close

innovation

collaborationinnovationInnovation Management

Mapping Expertise and Illuminating Dark Assets

by Alanna Riederer

At some point in your life, you’ve found yourself describing a project you’ve worked on to a friend. They interject, “I’ve done something similar to this before,” and go on to describe a field or skill you didn’t know they were familiar with. You’ve just uncovered some dark assets about your friend: a set of skills or knowledge that were only discovered due to an accidental trigger.

This can be problematic when it comes to group projects, whether you’re working with an existing team or you’re putting one together. The people and tools available to you are limited to those you are aware of or those cataloged in scattered directories and lists across the internet. There are far more dark assets than known assets.

In order to build and branch teams more effectively and innovatively, we need two things: a map and a compass. We build a map so that we can see the dark assets. We equip ourselves with a compass to guide us towards relevant assets.

We like to use a network diagram as our map.

Screen Shot 2019-05-07 at 7.46.30 AM

We use these networks to map people and resources. People could be resources, but we tend to distinguish people from inanimate assets, like publications or technologies.

We dub these people and resources “entities.” Every entity has “attributes” that describe it. For instance, people have interests, skills, passions, publications, and projects associated with them. A publication has a date, an author list, an abstract, and key terms. As I list these out, imagine how connections would form in the network between entities across shared attributes.

In the network below, you can see some shared connections on technology, for-profit, javascript, music, and sustainability and unique perspectives of Education, Social Good, cello, art, and AI.

In addition to the map, we need the equivalent of a compass – finer tools to navigate this environment. These tools illuminate the entities that bring the most complementary skills to our team composition.

  • Suggestion algorithms allow us to find teammates that add complementary differences to our team.  This is helpful for deciding which entities we should focus on in our map.
  • Artifact-recording tools allow us to document and track ideas inside documents and see how they connect.
  • Termscapes are a richer map for navigating the content that our community generates or studies. They are generated by analyzing unstructured text about a collection of entities and arranging those entities into a landscape of their terms.

Using these tools allows us to remove the accidental nature of discovering important resources. What tools do you use or wish you had to approach this problem?

The images in this post are screenshots from Data+Creativity City, an application that captures connections between members of the Data+Creativity Meetup. If you’re a member, come join the City and see how you’re connected!

read more
innovation

Innovative Technology Needed to Improve Crisis Response

article by and images from Dr. Victor Soji Ladele

Humanitarian crises in general are affecting more people, for longer. One in every 70 people around the world is caught up in crisis and urgently needs humanitarian assistance. Food insecurity is rising, with the number of people experiencing crisis-level food insecurity or worse increasing from 80 million to 124 million people between 2015 to 2017. The number of forcibly displaced people rose from 59.5 million in 2014 to 68.5 million in 2017. Natural disasters and climate change continue to affect 350 million people on average each year and cause billions of dollars of damage. Pandemics — large disease outbreaks that affect several countries — are rising as a global threat and pose major health, social, and economic risks. (Source: United Nations Coordinated Support to People Affected by Disaster And Conflict)

terrain_sm
Approaching the border between Liberia and Guinea.

My recent experience on the frontlines of a large-scale Ebola outbreak and many years of health emergency response, confirm that health system weaknesses in many countries are a source of global health insecurity. In an article in the influential New England Journal of Medicine in 2015, Bill Gates said, “There is a significant chance that an epidemic of a substantially more infectious disease (than Ebola) will occur sometime in the next 20 years. In fact, of all the things that could kill more than 10 million people around the world, the most likely is an epidemic stemming from either natural causes or bioterrorism.” In this interconnected world, a threat in one place is a threat everywhere.

Humanitarian action is intended to save lives, alleviate suffering, and maintain human dignity during and after crises and disasters, but often fall short of its lofty ideals in practice. The way it works is that most of the estimated $27.3 billion allocated to international humanitarian response comes from governments, but action is via proxies, the “humanitarian actors” (2017 Global Humanitarian Assistance Report by Development Initiatives). Humanitarian actors come from a plethora of UN agencies, the International Federation of Red Cross and Red Crescent Societies, military branches, non-governmental organizations (NGOs), local institutions and donor agencies.

coordination_sm
Operations conference room in Liberia during the Ebola response.

