Generative Advertising with Feedback: Bahio Coffee

M&C Saatchi have combined generative design with feedback analysis to try evolve the most engaging ad. The campaign is called Bahio coffe. I think this is an interesting idea and would like to talk about the good, the bad and the ugly. It has been written about here and has a good website to explore progress here. A two minute video overview is on YouTube.

The generative algorithm is given “copy, layout, fonts, colours and images” and this is expressed as a gene-string. There is still considerable human expertise that goes into the basic assets that are input into the Bahio generative system.

The feedback is attention – which appears to be tracked by watching the amount of eyeball engagement viewers have with the poster. Individual posters are scored by the amount of attention they get – with better posters having their genes preserved for future generations.

The algorithm to generate new posters is genetic. Mathematically this is a method for searching a large multi-variate space in a non-exhaustive manner. It works best when we assume the fitness landscape is hill-like – that is, there are smooth ways to improve towards a “best” poster. Though I suspect it has limited usefulness without some sort of similarity measurement between input possibilities. What that means is, how does it determine that a small mutation on the “image” variable results in an image that is different in a similarly small way? Though, for the relatively small number of images the campaign appears to run, this doesn’t appear to be a big problem.

However, in the offline world, we don’t yet have an easy way to target particular demographics. This technique is, without modification, limited to products that have a general appeal to everybody. Some control could be exercised by creative directors on the input materials to the generative system but then the evaluation is still going to be limited.

That doesn’t make this a bad approach at all. M&C Saatchi will learn a lot of useful things from conducting this experiment. So far, this is a form of multivariate testing which is a technique already employed in the web world. It’s great to see experiments with transferring this to the offline world.

Design Demons: The Pragmatist Demon

An earlier post gave an overview of the design demons: Creative, Critic and Pragmatist. This post takes a closer look at the Pragmatist Demon. A designer should develop ability in each of the each of their demons so that the overall team is stronger.

The Pragmatist demon ensures that things gets done. The Pragmatist can be overly economical and un-ambitious in the quest to get things completed. When the Critic Demon is insisting on quality and the Creative demon is insisting on novelty, an overly strong pragmatist can overrule these to complete a solution that is too watered down. The Critic demon is most useful at the beginning of a project (feasibility) and at near the end (deadline crunch). The Pragmatist demon will stifle good ideas from the Creative demon if the Pragmatist is too loud during the concepting phase. The Pragmatist demon's favourite word is: trade-off.

The problem with trade-offs is that the value of a project can be deleteriously compromised if the novelty or quality is watered down.

The underdeveloped Pragmatist demon is unable to set and meet deadlines. The underdeveloped Pragmatist will allow the Creative demon too long to discover the perfect idea and allow the Critic demon to continually nitpick at problems in the design. A person with a weak Pragmatist demon may be full of good ideas and even have some projects started - but little is actually finished.

The strength of the Pragmatist demon can be improved through practice. Set clear constraints (budget, materials, deadlines) for projects and stick to them. Completing work is the life-force of this demon. Any study into process, workflow and project management will permanently strengthen this demon. Writing proposals and problem solving in constrained situations are the Pragmatic demon's gym workout.

The noisy pragmatist will unnecessarily hurry the Creative and Critic demons into doing substandard work. The noisy Pragmatist will discourage the Creative demon by saying the ideas are impractical. By prematurely constraining the Creative demons then concepts might be unnecessary weak. The noisy Pragmatist might overrule the quality decisions of the Critic and this could ruin the polish of the project. However, a noisy pragmatist that gets work out the door is probably the least worst noisy demon because getting stuff done matters most.

A noisy Pragmatist demon can be taught to speak only in turn. Force yourself to use a standard process for projects and do not deviate from the standard process without permission from a mentor. Allow the Creative and Critic demons space to speak before applying "practical" constraints.

A weak Pragmatist demon is best trained through the successful completion of many projects. One way to do this by setting constrained projects (time, budget, other) that must have an output. This will improve the Pragmatist's ability to estimate feasibility going into a project and the constraints will force the Pragmatist to balance priorities in the later stages.

