investments in hardware, facilities, fire protection and redundant backups.  Also, in the event of a disaster using hosted solutions allow CAN’s workforce to quickly relocate to a new physical office or a virtual office environment.  All that we would need is power and an Internet connection.

When designing CAN’s security policies we wanted to make them as simple as possible so that our security policies were easy to remember, follow and enforce.  There are more complex and sophisticated security systems, but simple systems get implemented, and only a security system that get implemented keeps anything safe.  CAN and our clients are confident that these security policies will protect CAN, our clients, and CAN’s sensitive data.  We are continually refining and improving our security policies.

Please feel free to ask any questions that you might have.

Category: Data Science | No Comments » Tags: , , , , , , , , , ,

Posted by: Matt Dickinson on March 6th, 2012 Leave a Comment

Occam's Razor and Model Complexity

When using predictive analytics to develop a model it is important to understand the principles of model complexity.  Occam’s Razor is a concept that is frequently stated, but not always fully understood.  The basic idea is that “All else being equal, simpler models should be favored over more complex ones.”  It is concept we both embrace and approach with caution so that it is not misused.

First, let’s flesh out the concept of Occam’s Razor beyond the simple aphorism given above as it can apply to predictive analytics.

Suppose I flip a coin ten times, and I get a run that goes “HHTTTHHTTT”.  After observing the coin flips I assess that there are two possible models for the behavior of the coin:

(A) The coin is fair and has a 50/50 chance of getting either heads or tails on each flip.  The observed run was just one of 1024 possible results of the ten coin flips.

(B) The coin flips are deterministic and will land in a repeating pattern of “HHTTT” which perfectly fits with the results of our sample of coin flips.

Without further experimentation I have no certain way of knowing which model is actually true.  If I were to flip the coin five more times, if I got anything other than “HHTTT” all confidence in (B) would be gone, the same cannot be said for (A).  This is because (B) is a much more complex model then (A).  It other words, it would take much more evidence to be confident in (B) over (A).

Keeping this concept in mind is important when developing predictive models.  With the huge volume of information and the massive data sets that CAN utilizes it can be tempting to include as many parameters as possible.  Not paying attention to the model complexity, and the evidence required to support the claims of observed relationships can lead to false assumptions, and predictions that are outside of desired bounds.

Another problem arrises when Occam’s razor gets misapplied.  A common mistake is that people misinterpret this to mean that models should be a simple as possible, when the thought process should be to keep models as simple as they need to be to explain the what is observed.

One of the more famous examples of this is in the history of the understanding of the motion of the planets.  In an attempt to explain the retrograde motion of the planets Ptolemy devised a complicated geocentric model where each of the known planets, including the sun, orbited the earth while also moving in their own smaller circular paths.

Alternatively, Copernicus’ heliocentric model, placing the sun at the center of the solar system, was a much simpler model and it fit the observed motion of the planets, as the planets are orbiting the sun at different rates.

As revolutionary as the Copernican idea was, it does fit Ockham’s premise.   At the time, Ptolemy’s model was a better fit for what had been observed. But, like the more complicated coin flip model the geocentric model fit what had previously been observed yet utterly failed when later observations did not fit.

Ptolemy's Model

Copernicus' Model

But, simpler models alone do not mean that that the truth is revealed.  Copernicus’ model was not perfect.  Later, when Johannes Kepler discovered that the planets move in elliptical orbits, not the circular ones as supposed by Copernicus, it made the model much more accurate at predicting the movement of the planets.  But, ellipses are much more complex then circles, what does this mean for Ockham?

Again, utilizing Occam’s razor is not a search for the most simple model, but the most simple required.  While Kepler added complexity to the model, it was complexity that was supported by decades of information gathering on the inconsistencies in the Copernican model.  More complicated models require more evidence to defend, which is not the same as saying they are indefensible.

Let’s go back to the coin flip example and change the scenario slightly.  Let’s say we were attending a magic show, and the magician claimed that he could flip a coin and make it follow the pattern “HHTTT” (i.e.  model (B) ).  Does this change our perception of the complexity of the models?  Of course it does.  We expect there to be a trick that will cause the magician’s claim to be true.

Like Kepler’s model, there is more complexity in the model that predicts a distinct pattern of coin flips, but the presence of new data (the magician flipping the coins, or the precession of planetary orbits for Kepler) allows us to have more confidence in the more complex model.

At Contemporary Analysis we solve hard problems, and hard problems often necessitate complex models, and complex models are not in themselves bad.  Throwing out informative parameters for just the sake of simplicity would strip away the predictive value of the models. Its about ensuring that the factors of the complex models are both valuable and grounded in sound theory.  This is why we don’t just jump into building models as soon as we have data.  We spend a lot of time working with customers to understand the nature of the environment we are modeling.  Simple or complex, if our theory is misinformed there is no way our models can accurately reflect the real world.