In order for actions to be quick, agile, and impactful, coordination is paramount. Information management is the bedrock of coordination, and it is fair to say that this is one of the most important activities during a crisis response. However, in recent years, networks connecting humanitarians have expanded so quickly, that the volume of data flowing through these pathways — and the number of information sources — have become in and of itself a problem. Data comes fast and hard from many sources, and adoption of ICT applications to improve outcomes has been relatively slow. The innumerable NGOs that are working on international humanitarian issues cannot alone address needs of such magnitude and diversity. To tackle these complex problems requires deeper levels of collaboration between formal humanitarian organizations and tech communities like Data+Creativity.

inspection_sm
An Ebola treatment center closes after the last patient is discharged.

Taking the relatively recent Ebola pandemic of 2014-2016 as a case study, nothing prepared the health emergency responders, myself included, for the difficulty of containing the outbreak.  With its many intense “waves of transmission”, dealing with the deadly pandemic challenged assumptions like never before, but at the end established a new nexus of cooperation among traditionally dissimilar groups like – community chiefs, epidemiologists, pastors, imams, hobbyists, doctors, financiers, anthropologists, logisticians, politicians, computer scientists, and technologists.

map_smBetween its start in 2013 in Guinea’s dense forest, and end in 2016, the Ebola pandemic, which originated in a remote village, spread south to Conakry, Freetown and Monrovia, east to Lagos, north to Bamako, northwest to Dakar, and by jet to the United States, Spain, the U.K. and Italy. The virus killed at least 11,315 people in seven countries and caused more than 28,600 known infections. Beyond the immediate horror and loss of life, the usual routines of daily life in the most affected countries came to a halt: population movement was restricted, harvests interrupted, markets closed, and volume of trade contracted. Reduced commercial activity in the surrounding region reversed recent economic gains. An estimated $2.2 billion was lost just in 2015 from the gross domestic product (GDP) of the three most affected countries. This regional economic decline in turn caused a widespread crisis of food security, affecting hundreds of thousands of people and turned into a separate humanitarian situation of itself.

mtg_sm
A meeting with several partners, including local health authorities in Lofa County.

Prior to Ebola, I had been active in medical humanitarian assistance and health emergency relief for many years. Having gained experience both in tiny, poor village health centers and at higher strategic levels with responsibility for broader policy decisions. I was already convinced of the effectiveness of tackling complex problems with complementary, cross-cultural and cross-disciplinary teams. The idea is gaining broad acceptance in the humanitarian and global development community, but this model of cooperation is yet lacking a purpose-built Information and Communication Technologies (ICT) tool. During the Ebola outbreak, I served as information management officer in addition to my role as team lead with the World Health Organization. Then and now, a framework for blending local knowledge and expert knowledge is absent. The lack of an effective platform to harness local expertise within the humanitarian affairs coordination framework has brought about a shocking amount of missed opportunities in humanitarian crisis response.

Despite the sorrow and devastation, as Bill Gates has noted, “perhaps the only good news from the tragic epidemic (Ebola) is that it may serve as a wake-up call. We must prepare for future epidemics of diseases that may spread more effectively than Ebola.” The world is at greater risk than ever from global health threats. We may not know what the next epidemic will be, but we know that one is coming. Disease threats can spread faster and more unpredictably than ever before. People are traveling more, food and medical product supply chains stretch across the globe, and biological threats as well as drug-resistant illnesses pose a growing danger to people everywhere.

During crises, professionals tend to avoid novel approaches that have not yet been tried and tested. They instead reach for familiar and trusted ways. As a result, humanitarian relief operations often deploy older technologies. Due to poorly adapted tools, training, and strategies, responders are increasingly ill-prepared to produce useful knowledge from the flow of information and data. There is thus an urgent need for innovative groups to engage early with humanitarian organizations, explore joint projects, and strengthen relationships before crises occur. These sorts of engagement will help both sides better understand each other’s modus operandi. As collaborations start to yield fruit, solutions will be developed and deployed to make all of us safer.

celebration_sm
The first celebration of the end of the outbreak. Four days later there was a new case.

For startups and midsize companies, this presents an incredible opportunity and the timing is right. The timing is right because the biggest funding agencies are currently enamored with the idea of private sector engagement (PSE) as a strategic approach to international development and humanitarian crises response (USAID). Furthermore private foundations, traditionally a good source of funding for innovation, are getting more assertive and acting with more ambition. This is a good time for data practitioners, software developers, researchers, creative technologists and thinkers  to build relevant partnerships with humanitarian and international development organizations, who on their part have become more supportive of broader engagement to help forcibly displaced people, respond to natural disasters, and prevent pandemics.

