Tag Archives: system 1

The evolution of insights: practicing what we preach: 6 summaries #IIeX #MRX 

Live note taking at #IIeX in amsterdam. Any errors or bad jokes are my own.

Power of human intelligence in the new era – man and the machine by Simon Edward and Seda Tokcan, (IBM)

  • Our personal lives have blurred, it’s an always on world, a do it yourself mentality prevails
  • Expertise still drives world progress, but what is the role of expertise
  • There are barriers associated with building expertise in the new digital era
  • Even simple analytics are not straightforward 
  • Human cognitive capacity is inadequate compared to what is required in today’s digital world
  • Advances are ushering in a new era of computing, no more punchcards, no more simply programming, now we’re in cognitive systems era
  • To error is human but to really mess things up requires a computer, now computers can learn and build expertise
  • What is so unique about human intelligence, ability to create a novel idea, ability to differentiate between causality and correlation, ability to combine intuitions with intelligence, ability to ask questions
  • The essence of being human is asking questions, not answering questions
  • Technology boosts the expertise of intelligence professionals – enhance, scale and accelerate expertise
  • computer system confirmed 99% of medical diagnosis but added diagnosis precision to 30% of them
  • Think of technology as an enabler, let it cut through the ego and bias of humans

Automation: Robot vs Researcher by Paul Albert (Zappistore) and Tony Costello (RB)

  • WHat used to take 6 months is now being done in hours and TV marketing budgets have gone up
  • Research budgets are continuing to decline for three years in a row
  • In fifteen years, half of Fortune 500 companies have disappeared
  • Data and digital requires more research to fuel profit, Netflix and uber have grown immensely but TASI and blockbuster are dying
  • We need lower cost and more speed but we also need validated methodologies
  • Do you delay until the method os fully validated or launch Asap
  • Business that don’t adopt technology are destined to fail, bravery is need to adopt new approaches
  • Now they can test many more ads for more brands and chose more effective ads

System 1 Driven Brand Insights by CHristian Ohm (Magda) and Karthik Posnanski (BrainJuicer)

  • Mazda has rebounded because of the product line, youngest
  • They moved from lower premium and generic to more premium and distinctive, premium experience not high price
  • Have a strong product perception but a weak brand image perception, most brands don’t
  • Fragmentation leads to a weak brand, in message or tone, sounds like a different brand in different markets
  • Took a co-creation approach, more people than marketing need to understand the brand – call Center, dealer, sales person
  • People knew the brands and could talk about them but there isn’t a lot of emotion but some people just love driving and are passionate about it, they want to deliver on this experience
  • Spirit of Hiroshima – challenger attitude, never give up, we can do it
  • Emotional connection is achieved when care and driver are in perfect harmony
  • Created a brand book to share with everyone
  • Tracking needs to be fast and actionable, cover emotions, simple and engaging, modular and flexible, adapt latest MR thinking, forward focused and predictive, strategic and tactical, more qualitative [excellent advice for research in general]
  • Considered fame, feeling, and fluency for brand growth

The nature of consumer emotion by Aaron Reid

  • Visceral factors theory – Lowenstein, falling asleep at the wheel – extreme deviation from a desired equilibrium point
  • It was a bold man who first ate an oyster – well, maybe a crazy person or simply a very hungry person
  • System 1 ans system 2 interact, it can’t be one or the other
  • The proportion of emotion model combines emotion and reason in a single predictive algorithm, we are more accurate in predictions if we use both
  • You can’t measure racism explicitly, emotion interacts with reason
  • We see eye tracking and emotion tracking of the Budweiser immigration ad, can see attention in the right places and emotion being positive or negative at the right moments
  • Adding implicit facial coding and implicit impact of ads greatly increases ability to predict virality of an ad
  • Need to quantify the emotions from pride, gratitude, and anxiety

Unilever’ innovation in action by Vijay Raj (unilever), @vijayiraj

  • They engaged with startups so they could increase the work with half the cost, half the time and better quality
  • Have worked with 800 startups in recent years – the Shark Tank, piloted 200, recruited 30 for research and the new way of doing business
  • Want to move away from asking to observing, people forget, they give estimates (not because they’re lying)
  • Used google glass technology and advanced video analytics
  • Move from asking to sensing, though people struggle to articulate emotions, FMRI, emotion coding, facial coding, they use facial coding on every ad
  • Why should we ask at all? Asking reveals needs, combine what people search for on google with what people say on social media to replace traditional research
  • Move from studying consumers to building relationships with people
  • The technology enables them to string together a more powerful story
  • Let’s move to “i have the answer what is your question’
  • The pyramid of tomorrow: Input powered by tech, output enabled by tech, outcome delivered by people
  • Make the leap from insights to ideas
  • They pay their vendors bonuses if they do a job well [fabulous idea, will you do this?]