References:  

http://philosophy.wisc.edu/forster/520/Chapter%203.pdf 

http://www.stat.duke.edu/~berger/papers/ockham.html

http://andrewgelman.com/2004/12/against_parsimo/

Category: Predictive Analytics | No Comments » Tags: , , ,

Posted by: Nate Watson on March 5th, 2012 Leave a Comment

Nate Watson is a Navigator at CAN.  His job is to help people work smart.  He helps CAN’s clients understand what CAN is capable of, identify the right solutions for them, develop a plan, and work with them to implement their specific plan to work smart.  In this video he explains how CAN helps our clients.

Category: Client Stories, Video | No Comments » Tags: ,

Posted by: Nate Watson on February 27th, 2012 1 Comment

CAN’s goal is to use predictive analytics and data science to help our client’s work smart.  While predictive analytics and data science can help a company generate more profit, the technology can be very complicated and the process very cumbersome.  CAN is committed to making predictive analytics and data science simple.  Simple systems get implemented, and our systems are only valuable when they are implemented.

CAN’s Navigator program is key to making predictive analytics simple.  We developed the Navigator program, because in addition to great software, data visualization and reports, wanted to provide our clients with great customer support.  Navigator’s are here to help introduce you to CAN, predictive analytics and data science, understand your business, create a plan so that you can work smart, and then work with you and CAN data scientists to implement the best solution for you.

CAN makes sure that Navigators are ready to show you the way.  Each Navigator completes 8-weeks of training at CAN HQ before they are ready to work with clients.  They are trained on data science, predictive analytics, customer service, and principals of economics and business.  If you are ready to work smart they are here to help show you the way.

Category: Client Stories, Video | 1 Comment » Tags: , , ,

Posted by: Grant Stanley on February 23rd, 2012 Leave a Comment

Managing Smart People: Leaders and Experts

CAN’s success depends on our ability to provide great jobs to innovative and creative professionals. However, managing these highly intelligent and creative people can be challenging.  Smart people want clear career paths, frequent meaningful promotions, and competent managers.  If smart people perceive a position lacking, they quickly lose motivation.  For example, smart people quickly lose respect for a manager they perceive as being incompetent or  less intelligent.  CAN has tried to address the challenges of hiring smart people.

First, we have limited the number of positions that are not core to the business. If possible we have outsourced any position that is not sales or operations. Essentially we have outsourced for quality not price. This has created an organization were almost every position has a clear career path. This has allowed CAN to focus on building in-depth training programs that allow us to develop our people so that they can earn frequent and meaningful promotions.

Second, we have created two career paths. People can be promoted as leaders or experts. Leaders are people that have natural talents working with people, helping, motivating and inspiring them. Experts are people that have natural talents working with ideas and technology. While being a leader or expert is not mutually exclusive, they are promoted based on their strongest natural strengths.  This allows them to focus.

Good leaders can respect the technical prowess of experts, and experts can respect the technical prowess of leaders. This mutual respect allows leaders and experts to hire the best people without feeling threatened. Imagine a company where managers are encouraged to hire the best people possible without feeling threatened.

This is one of many posts we will publish on how CAN is creating a work environment for smart people.  CAN’s purpose is to help our clients work smart.  That is why CAN is committed to being a place where smart people love to come to work and help our clients.

Category: Management | No Comments » Tags: , , ,

Posted by: Nate Watson on February 22nd, 2012 1 Comment

What to put on your Business Card

I received a business card from a networking event. I do what I always do, went to my CRM to add it to my contact list. I wanted to send them a “thank you for coming to our event” email. There was a problem. No last name. I have never, in my career as a sales person, seen the likes of this. I can usually catch someones first name because its usually simple. Bob, Frank, Susie, etc and this one was no different. A simple first name. I know they told me their last name, however I can’t remember much less spell it. After hitting the ceiling about not knowing their last name, I thought, I will just look at their email address. Most of the time its first and last name (me excluded), and this is where I really shook my head. There was no email address…

<shocked face>

<more shocked face>

It is 2012. We email now. We connect on Linked In, Facebook, Google Plus, and ten others I have never heard of. Without the right information on your business card it is impossible for me to connect with you. If I can’t connect with you then I will never find out about you, learn to like you, exchange leads with you, let alone buy something from you.

I pitched the card in the trash. If they can’t make it easy for me to contact them, I’m not going out of my way to try to contact them.  I can’t even  find that person on LinkedIn, Facebook, or Google plus. I don’t have their last name. I will not be giving my money to this person.

I still am shaking my head. They had a lot of other things on their card, such as what they do, name of business, and their website address. However, no last name and no email.

Here is everything that you need to make sure you have on your business card. You can have other information, graphics or pictures on your card, but you need to have the following. Also, it needs to be in a size, font and color that makes it easy to read.