The key to having impact quickly during complex emergencies is through cross-disciplinary collaboration. Funders realize this and are actively seeking for great ideas to get behind. To close with a quote from a popular author, Marianne Williamson: “Success means we go to sleep at night knowing that our talents and abilities were used in a way that served others.”

 
Dr. Victor Soji Ladele presented at the Data+Creativity Meetup in Oklahoma City, OK, on February 21, 2019. Watch the video archive here.

read more
collaborationinnovationInnovation ManagementResearch

Sparking Ideas for Visualizing Innovative Research Teams

A collaborative blog series about collaborative research: a data scientist and a cognitive psychologist combine perspectives.

co-authored by Dr. Alicia Knoedler and Dave King

Dr. Alicia Knoedler: For the past 18 years, I have sought opportunities and means to advocate for researchers working to develop and accelerate their research programs. I had the very fortunate opportunity to meet Dave King in 2014 when he relocated his company to Oklahoma City. At that time I was the Associate Vice President of Research and leading a team called CRPDE. One of the core missions of this team was to assist researchers in their efforts to form teams and seeking resources and funding for those teams. Although it is challenging to form teams that work together well and pursue innovative work together, it was equally if not more challenging to demonstrate why a newly assembled team would be innovative.

When I found out that Dave had designed his company, Exaptive, to apply data analytics and data visualization tools to matters of team dynamics and innovation, I knew we had much to discuss and ideas to explore! We’ve been working together ever since, and this blog post is the first in a set of collaborative blog posts between the two of us.

Dave King and Dr. Alicia Knoedler discuss transdicplinary research teams.

In each post, we aim to take issues that I have experienced “in the trenches” of facilitating collaborative research and consider them through the technological lens that Dave brings. We hope you enjoy this series, and we encourage you to let us know if there’s a particular collaborative research challenge that you’d like us to tackle.

The way that innovative research gets funded is changing.

Teams that choose to pursue grant opportunities need to keep up with the trends if they want to secure dollars supporting their projects. Open accessFAIR data, and interdisciplinary collaboration are a few topics that have become more and more important to funders, whose priorities often reflect progressive social change and broad issues like inclusivity and accessibility.

As an example, considering various funding opportunities at the National Science Foundation (NSF), a federal funding agency with a long history of funding research teams and striving to advance groups of researchers to exceed their potential, here is a sampling of program expectations regarding teams:

  • Clearly establish the means of developing a coordinated, collaborative approach involving investigators across different institutions and jurisdictions. Describe interactions with other groups and organizations among the jurisdictions, and at the national and international levels, as appropriate (NSF EPSCoR Track 2 solicitation)
  • Support will be provided for groups of investigators to communicate and coordinate their efforts across disciplinary, organizational, institutional, geographical and/or international boundaries. The objectives are to facilitate open communication and exchange of information and resources, to integrate research, education, and/or cyber infrastructure activities of scientists, educators, and engineers working independently on topics of common interest; to nurture a sense of community among young scientists, educators, and engineers; and to minimize isolation and maximize cooperation so as to eliminate unnecessary duplication of efforts. (NSF Research Coordination Network (RCN) solicitation)
  • Team Formation: The process by which all necessary disciplines, skills, perspectives, and capabilities are brought together. Successful teams are interdependent, multidisciplinary, and diverse and can work and communicate effectively even when geographically dispersed. Team formation includes strategies to overcome barriers to effective, collaborative teaming, including the integration of members with different areas of expertise, different vocabularies and core values and ways of approaching problems, different understanding of the problems to be addressed, different values, and different working styles. (NSF Gen-4 Engineering Research Centers (ERC) solicitation)

An org chart, really?

I have worked with many teams. In the course of catalyzing and developing nascent teams, the processes to form teams, identify and include members, and establish team culture can be onerous. Creating representative ways to describe and visualize the teams as connected, integrated and cohesive groups of individuals working together can also be challenging. Unfortunately, in efforts to seek funding and resources for teams, the decision is often made to conservatively approach team visualization, using an organizational chart or similar hierarchical rendering to communicate roles and some relational pathways.

The exemplar solicitations above are challenging convention and attempting to expand the capabilities and expectations for research teams. But some of the requirements in these solicitations remain conventional. It is time for a change; not only in imagining how to visually represent teams but moving beyond visual relational images to technology platforms that serve to support the teams’ behaviors, dynamics, decision-making, collaborative work, and their potential to innovate together.