A strong Pragmatist demon is important for a designer to select good projects and complete them on time and in budget. Working to improve the Critic demon will give long term benefit to the designer because completed projects are better than incomplete projects.

Design Demons: The Critic Demon

An earlier post gave an overview of the design demons: Creative, Critic and Pragmatist. This post takes a closer look at the Critic Demon. A designer should also seek to develop ability in each of the each of their demons so that the overall team is stronger.

The Critic Demon is more strongly related with the left side of the brain. It is the analytic thinker that evaluates and judges the ideas flowing from the Creative demon. The Critic demon can be overly picky and will have impossibly high standards. When the Critic demon is rejecting all ideas then perhaps trade-offs should be made in the design. The Critic demon is most suited to the development and refinement stages of the design process. The Critic demon will cripple the Creative demon if the Critic demon has influence during the Concepting phases. The Critic demon's favourite word is: Perfection.

The problem with perfection is that there is never a single solution and design is often a trade off between many competing factors.

The underdeveloped Critic demon will be unable to properly evaluate the ideas of the Creative demon. The underdeveloped Critic will allow poorly resolved and aesthetically unpolished work to progress. A person with a weak critic demon and good execution skills will make a high volume of rough work. They might be successful through volume alone.

The strength of the Critic demon can be improved through education, reflection and critique (see the critique section). Critical analysis and logical thought is the life-force of this demon. Any study into understanding of design theory, history and case studies will permanently strengthen this demon. The act of reviewing and thinking about design work - especially honest criticism confirmed by trusted peers - is the Critic demon's gym workout.

The noisy Critic will distract the Creative demon and may war with the Pragmatist demon during the later stages of the project. The Critic will discourage the Creative demon by saying how each idea of stupid and this will stop the Creative demon from leaping from idea to idea. The pragmatist will want to finish a project but the Critic demon will insist that it is completed properly before it can be released - even if this means expending more resources than allowed for the project. This can delay the delivery of a project.

A noisy Critic demon can be taught to speak only in turn. Use good conceptualizing procedures where the Creative is free to talk for a set period of time before the Critic can judge the ideas. Standard brainstorming technique is to simply record all ideas without judgment or editing for a set period of time and only then allow for the Critic to speak. Focusing on the resources allowed for a project (esp. the deadline) gives the Pragmatist demon enough power to overcome the Critic. A beginner design can delegate the critic function to a trusted and more experienced peer. This should eventually train the critic to influence at the most useful times.

A strong Critic demon is important for a designer to produce professionally polished works that are executed well. Working to improve the Critic demon will give long term benefit to the designer.

Say Hello to Your Design Demons

Based upon more than a decade in graphic design education I have a working theory called “Design demons” to explain the psychology behind the design process. In a previous post I looked at how design schools grades matched particular designers. Design demons more specifically looks at how the personality of the designer relates to the design process and therefore acts as a basis for giving individualised advice for designers to develop themselves.

There are three primary demons in the designer’s mind that each battle for attention. These are the Creative, the Critic and the Pragmatist. The label demon was chosen because these are powerful forces that can both help and overwhelm. Each demon has a different level of loudness, ability and affinity for a stage of the design process.

The Creative demon is the divergent thinker. Full of enthusiasm, curiosity and ideas this demon always has a positive attitude: “Wouldn’t it be cool if .... “ The Creative demon is the wellspring of new ideas. The Creative demon is at their best during the early “Concepting” stages of the design process though the Creative demon can have a role to play in later stages for problem solving. However, if the Creative demon is always coming up with new ideas then the project will neither be polished nor finished on time.

The Critic demon evaluates ideas and judges them. A strong Critic demon enables the designer to choose their best concepts and refine them further. The Critic demon decides when an idea is good enough to pursue further. Therefore the Critic demon relates to the Development and Refinement stages of the design process. An overly negative Critic demon will trap a designer into constantly going back to the drawing board. A poorly developed critic is unable to make decisions.

The Pragmatist demon is the taskmaster. This demon watches the clock, the budget, the ability of the designer and other available resources. The demon tells the Critic demon to stop being so picky and to move on because the deadline is looming. A weak Pragmatist demon will miss milestones. An overly safe Pragmatist demon will only allow easy to produce, safe ideas to progress. The Pragmatist is most useful in the feasibility and production stages of the design process.