  • Your name–First and Last, I am disappointed that I have to point this out.  Do not hand out a business card with just your first name. Who do you think you are, Snuffleupagus?
  • Your Title.  In business, your title is a filter that people can use when contact you.  Working at a small company I used to think I didn’t need to include my title.  I had so many different roles, and I didn’t want to be egotistical.  However, I realized that including my title wasn’t for my benefit, and that it helps people decide how to interact with me.
  • Your company name.  I have had cards before with no company name.  Please don’t had me your personal card.  I want your business card.  If I meet you while networking I want to hire you or refer you as a business not a individual.  Also, don’t hand me a stack of cards, pick one card.  Don’t be the Dealer.
  • Your address.  I might want to come by and see you in person or on Google.  I understand you might have a home office, then put a PO box.  At an absolute minimum put your city and state.
  • Your phone number and email address.  You need to make it as easy to contact you as possible.  Some things are best communicated over the phone, and somethings are best communicated using email.
  • Your website address.  You must have one of these.  We can discuss how you succeed without a website, but you will lose the argument.  Have a website, even if it is a simple one or a template.  WordPress.com or Blogger.com are more than acceptable.  You don’t have to spend tens of thousands of dollars, but it is important that you have a web presence so that I can get to know you.

When you hand me your business card please make it easy for me to contact you.  Until next week, Happy Hunting!

Category: Sales & Networking | 1 Comment » Tags: , , ,

Posted by: Jefferson on February 20th, 2012 Leave a Comment

A Preattentive Dashboard

The visual world is extraordinarily complex.  For example a quick scan of my desk reveals hand-written notes, dry erase markers and USB thumb-drive.  While I recognize these objects rapidly, I experience them at a basic visual perceptual level long before I can label or describe them.  This low level of perception is what is called preattentive processing, or visual processing that occurs without deliberate attention.  Preattentive processing can be used to create dashboards that easily communicate extraordinary amount of information per pixel and need very little effort to understand.

Characteristics such as shape, size, color, contrast, luminosity and motion are examples of features that are perceived at this low level of perception.  These factors are referred to as preattentive visual cues and help our brains categorize and filter our visual environment.  Simply put, preattentive features are the information we gain from a visual scene before we direct attention to salient features to extract deeper meaning.

Humans are very good at extracting meaning from complex visual environments.  However, this does not mean that we should be required to.  This is certainly the case when designing dashboards and data visualizations.  To keep things simple, CAN designs visualizations that focus on using preattentive imagery.  Preattentive imagery allows us to communicate complex information in a rapid and concise manner.  Our lives are complex enough.  We deserve simple dashboards.

CAN recently competed a project for one of our clients examining the accuracy of industry level forecasts for every Metropolitan Statistical Area (MSA) in the United States.  The report contained over 600 pages!  Six hundred page reports do not get read, and consequently are rarely of value.  We decide to go back to the white board.  A 600 page report contrasts with our goal of making complex information easy to understand and act upon.

We needed a way for our client to explore and understand the meaning of our  complex analysis.  The result of our research are meaningless if they are not implemented.  We started our design process by defining the business question our client needed to answer, “Which forecasts are inaccurate, and why?”  Our client needed to navigate forecast accuracies by geography, industry sector, and the duration for which the forecasts are accurate.  The dashboard we developed presents a 600 page report on one screen and can be fully navigated with three clicks.

Pre-Attentive Dashboard 1

 

Users explore the data by selecting areas on the map, concepts or MSAs individually or in group.  This action updates the State, MSAs, forecast accuracy durations and industry sections for the selected region.

Pre-Attentive Dashboard 2

For our client, forecasts with greater than 90% accuracy are deemed acceptable, and closer examination is need for forecasts with 75 to 80% accuracy.  We built these tolerances into our design.  Notice the positioning of the grey crosses in each pane.  The thin pink line shows 90% accuracy while the pink band shows 75-80% accuracy.  As users explore the dataset, this relationship allows them to quickly identify and focus on values which are below the desired range.  Glancing at the MSA window, it is clear that forecasts for Yuba City and Merced are suspect, and MSAs like Modesto should be examined more closely.

Let’s take a closeup look.

A Preattentive Dashboard 3

We’re looking at an overview of all Californian MSAs across several industry Concepts and at the Duration of Forecast.  It’s immediately clear that the accuracy for Concept #4 is ‘in the red’.  At this point, end users who are experts in the data can ask questions about what is going on in Concept #4, and discuss how this accuracy impacts future planning.

When elements on a page are judged to a similar standard, it is useful to maintain consistent visualization techniques.  For example, we kept the theme of the reference lines constant across the Concepts and Duration of Forecast window. This helps reduce the effort required to use the dashboard and frees up some cognitive bandwidth to focus on the meaning of the data.

To visualize the Duration of Forecast, we carried over the reference line theme used in other panes.  The purpose of this window is to let the user decide; for the region or categories they have selected, how accurate are the forecasts X quarters out.  All the user needs to do is watch for where the grey line crosses the pink lines.  This is a simple graphic.  Users know they can expect this combination of forecasts to be 90% accurate up to 14 quarters out, and after 18 quarters the usefulness of the forecasts dissolve.

This approach strikes true to CAN’s goal of helping businesses work smarter.  We turned a 600 page report into a single page that can be navigated with three clicks.  Rather than increase complexity, we just built simplicity.

Category: Dashboards and Visualizations | No Comments » Tags: , , ,