Let’s explore the NSF ERC solicitation in a bit more detail. The solicitation specifies that a successful proposal will delineate:

  • The overall management and reporting structure of the ERC.
  • Which personnel or groups will be responsible for Research, Engineering Workforce Development, Diversity and Culture of Inclusion, and the Innovation Ecosystem. Please explain the relevant experience and expertise of these individuals and how they fit their assigned roles. These individuals should be included in the leadership team.
  • An organizational chart, including advisory boards and the reporting/feedback loops involved.

The accompanying narrative for the organization chart should define the functional roles and responsibilities of each leadership position, and how these positions support the integrated strategic plan described earlier. It should also define the functional purpose of any additional advisory bodies that are deemed necessary to support the four foundational components, accomplish the proposed ERC vision, and achieve the desired long-term societal impact. Note that the functional roles of the two mandated ERC Advisory Bodies, the Council of Deans and the Student Leadership Council, are defined earlier in the section on Community Feedback. Since the quality of team member interaction is critical to team effectiveness, describe the managerial processes overlaying the organization chart that will be used to integrate the team. Please provide sufficient detail to allow critical evaluation.

The NSF ERC solicitation suggests that an organizational chart is the way to go. It details what the organizational chart should demonstrate: functionality, relationships, and integration within the team. These are important features of the ERC teams but will a two-dimensional, non-interactive, hierarchical representation really align with what the Gen-4 ERC teams are expected to do?

The Gen-4 ERC program has been re-envisioned. So, let me invite Dave to share his perspective on how the representations of teams can be re-envisioned too.

Ideas are networks. Your team should be, too.

Dave King: I don’t know nearly as much as Alicia when it comes to assembling academic researchers or applying for grants, but as a software architect and data scientist, I do know one thing for sure — a tree is not the same thing as a network. If you’re not sure what I mean by that, just check out this Dilbert cartoon:

The idea of printing out a website is laughable because a website is, well, a web. It’s a set of interconnected content that can be navigated in a multitude of different ways from a multitude of different directions. It’s not a tree. Sure, you can try to make it look like a tree by creating a “site map” like the image below:

There is some utility in being able to look at a website like that, because it helps you understand how a website is built. But it doesn’t really capture at all how a website is used. If you visualize the traffic through the different pages of a website, you don’t get a hierarchical tree, you get something like this:

The difference between those two visualizations and what they represent, how something is built vs. how it behaves, encapsulates exactly the problem with trying to convey the innovative trans-disciplinary nature of your research team through an org chart. The org chart might show how the team was built, but it doesn’t provide any insight into how the team will behave.

Like with a website, where it’s critical for a person to be able to jump around from page to page regardless of hierarchy, in research teams it’s critical for members to similarly jump from perspective to perspective and from expertise to expertise, because that sort of jumping around is exactly the process of ideation that makes trans-disciplinary teams so powerful, and different from multi-disciplinary teams. Just because you assemble a team that includes different expertise doesn’t guarantee that that expertise will be integrated together in synergistic ways. Said another way, it’s easy to build teams that have siloed experts within them (trees) but much harder to demonstrate teams that are true collaborations (networks), which is ultimately what organizations like the NSF want to fund.

Technology can help!

The good news is that when it comes to building networks, and visualizing them, technology can really help. There are an increasing number of tools for network visualization. Many of these tools are for technical developers, but the barrier to entry is getting lower and lower as it is becoming increasingly recognized that non-programmers have reasons to visualize networks too. It is now fairly easy to take an excel file and transform it into a network. For example, I made a spreadsheet of the two-person team comprised of me and Alicia, and some of our expertise and focus areas:

Then I used an Exaptive xap (pronounced zap) to turn it into this network:

(If you’d like to use this application yourself to experiment with visualizing your own team, just let us know here.)

Stephen Johnson, author of the book Where Good Ideas Come From gave afantastic TED talk about how ideas are networks. My hope is that as technology makes it easier for more people to define networks, visualize networks, and quantify the dynamics of networks, they will be able to start providing organizations like the NSF not org charts that ignore the inter-relationships within a team, but network charts that illuminate those overlaps. It’s only through that sort of visualization that a team’s true potential for innovation can be conveyed.

Not all team networks are structured the same way.

Once you start looking at teams from a network perspective, you open up new opportunities for characterizing teams. In the Harvard Business Review article “Better People Analytics”, Paul Leonardi and Noshir Contractor look at how different team network structures may offer different advantages for different situations, developing a set of team “signatures”. The figure on the left shows two signatures covered in the article, one better for innovation, one better for getting projects done on time!

These signatures are important because they open the door for us to be able to do more than just visualize teams — they allow us to start to quantify some metrics of team performance.

I’m particularly interested in a team’s capacity for cognitive exaptation — the application of an idea in a different context than the one in which it originally emerged — so I’ve focused my company on creating a platform that can help find teams more likely to exapt tools and techniques across fields. The screenshot below shows our analysis of the possible 3-person scientific teams that could be assembled from 143 scientists associated with a large pharmaceutical company’s research program. There were over half a millionpossible 3-person teams that could be assembled from just that small pool of researchers, but by modeling each possibility as a network, and then applying some analysis on each network’s signature, we could organize all those possibilities along a meaningful axis and allow for the interactive inspection of the different structure along that axis:

The goal is to augment human intelligence, not automate it.

Once we start talking about applying algorithms to “quantify” things, we start getting into the dangerous territory of thinking that we might be able to use algorithms to replace human decision making. Even though I’m a technologist and data-scientist, I’m not a fan of that approach. Don’t get me wrong, I think there are plenty of areas where computers can probably do a better job than humans making certain types of decisions, but I don’t think that designing innovative teams is one of them.

There are so many subtle parameters involved in high-performance teams and their interpersonal dynamics that a computer has no hope of having the complete picture. The computer, therefore, has to be used as just a tool in a human’s process. It’s important for that process to be a collaborative back-and-forth between what the computer can analyze and what the human can intuit. Computers can help separate some of the signal from the noise, but humans have to be able to iterate based on what the computer is helping them see, adding their own knowledge and experience into the mix, steering the computer in the most fruitful directions. Steve Jobs used to say that a computer is like a bicycle for our minds. In the case of team-building, I think a computer is like a flashlight for team-leads and facilitators.

That’s where people like Alicia come in. Research facilitators know where to shine that flashlight and how to take what the computer is telling them and combine it with all the things the computer doesn’t know. They know how to take the visualizations that a computer can produce and place them into the broader context of a proposal for innovative research. I’m excited about giving those people better tools to do their job. There is an increasing proliferation of research profiling systems that help organizations capture and harvest all the information they have about their researchers, publications, grants, focus areas, etc. In the effort to build those catalogs, it’s important not to forget what all those data are for — being able to assemble teams that can do innovative research, and being able to convey to sponsors why those teams are worth funding.

Where do we go from here?

Dr. Alicia Knoedler: We started this conversation by suggesting that providing more insightful visualizations for research teams is among the many opportunities for innovation in research programs. The technology is readily available and becoming easier to utilize. Dave and I are both excited by the prospect provided by technology to team facilitators to enhance their powers of observing, noticing, and catalyzing behaviors within research teams. But we also want to promote these ideas within funding agencies, research team sponsors, and to the reviewers who evaluate proposals. There is opportunity to open up requirements within funding programs for new ways to show team compositions, illuminating team structures and functions, the dynamics and roles of team members, and the proposed behaviors that will lead to competitive research outcomes.

We know that investigators submitting proposals for research funding know to follow the solicitation instructions to the letter. But if the solicitations are requiring conventional, traditional information for team descriptions, it is difficult for research teams to propose something really new. We think the accessibility of these new tools and technologies and will inspire others to push beyond the conventional approaches to suggest that visualizing research teams can be just as innovative as the research they are proposing.

read more
innovation

Cowboys and Inventors: The Myth of the Lone Genius

I recently moved from Boston to Oklahoma City. My wife got offered a tenure-track position at the University of Oklahoma, which was too good an opportunity for her career for us to pass up. Prior to the move, I had done a lot of traveling in the US, but almost exclusively on the coasts, so I didn’t know what living in the southern Midwest would bring, and I was a bit trepidatious. It has turned out to be a fantastic move. There is a thriving high-tech startup culture here. I’ve been able to hire some great talent out of the University, and we’re now planning to build up a big Exaptive home office here. Even more important, I was delighted to find a state that was extremely focused on fostering creativity and innovation. In fact, the World Creativity Forum is being hosted here this week, and I was asked to give a talk about innovation. As I thought about what I wanted to say, I found myself thinking about . . . cowboys.

Before I came to Oklahoma the image I had in my mind was pretty much like this:

TheCowboy
Image by Kim Bui, IEPPV

And while there is certainly a cowboy culture here, I have yet to see anyone in downtown Oklahoma City ride off on a horse into the sunset. This Marlboro Man image is not the Oklahoma of today, but nevertheless it’s an image that persists, quite powerfully, in our collective imagination.

The more I thought about my new home in OKC, and the mythology of the Marlboro Man, the more I thought about the myth of the lone genius. We love the idea of the lone genius. Perhaps the desire to think of innovators this way is particularly American? Perhaps it comes from our history and our ethos, born from the enviable rugged independence of the frontiersman and reinforced in the next generations by endless cigarette ads? We often use Thomas Edison as the example of the quintessential inventor, and when I did a Google image search, I was quite struck by the pictures I found, like this one:

Edison
Photograph by AFP/GettyNational Geographic, Published October 6, 2014

The above picture of Edison strikes me as the intellectual equivalent of the Marlboro Man image. We know this picture of Edison isn’t the whole story. We know he had a huge team of people working under him in his lab, all of them conspicuously absent from the picture above. We know he performed in-depth research on other inventors’ work, like that of Joseph Swan, who had invented a less practical but functional light bulb years before. Swan’s picture is yet another Marlboro Man lone inventor image:

Swan
Image courtesy of the German Wikipedia page on Swan

I think that in order to push the discourse about innovation ahead, we need to find new ways to describe and exalt our inventors. Indeed, Edison was a genius, as was Swan, but their genius lay in how they synthesized previous work and connected together the contributions of others, adding their own contributions as was needed to fill in the gaps.

It’s a challenge to capture, explain, and promote this view of innovation and innovators. Increasingly we are recognizing that ideas are networks, but this recognition gives us the challenge of figuring out how to represent them. The field of data visualization has had a notoriously hard time figuring out how to display complex networks. They so frequently end up looking like a big mess that the term “hairball” has become a technical term in the field, for reasons the network below makes obvious.

HairBall

If we are to push the discourse about innovation forward, we need to find ways to visualize idea networks in ways that are just as striking and inspirational as the portraits of Edison and Swan.

hepatitis_C_coauthorship_network

This image, created by London-based group Social Physicsshows the co-authorship of papers by researchers studying Hepatitis C. It’s still a bit of a hairball but certainly a beautiful one.

A while back we used Exaptive to analyze the hundreds of different data visualization projects that were collected on the well-known site VisualComplexity, and to draw a network of the contributions based on their field of study and author:

VC-BenFry-Inset

Once we did so, data visualization guru Ben Fry was clearly revealed as a hub in the network, his many projects spanning many disciplines. Which is a better picture of Ben the innovator, the one above where he is a hub connecting many disciplines or the one below in the style we are more accustomed to?

benfry06

As a photographer, I love portraits like the one above. As a student of innovation, I have come to love network diagrams much more. As a software architect, when I sat down to design the Exaptive platform, it was clear to me that it needed to be inherently based on a network structure. To represent that underlying structure, we decided to use a dataflow programming paradigm within our development environment:

xap

All programming is modular. All programmers build programs leveraging libraries of functions built by others, but the act of writing a program often obfuscates these connections, much like the act of invention often obfuscates all the prior art that made it possible. When we designed Exaptive we wanted to allow people to build new things, but we wanted to do so within a framework that preserved the network of how they did so. We believed that the network was the idea itself and equally important as any particular output. We also believed that the most important things behind each of those code modules was the person who wrote them and the person who used them. We believed that any system that was making it easier to connect code together should make it easier to connect the people behind that code together too. We recently had an exciting project show us just how important this is when it comes to generating new and novel solutions.

A few weeks ago we started work on an interesting data science project. Our contact at a large NGO had a bunch of longitudinal data about every country on Earth, and wanted help trying to group the countries together by these data. Matt Coatney, a data scientist who was using the Exaptive platform to experiment with neural networks on time-series data, decided to take on the challenge. He started experimenting with converting the country time-series curves into alphabetic sequences. He was thinking of DNA and hoping that once he had alphabetic sequences he could use DNA clustering algorithms to cluster the countries like they were different genetic codes. Exaptive’s Science Advisor, David Merberg, a PhD cell biologist, got alerted to the work Matt was doing. When he saw the letter strings coming out of Matt’s algorithm, he remarked how they were more like proteins than DNA and perhaps better suited to protein clustering techniques. This led Matt to push his algorithm in a new direction, ultimately producing a novel way of clustering global country data based on the techniques that David clued him in to from genetics. It was innovation in action, and if I were to draw a picture of it, it would look like this:

Coatney

This to me is what true invention looks like. This project involved a great exaptation, taking something from one field and applying it in another in a new way. It involved three different people, from three different disciplines, living in three different states, and it all got done in three weeks. It’s a messier picture than the nice neat portrait of Thomas Edison standing proudly alone in his lab, but I think these are exactly the sorts of pictures we need to get better at learning how to communicate. We need to better learn how to value the messy interconnected hairballs of idea networks and give them just as much swagger as those cowboys riding off into the sunset.

read more
innovation

Einstellung Effect: What You Already Know Can Hurt You

Author – Stephen Arra, Developer

The Einstellung effect is a psychological phenomenon that changes the way we all come to solutions and impedes innovation.

light_bulb_outside_box-1
(Image Source: http://victoriousvocabulary.tumblr.com/post/15446374280/einstellung-noun-the-einstellung-effect-is-the)

Every day we solve problems – from choosing the quickest way to work, to how we’re going to fix a problem for that one client. How do we know if our solutions are any good? What if there is a much better solution that we haven’t thought of yet?

I recently came across a cover letter where someone said, “Every solution comes to me eventually”. This struck me as a strange thing to say. We don’t have visibility to every solution; we all have unknown unknowns. But even further, known knowns may not even make a connection for a certain problem. The Einstellung effect may occur, preventing us from considering all the available solutions.

The Einstellung effect occurs where preexisting knowledge impedes one’s ability to reach an optimal solution. We become unable to consider other solutions when we think we already have a one, even though it may not be accurate or optimal. It leaves us cognitively incapable of differentiating previous experience with the current problem. So we may solve a problem but we don’t actually innovate.

Einstellung is a German word that translates to setting, mindset, or attitude. The brain attempts to work efficiently by referring to past solutions without giving the current problem much though. It’s stuck in a mindset. We apply previous methods to a seemingly similar problem instead of evaluating the problem on its own terms. This effect presents across disciplines and skill levels. Whether or not we know it, we all experience it.

Experiments

The classic experiment used to validate this effect was conducted by Abraham Luchins in 1942 – the water jar problem.

water_jar_problem

(Image Source: http://www.kn3w-ideas.com/why/fixedness-its-all-in-the-mind/19-fixedness-abraham-luchins)

Participants were separated into two groups, one given a few priming questions before the core question. The priming questions led the focus of the first group to a particular method of solving the solution. When presented with the core problem, one that couldn’t be solved with the same technique, they were unable to solve it. The participants in the second group, on the other hand, were asked the same core question without the primer and, more often than not, were able to find the optimal solution. (You can find the problem here.Try it yourself!)

Another experiment involved analyzing chess players and their eye movements on the board. The participants were again split into two groups, the first group with a suboptimal solution on the board along with an optimal solution and the other with just the optimal solution. The group with the suboptimal solutions continued to look at squares relating to the found solution even though they mentioned they were actively looking for a better one. Their eyes became fixated on the known solution. The Einstellung effect prevented them from viewing the board with an unbiased view even though they were intentionally trying to do so.

This effect suggests that once we gain experience, the more likely we are to fall trap to its influence and fail to evaluate each problem for its merits. We need to ask what the fundamental difference with this problem is and evaluate each new problem without bias. Prevent our brains from going on a mechanized state of autopilot. It’s not a lack of knowledge that leads to these errors but initial ideas formed from previous experience.

In Data Science

Data science is an emerging field where new technologies and methods emerge what seems like every day. But be wary, as trending methods may cloud our judgement. These new tools and ideas can be like shiny objects, where we can’t look away even if it’s not the right tool for our problem, such as the use of tools like Hadoop and NoSQL for the sake of using something trendy or ‘big data’ associated. Rather than leveraging a smaller dataset, we jump into an ocean of unexploited data without adequate reasoning or preparation. Or there’s approaching a problem by blindly throwing the trending algorithm of the day at it. (Recurrent Neural Networks and Random Forests are all the rage these days.) This can lead to solution blindness, especially when intelligence is added too early in the process. Sometimes we form our problem around the solution rather than the other way around.

The Einstellung effect also presents itself in the context of confirmation bias, where we ignore results that don’t support our initial representation of the model or hypothesis. Feature and model selection need to reflect an accurate depiction of the data. Exploratory data analysis is a critical stage in data science that is often overlooked. We need to explore and visualize the data in various ways to dispel preconceived notions before going toward solutions.

“Good is the enemy of great.” – Voltaire

Although a bit of an extreme case, this problem is synonymous with the philosophy of JK Simmon’s character in the recent movie Whiplash: “There are no two words in the English language more harmful than ‘good job.'” One becomes content with local maxima rather than the absolute maximum.

hero_Whiplash-2014-1

(Image source: http://www.rogerebert.com/reviews/whiplash-2014)

Solutions

Our brains are sabotaging our ability to come up with new ideas! What can we do about it? Break the pattern.

Distraction

Usually when we think of geniuses, they are the people with a large working memory. They are able to process more at a single point in time. However the working memory, the prefrontal cortex, can block other memories from creating a connection, which consequently prevents creative thinking. A well-known creative process looks something like this:

  1. Gather as much information as possible
  2. Come up with ideas – they won’t be good
  3. Forget about the project and think about or do other things.

The third point is key in coming up with novel solutions and bypassing the Einstellung effect. Taking your mind off the task at hand for a while effectively activates the cerebral cortex and gets you out of the working memory to explore new ideas and connections.

Interleaving

Similar to distraction, interleaving is the technique by which one switches between ongoing tasks to improve memory, retention, and learning. It allows a topic to percolate in your mind and extract the general rules. This is not to be confused with multitasking. It could similarly result in a loss of productivity since switching between projects and modes of thinking can be time consuming. But the added benefit of jumping in and out of a problem can greatly outweigh the time required, if it leads to a better solution. Being flexible and allowing yourself to explore paths that don’t necessarily look promising from the start are great ways to allow your mind to discover new dimensions of a problem.

Collaboration

Collaboration, getting different perspectives, is a great method to break out of a rut. An approach that I like is to have multiple people work on an initial concept separately then convene with their findings and explore each other’s unbiased ideas. If a solution is presented too early, it can cause the others to suffer from the Einstellung effect.

The field of data science lacks meaningful collaboration tools. Data science encompasses a large domain of knowledge and many times requires more than one perspective. There are competitions like Kaggle where people can work together on a project, but a meaningful collaboration tool would not only allow data scientists to work with each other on a dataset but track decisions made in the process. Visualization redesigns for example could greatly benefit from this. Edward Tufte’s redesign of the challenger data effectively shows the desired result in hindsight. But his knowledge of the outcome rather than the decisions made in the process leads to an unfair critique. Most of the data is left out to highlight the major data point that caused the disaster.

In a production environment sometimes good enough really is good enough. It may not be worth the extra effort to get the best solution. It may not even be possible with the current technology. Marginal benefits may not be worth the time it takes to reach a better solution. The key is in knowing the tradeoffs and when to explore. Recurring problems are the best candidate for exploring if there is a better solution, when it could be just around the corner. 

A Cognitive Network

At Exaptive, one of the things we are striving to facilitate is a better method for discovering novel innovations around data. We want to eradicate the Einstellung effect in our field, and eliminate any associate efficiency loss to boot. (Hey, it’s good to have lofty goals.) We believe something along the lines of a suggestion engine is what data practitioners of all kinds need.  Except, in addition to suggesting new approaches, the right suggestion engine would reveal the potential collaborators who designed those approaches. What we like to call a cognitive network – a concept that deserves a post of its own – allows people to explore data in various ways with a diverse set of collaborators and suggests different ways to think about a problem.

At its core, a cognitive network is focused on connections, connections that wouldn’t be made if the Einstellung effect has anything to do with it. Connections are what allow us to know when something fits for a particular application, where to apply a technique, or to translate a concept to another area or field of study. They are the glue that hold together pieces of information by use and meaning. The connections then are crucial to innovation, and missing one is detrimental.

We should set aside some time to determine if we are settling for a known, good enough solution or we are evaluating the problem with clear eyes and see all solutions. At the end of the day, we may still not consider every solution. However, being mindful of the Einstellung effect and open to new approaches even if an apparent solution has presented itself will aid in reaching those solutions just outside our conventional way of thinking and lead to innovations.

Sources

http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0075796
http://dspace.brunel.ac.uk/bitstream/2438/2276/1/Einstellung-Cognition.pdf
read more