Developing ability in each demon is part of a good design education. For beginning designers they will learn to listen to each demon in turn as they progress through the design process. More experienced designers can allow all the demons to speak at once.

Example of Design Demons 1: Often highly creative people struggle in graphic design programs because their Critic demon is too weak to rank concepts and the Pragmatist demon is not strong enough to keep an eye on the clock. Right up to the last minute their loud Creative demon will be feeding them with crazy off-the-wall and impractical ideas. These people can become successful designers by reigning in the Creative demon and allowing the other demons room to develop.

Example of Design Demons 2: Sometimes a designer can get stuck in a loop where the Creative demon cannot come up with anything to satisfy the Critic demon. This is either a sign that the Critic demon is too loud and the Pragmatist demon needs to make the Critic demon choose something that is “good enough”. Or, it could be a sign that the designer needs additional help in developing ability in the Creative demon.

My hope is that thinking in terms of Design Demons helps educating designers and gives a framework for designers to self-evaluate their strengths.

Future Design Software: Streamlining Critique

Critique is important for designers to judge the appropriateness of their designs and to progress in their craft. Unfortunately for the working designer the pressures of budget and time and the difficulty of finding people to critique work mean that critique rarely happens. Future design software could change that.

Ideally designers should get critique from designer peers, clients and the target audience. Each brings a different perspective to the work that is important for different reasons. Client critique is usually built into the design process because it is the easiest to do – there is often a single client representative who critiques before they signoff work.

Critique from peer designers is more difficult to come by. There are design communities like Behance and DeviantArt that will critique but those communities are too public for pre-release design and the level of critique is often not high – despite being enthusiastic. Design critique should come from experienced people whose opinions you trust. These people are probably already in your social network (like Facebook).

Research I co-supervised for Kerrin Meek’s Honours work looked at how social media could be used for designer critique. While in the early stages, many good ideas were explored. The central idea is that by extending critique notifications into the activity stream of others and making those critiques easy to accomplish, peer designer critique might become more successful.

Facebook already allows for posting images and collecting comments. This can functionality can be extended by adding semantic differentials, alternative image voting, and critiques where hotspots can be highlighted for comment. This can be done via a third-part website that integrates tightly into the Facebook experience using the existing Facebook API.

Target audience critique is a more difficult to organize – especially with the speed demanded by many design projects. Market research companies already have large databases of willing participants sorted by demographics that are used to working online. The missing piece of future design software is a website where designers can place their work for critique in standard forms (comments, votes, surveys, questionnaire, semantic differentials), assign a budget, and have that targeted towards a particular demographic. If the process was thus streamlined through future design software then costs could come down and turn-around times improved. As costs and time decrease then the feasibility of adding user critique to a project increases.

Future design software has the potential to revolutionize designer peer critique and make target audience critique more affordable both in terms of time and money. Would you consider expanding critique in your projects?

(This is another article in the Future Design Software series.)

Beauty is not in the individual eye of the beholder

The phrase “beauty is in the eye of the beholder” (BIITEOTB) is often misused to justify poor design – situations where somebody tries to justify poor taste by judging according to their individual preference. The actual meaning of the phrase goes further than individual taste and shared understandings of aesthetics.

One way of interpreting the phrase BIITEOTB is quite simply that an object is not innately beautiful in of itself – it is that perception of that object by a viewer that makes it beautiful or not. In a similar vein Roland Barthes proclaimed that the author is dead meaning that the reader/viewer decides on the meaning and by extension makes aesthetic judgments of beauty. The creator of an object does not make imbue an object with beauty but the creator can make an object that is likely to be perceived as beautiful.

Another way of looking at BIITEOTB is that there is individual judgment involved. Humans are not actually as different as we might suppose because many of our aesthetic experiences are very similar to other humans. Because of it is useful to divide the eye into three aesthetic judgments. These are universal aesthetics, cultural aesthetics and individual aesthetics.

Universal aesthetics are generally shared by all other human beings (see an Absolutist Theory of Beauty PDF). For example: humans are commonly drawn to symmetry and order. There is fMRI research that scanned the brains of people who looked at images and ranked them for beauty. The images with the highest beauty rankings were the ones that cause the least brain activity. This suggests that the roots of universal aesthetics are in things that are “easy on the eye.” Interestingly the Chinese word for ugly is难看(pinyin: nankan) which literally translates as “difficult to see”. Evolutionary research suggests that our love of aesthetics is rooted in judging healthy partners to create strong offspring.

Cultural aesthetics are aesthetic tastes that are shared amongst sub-sections of the human population. It’s unclear whether these are nature or nurture – that is in the DNA or learned. More likely these are learned preferences and things that a person likes because they have become used to them and have strong emotional associations with them. Cultural aesthetics encompasses things from modern tribes such as music genres or strong brands. Most target audience research in graphic design tries to uncover the cultural aesthetics of our audience.

Individual aesthetics are where individual taste comes into the equation. The effect of this is probably much smaller in normally well adjusted humans than the effect of universal and cultural aesthetics. One situation where individual aesthetics becomes powerful is in the faces of family. Repeated viewings of family faces with strong emotional ties creates a familiarity that resonates deeply within an individual and overrides the universal aesthetic. Again there is a survival evolutionary basis for favoring family over others.

Graphic Designers will study universal aesthetics and master these. Much of the teaching in typography, design principles, grid systems and colour theory are based on universal aesthetics. Further education of the designer has them explore cultural aesthetics so that they can better communicate to their target audiences. Graphic designers usually leave exploration of individual aesthetics to the fine artists, the fashion designers, the illustrators and photographers.

So next time somebody says “beauty is in the eye of the beholder” remember that eye has aesthetic judgments that are universal, cultural and individual.

Who should critique your work: Why designer critique matters

An answer to a question on LinkedIn: Are other designers really the best critics of your work? The continuance of the discussion might be worth reading.

You ideally should have designer, art director, target audience and client feedback.

Client feedback is important because they hopefully understand their target audience and functional requirements better than the designer. Ultimately the client needs to be happy with signing the paycheck so their acceptance is important to the politics of the process. Though I keep reminding clients that they should try judge work from the perspective of their audience.

Target audience feedback is great when you get it. Clients are often open to some form of testing - and if you keep it lightweight it can be quite cheap. The thing is that target audience are often limited in the insights that they can give. They usually cannot see past an incremental improvement so take what they say with a grain of salt. Make proposals to users, don't ask them what they want because they can't tell you their latent needs. Cool design hits latent needs.

Art directors are great for judging the feel of a piece. Though in my small country often art director and designer are the same person.

Other designer feedback is critical. It's nearly impossible to critique your own work (though I'm actively researching techniques to make self-critique more effective). The arty side of designers might be fickle but the underlying design aesthetic is not as subjective as people think. There are underlying aesthetic principles that are quite universal and some that are culturally situated. Good designers can critique work because they are trained and have developed connoisseurship. They are not just somebody who thinks that just because "beauty is in the eye of the beholder" that somehow qualifies them as having a useful opinion just because they feel "creative". Also, the graphic design eye is very different to that of other types of visual creative.

Much of the formalist side of critique will encourage adherence to grids and greater coherency between things on the page in order to increase unity. If a piece is too unified/simplistic then the critique will recommend a "breaking of the rules" to create interest. That's the basis of most visual critiques (yes, I am researching this). E.g. On a website with many colours and type treaments, obvious critique is to choose a colour scheme and to systematise the type treatments because that increases unity. Counter e.g. On a website that is black and white, a critique might suggest to add a highlight colour in order to create interest.

To bring it back to the question: Designers are one of the important critiquers of your work but don't forget the others. I don't think there is currently a better way of measuring work where aesthetics is involved - though there are established tests for measuring function.

On a cautionary note: The whole "Design Science" movement tried and failed to objectify aesthetics in the 1960s. They thought that science could start to properly measure aesthetics - luckily we are over that though I do think that the post-modern reaction to design science swung the pundulum too far past humanism into outright mysticism where it concerns creativity. Contemporary techniques like fMRI are given interesting insight into how the brain interprets aesthetics - but fMRI is simply out of reach of most designers.