Integrating new data sources to improve the value of your segmentation research by Hilary DeCamp (LRW)

  • Can you buy an ad for a segment?
  • Geolocation, attitudinal profiles, likely voters
  • Need to use machine learning and targeting to buy thousands of direct targeted ads
  • Microsegmentation has its use but you still need to use classic segmentation for higher level needs
  • Alternative lenses for segmentation – demographics are targetable in media, behaviors for usage styles of path to purchase, attitudes for believes about category or self, needs for key buying factors, occasion based for needs that vary by occasion
  • Right now demographics and behavior segmentation are highly used
  • Challenges with segmenting – surveys are too long and phones are too small, we don’t know what we don’t know, self report behavioural data is not very accurate or precise, targeting segments is hard to do in advertising
  • Can profile based on quantative data but people are bad with numbers, qualitative research brings richness and texture, plus can add real world behaviours like actual online activities or models propensities
  • Audiences are identified and you can message them differently by segment
  • The new tools are making classic segmentation more actionable than ever before
Advertisements

Up close and personal with consumers using nonconscious measurement and text analysis #IIeX 

Live note-taking at #IIeX in Atlanta. Any errors or bad jokes are my own.

Chameleon communities: immersive learning takes many forms with Stephen THompons and Kendall Nash

  • Communities are iterative sharing, exchange of ideas, genuine dialogue, relationship building, sense of accountability
  • Chameleons can change colour, to communicate, to be what they need to be; communities should be what we need them to be
  • COntinuous insight communities – reach out to them an any time, on-demand insights
  • Longer term communities 3 to 4 weeks
  • SHort term pop-up communities – bulletin boards sometimes, less than 3 weeks, part of a wider research program 
  • Use for testing, online diaries, advisory Angels, shop alongside, co-creation, feedback, and it’s better if they’re layered
  • Technology accommodates learning 
  • Build an online environment o suit – easy to use, attractive, and engaging tools make research fun
  • Great for discussions of TV shows and what is and isn’t funny
  • Feel licensed to right size them and make the suit your needs, if it’s not perfect then make it right


What nonconscious measurement says about America as a brand by Elissa Moses 

  • America is a brand [I assume you mean USA because America includes Canada, Mexico, and Brazil]
  • When brands erode, they become vulnerable
  • Brands give you shortcuts re expectations and whether something will be a good fit
  • Implicit research was great to study racial prejudices because they either don’t want to tell you, or they’re conflicted or they really just don’t know
  • Brands can change – Disney, apple, VW, BP all used to be high esteem and fell from grace, vulnerability always lurks, there can be a scandal tomorrow
  • Used a device agnostic tool, mobile friendly [Did you hear that MOBILE FRIENDLY! 🙂 ]
  • Calibrated on individual baselines [thus repeated measures, within subjects design]
  • Sweden, USA, MExico, France have high scores on great place to live
  • but if you ask if their country will ever be as great again, then negatives pop up
  • There is huge ambivalence about where the country is headed and that people worry about
  • 50% of Americans say yes to beginning in immigrants [ of course, even if I take longer to answer a question, it could be not that am unsure, but that I want to make sure I truly believe my answer. I know I pause a lot when I answer questions because that’s how introverts do it]
  • Tools is good for busting cliches
  • People in America just aren’t sure about their country any more
  • People don’t believe American standards for justice, upholds the constitution, respects separation of court and state, gives equal to rights to all
  • People DO have pride in America so we can get back on track


Return on customer investment: linking customer insights to revenue growth by Manila Austin

  • Are companies customer-centric? 80% of companies think they are but only 8% of customers think so
  • Returns on Assets is declining and going flat, old models are no longer working 
  • Companies spend 14$ on advertising for every 1$ spend on understanding consumers
  • Most R&D efforts go towards sustaining existing products
  • When customers are more likely to say a company “Gets them” their revenues are more likely to increase in comparison to other similar companies
  • Raising your customer quotient will increase your ROA, a .5 point increase is worth millions in revenue and net income
  • Employees and consumers see things differently, employees thinks their customer experience is far better than consumers
  • Consumers want openness, relevant, loyalty; employees want openness, empathy, to be closer to end users
  • Diagnosed the customer into the organization


Social Insights: The next generation by Rob Key

  • Language is really complicated
  • Rules based solutions are complicated, one wrong word and everything gets messed up
  • Precision – do they match gold standard of humans, 80% of time humans can tell what it means – 3 independent humans [I remember when no one cared about validation 🙂 ]
  • Relevance – does a Boolean query do the trick? Maybe but it’s not nearly enough; words take on different meaning in different domains, small is good for smartphones but not for hotel rooms; faded jeans are good but not faded interiors; every industry has its own lexicon
  • Need precision and relevance and recall to achieve quality
  • People don’t say “I trust this brand” or “I highly recommend this brand” THey say things like “I give this to my baby” or “I’m the hell outta here”
  • Language must be customized to industry
  • Emotions come in many forms which many words [seems like everyone uses plutchik’s wheel of emotion 🙂 ]
  • Can you isolate spam the food from spam the email hell
  • Unify the data with call Center data, survey data, unification f the voice of the customer 
  • Social data is not quantitative and meaningful, mainstreamed into large organizations
  • Clean data does indeed create valid results [as does clean survey data and clean focus group data]

%d bloggers like this: