MxMIndia

Tag: AI

  • … from the 2023 Artificial Index report just published by the Stanford Institute for Human-Centered Artificial Intelligence (HAI)

    Top 10 Takeaways on AI…

     

     

    By Our Staff

     

    Every year, the Stanford Institute for Human-Centered Artificial Intelligence (HAI) publishes a report studying trends in artficial intelligence.

     

    The 2023 AI Index has just been released and as it notes, the technology “has surpassed many benchmarks, leading researchers to reevaluate some of the very ways in which it should be tested and forcing the broader public to think more critically of its associated ethical challenges.”

     

    Here’s a little about the report: “The AI Index, led by an independent and interdisciplinary group of AI leaders from across academia and industry, is one of the most comprehensive reports on the impact and progress of AI. The AI Index tracks and evaluates AI progress through a wide range of perspectives, looking at trends in research and development, technical performance, ethics, economics, policy, public opinion, and education. The report helps to ground the AI conversation in data, enabling decision-makers to take meaningful action to advance AI in responsible and ethical ways.”

     

    The AI Index has published a list of 10 takeaways which we believe are must-reads and hence are publishing as is.

     

    Here goes:

     

    1. Industry races ahead of academia. Until 2014, most significant machine learning models were released by academia. Since then, industry has taken over. In 2022, there were 32 significant industry-produced machine learning models compared to just three produced by academia. Building state-of-the-art AI systems increasingly requires large amounts of data, computer power, and money—resources that industry actors inherently possess in greater amounts compared to nonprofits and academia.

     

    2. Performance saturation on traditional benchmarks. AI continued to post state-of-the-art results, but year-over-year improvement on many benchmarks continues to be marginal. Moreover, the speed at which benchmark saturation is being reached is increasing. However, new, more comprehensive benchmarking suites such as BIG-bench and HELM are being released.

     

    3. AI is both helping and harming the environment. New research suggests that AI systems can have serious environmental impacts. According to Luccioni et al., 2022, BLOOM’s training run emitted 25 times more carbon than a single air traveler on a one-way trip from New York to San Francisco. Still, new reinforcement learning models like BCOOLER show that AI systems can be used to optimize energy usage.

     

    4. The world’s best new scientist … AI? AI models are starting to rapidly accelerate scientific progress and in 2022 were used to aid hydrogen fusion, improve the efficiency of matrix manipulation, and generate new antibodies.

     

    5. The number of incidents concerning the misuse of AI is rapidly rising. According to the AIAAIC database, which tracks incidents related to the ethical misuse of AI, the number of AI incidents and controversies has increased 26 times since 2012. Some notable incidents in 2022 included a deepfake video of Ukrainian President Volodymyr Zelenskyy surrendering and U.S. prisons using call-monitoring technology on their inmates. This growth is evidence of both greater use of AI technologies and awareness of misuse possibilities.

     

    6. The demand for AI-related professional skills is increasing across virtually every American industrial sector. Across every sector in the United States for which there is data (with the exception of agriculture, forestry, fishing, and hunting), the number of AI-related job postings has increased on average from 1.7% in 2021 to 1.9% in 2022. Employers in the United States are increasingly looking for workers with AI-related skills.

     

    7. For the first time in the last decade, year-over-year private investment in AI decreased. Global AI private investment was $91.9 billion in 2022, which represented a 26.7% decrease since 2021. The total number of AI-related funding events as well as the number of newly funded AI companies likewise decreased. Still, during the last decade as a whole, AI investment has significantly increased. In 2022 the amount of private investment in AI was 18 times greater than it was in 2013.

     

    8. While the proportion of companies adopting AI has plateaued, the companies that have adopted AI continue to pull ahead. The proportion of companies adopting AI in 2022 has more than doubled since 2017, though it has plateaued in recent years between 50% and 60%, according to the results of McKinsey’s annual research survey. Organizations that have adopted AI report realizing meaningful cost decreases and revenue increases.

     

    9. Policymaker interest in AI is on the rise. An AI Index analysis of the legislative records of 127 countries shows that the number of bills containing “artificial intelligence” that were passed into law grew from just 1 in 2016 to 37 in 2022. An analysis of the parliamentary records on AI in 81 countries likewise shows that mentions of AI in global legislative proceedings have increased nearly 6.5 times since 2016.

     

    10. Chinese citizens are among those who feel the most positively about AI products and services. Americans … not so much. In a 2022 IPSOS survey, 78% of Chinese respondents (the highest proportion of surveyed countries) agreed with the statement that products and services using AI have more benefits than drawbacks. After Chinese respondents, those from Saudi Arabia (76%) and India (71%) felt the most positive about AI products. Only 35% of sampled Americans (among the lowest of surveyed countries) agreed that products and services using AI had more benefits than drawbacks.

     

  • The humanness of artificial intelligence intrigues me and I for one have never been afraid of it, writes Prabhakar Mundkur

    Chatting with ChatGPT

    Photo : Tara Winstead on pexels.com

     

     

     

    Prabhakar MundkurIf you are an artificial intelligence fan like me, you have no doubt watched all the seasons of Westworld.  Or you might have been an avid watcher of Stanley Kubricks 2001 Space Odessey and HAL’s famous words from that movie when he says: ‘I am putting myself to the fullest possible use, which is all I think that any conscious entity can ever hope to do.’ That was as human as human can get.

     

    When I first heard about ChatGPT, I was intrigued. I had played around with IBM Watson many years ago and even used it to make some revealing business analyses and business decisions.  So what was ChatGPT going to be like?  The humanness of artificial intelligence intrigues me and I for one have never been afraid of it.

     

    Humanity’s biggest threat has always been itself. ~Engerraund Serac in Westworld

    In fact ChatGPT interacts with you in a very human way.  You could have a conversation or you could ask it questions.  What I found was that the interactions are certainly very human, I wouldn’t know the difference.

     

    What is ChatGPT?

    ChatGPT is an open chatbot system released just three months ago by OpenAI, a for-profit research lab.  You can almost ask it any question. And it will go thru swaths of data from the internet to deliver a dialogue with you. ChatGPT, according to its inventors, is still not perfect and it is still ‘learning.’ The biggest challenge for AI researcher to tackle is the Turing Test. You would have heard of that in the movie ‘The Imitation Game’ that portrayed the life of English mathematician and computer scientist Alan Turing. Turing proposed the following test to gauge intelligence. Can a human conversing with a human and with a computer tell which is which?

     

    UBS Analyst Lloyd Walmsley estimated that 100 million users had used ChatGPT in January 2023 in two months after launch what took Instagram two and half years.

     

    What kind of questions can you ask ChatGPT?  Mostly everything from asking it questions in quantum physics to asking it to write a poem.  Here are some of the questions I asked.

     

    PM: What is Schroedinger’s Cat?

    Chat GPT:  Schrödinger’s Cat is a thought experiment in quantum mechanics, proposed by Austrian physicist Erwin Schrödinger in 1935. The experiment describes a scenario in which a cat is placed in a sealed box with a radioactive substance and a poison, such that the radioactive decay of the substance has a 50-50 chance of killing the cat. The idea is to demonstrate the concept of superposition in quantum mechanics, where a particle can exist in multiple states at the same time, and the act of observation collapses the wave function and determines its state. In the case of Schrödinger’s cat, the cat is both alive and dead at the same time until the box is opened and the state is observed.

     

    Or I asked it to write a love poem and this is what I got.

     

    Love is a rose, with petals soft and bright,

    A flame that dances, illuminating the night.

    A treasure to hold, a gift to share,

    A feeling that warms, a bond that’s rare.

     

    It’s the twinkle in your eye, the skip of your heart,

    The laughter that echoes, when we’re worlds apart.

    It’s the comfort you bring, the peace you bring to my soul,

    The place I call home, the place I call home.

     

    With you, I am whole, I am free, I am me,

    Together we soar, through the highs and the lows.

    And though the winds may howl, and the skies may turn gray,

    Our love will endure, with you, come what may.

     

    So here’s to the laughter, the tears and the joy,

    To a love that is true, a bond we’ll enjoy.

    With you, my dear, my heart overflows,

    With love and with life, with love that glows.

     

    Interesting isn’t it? Chatbots are based on Natural Language Processing or NLP. Chatbots are being used for internal business communication, enhancing customer service and to boost online commerce.

     

    What is the future of AI?  I think so far all of what we thought was science fiction has pretty much turned out to be reality.  I wouldn’t be surprised if our future world was a lot like Westworld.

     

    Prabhakar Mundkur is a veteran adperson, a prolific writer and musician. He writes for MxMIndia on and off. His views are personal

     

  • Deep Learning will emerge as a valuable tool in increasing marketing efficiency and effectiveness, writes Ashoke Agarrwal

    Marketing Analytics, Rich Data and Deep Learning

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalMarketing analytics is as old as marketing. Simple arithmetic and the magic of ratios drove marketing analytics in the early days. For example, the rug shop owner in the bazaars of Istanbul would estimate his annual sales based on his year-to-date sales as a ratio of his last year’s sales. Or he would estimate price elasticity by running an experiment for a day or two and analysing the data again using simple arithmetic.

     

    Over the decades, as marketing evolved as both art and science, the depth and availability of data increased, and so did the sophistication of marketing analytics.

     

    Marketing mix modelling using multivariate analysis became a vital activity in the marketing departments of large companies. The data fed to the analytics was sales analysis by geographies, advertising spends, pricing and SKU spreads, and measures of brand lift – awareness and consideration across the company’s brands and competition. Some of the data was first-party data – collected and owned by the company. Further, second-party data – data provided by syndicated research studies like retail and advertising audits – became increasingly important over the years.

     

    The statistical tools’ sophistication increased, including multivariate analysis tools like Principal Component Analysis, Multivariate Analysis of Variance, and Hierarchical Cluster Analysis.

     

    About two decades ago, the age of Big Data, Smartphones and Social Media dawned. And as the next decade sees the emergence of the age of AI, a new dimension to marketing analytics has begun to come into view.

     

    Machine Learning, particularly Deep Learning, is different from statistical analysis.

     

    A simple explanation of the difference is that statistical analysis gives a more precise inference about the relationship between variables, while Deep Learning is more focused on making accurate predictions.

     

    Currently, the debate on using Deep Learning in Marketing Analytics is raging in academic circles.

     

    The October 2019 issue of Sloan Management Review published one such paper – “Is Deep Learning a Game Changer for Marketing Analytics?” by Glen Urban, Artem Timoshenko, Paramveer Dhillon, and John R. Hauser.

     

    Urban et al. studied data on credit card choices provided by NerdWallet.com. The data set was for 260,000 individuals across demographic factors like age, gender, household income, and cards owned. Zip code etc. The data set also included 132 attributes for cards offered (APP interest, reward points – miles, cash etc. and card fees – annual, transfer etc.). The study used three models to analyze the data:

    :: Linear regression of choice as a function of user demographics and card attributes

    :: The second model was a simple deep-learning model

    :: A third model used deep learning but added a step of consideration to the final purchase.

     

    The study found that the difference in predictive accuracy between the three models was insignificant – 70.5% for linear regression, 71.7% and 73.0% for the two Deep Learning models.

     

    Deep Learning is expensive to conduct in terms of the expertise required and the processing needs, including computer power. Urban et al. concluded that statistical analysis would be more cost-efficient when the data set is fully structured. They hypothesized that Deep Learning would be more efficient at analyzing “rich” databases, including user-generated content like Amazon reviews, Instagram posts, Facebook posts and comments.

     

    A study by Liu, Daria and Mizik supports the above hypothesis. The July/ August 2020 issue of Marketing Science reports on the study under the title “Visual Listening: Extracting Brand Image Portrayed on Social Media”.

     

    Liu et al. used a multi-image deep convolutional neural network model – a form of Deep Learning- to predict the presence of perceptual brand attributes in the images consumers post online for 56 brands in the apparel and beverages categories. The study checked the model’s predictions against those made by human judges and found a good fit. The model used by the study is branded as the BrandImageNet and is of use to brand owners for automatically monitoring their brand’s portrayal on social media in real-time and thus better understanding consumer brand perceptions and attitudes towards their and competitors’ brands.

     

    Decades ago, Ogilvy launched the Magic Lantern, which used factor analysis to create a highly appreciated compendium of dos and don’ts for advertising in a particular category. The Magic Lantern used multivariate analysis tools like Component Factor analysis to factorize a brand’s advertising and relate the factors to its market success. It is quite likely that today the Magic Lantern team has moved on to include social media imagery besides advertising imagery along with Deep Learning methods.

     

    Deep Learning is a valuable tool in analysing other aspects of user-generated content, as Timoshenko and Hauser reported in their paper – “Identifying Customer Needs from User-Generated Content”, published in the Jan/ Feb 2019 issue of Marketing Science. The study worked on an extensive data set of 115,099 oral‐care reviews on Amazon in the US, spanning the period from 1996 to 2014 and randomly sampled 12,000 sentences split into an initial set of 8,000 sentences and a second set of 4,000 sentences. The study then used a convolutional neural network to filter non-informative and repetitive content. The study compared user needs identified through Deep Learning analysis of User Generated Content (UGC) with needs identified by professional researchers working on industry-standard experiential interviews. In summary, UGC identifies the vast majority of customer needs (97%), opportunities for product improvement (92%), and hidden opportunities (92%). In addition, the UGC-only method identified seven hidden opportunities, while the interview‐only identified two. As user-generated content explodes, Deep Learning methods are proving to be very useful in using this expanding treasure trove to increase marketing efficiency and effectiveness.

     

    And as the Internet of Things (IoT) develops along with the age of AI, Deep Learning will play a more significant part in product design. A paper titled “Unsupervised Learning for Product Use Activity Recognition: An Exploratory Study of a “Chatty Device” by Nemitari, Khanesar, Burnap and Branson, published in the journal Sensors offers a fascinating insight into this area.

     

    In conclusion, advanced statistical analysis will continue to be more cost-efficient and effective compared to Deep Learning regarding structured data analysis. However, in a world where “rich data” – unstructured multi-media user-generated content on brands and products is exploding, Deep Learning will emerge as a valuable tool in increasing marketing efficiency and effectiveness. Further, deep learning techniques will be needed as IoT matures to effectively use the continuous chatter of embedded sensors.

     

  • Tomorrow's marketing communication agencies could then very well be AI specialists, writes Ashoke Agarrwal

    AI, B2I, CI & Advertising

     

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalAdvertising sits at the interface between marketing and media.

     

    Therefore, the impact of technological change in the media world has had a lasting effect on advertising. Advertising’s first phase of evolution was from being a press-driven cognitive medium to the emotive resonance of the radio age. Then, in the television age, the emergence of video changed the very grammar of advertising. And now, in the Internet and social media era, advertising is trying to come to terms with a shift from being an intrusive form of mass persuasion to learning to be interactive and conversational.

     

    Historically, technological changes in spheres other than media have had a peripheral effect on the business of advertising. For example, computer technology has improved studio, planning and operations productivity.

     

    A new era of technological disruption is approaching with the gathering emergence of AI in its various avatars. But what will the effect of AI be on the business of advertising? Will the impact be peripheral, or will it affect the core? Two alternative scenarios emerge.

     

    Like the IT age, the AI age may only affect the productivity of advertising agencies. For example, the AI age could lead to a more efficient and faster path from idea to campaign production. Creative departments could use AI-driven CGI to create photographs and videos using avatar-licensing arrangements with celebrities, influencers, and models. Strategic and media planning could use Deep Learning engines that probe research databases and Big Data to deliver more effective plans. Operations could be more streamlined with meeting memos and day-to-day communications handled by bots. The lead in productive efficiency and effectiveness that the AI age brings to the advertising business could be as high or even higher than the IT age.

     

    The second scenario is when AI disrupts the very core of the advertising business. Imagine a situation where due to advances in AI, advertising as a business, if it was to continue to exist, has to sit between marketing and the individual and not as it currently does between marketing and media.

     

    Marketing in the AI age could morph into a discipline which truly owns the consumer relationship. Today companies act in the world of mass marketing. So much of a company’s marketing, sales and advertising budgets are wasted on addressing consumers who will never buy their products and brands. Tomorrow marketing could shift to being the art and science of marketing the brand to an individual, one individual at a time. Let’s call it B2I marketing. A B2I brand will focus on owning and nurturing the brand’s relationship with a specific individual, individual by individual.

     

    A B2I brand’s product development, distribution, marketing and marketing communication budget will be an accretion of the resources required to build and nurture the relationship with a specific individual, individual by individual.

     

    The age of B2I marketing will dawn when AI leverages a slew of other technologies. Robotics-assisted flexible manufacturing technologies will enable the customization of products. High bandwidth, low latency mobile and IoT networks combined with real-time Big Data analytics will drive true customization of services. In addition, the maturing of delivery drone technologies will facilitate D2C distribution. Finally, Deep Learning engines will sit atop the entire ecosystem to build ROI across the system.

     

    The brand will become, in essence, an AI entity in touch with individual customers. And marketing will shift to the next generation of the Service-Dominant-Logic (SDL) paradigm as outlined in my MxM India column dated 27th October 2022.

     

    The AI brand-side revolution in marketing will also have a consumer-side AI facet.

     

    As AI scales over the coming decade or two, it will develop as a “consumer appliance”, which I call Concierge Intelligence (CI). I have written about CI in my MxMIndia post on 6th January 2002 titled “The Coming Post-Digital Age.”

     

    An individual’s CI will communicate with the brand’s AI in two-way, always-on, low latency, Big Data cognisant communication. The objective will be to maximize the individual’s satisfaction levels with the brand while driving the brand’s ROI.

     

    The question now is if, in the AI age, marketing morphs into B2I marketing, what will become of the business of advertising?

     

    If it is to exist in the age of B2I, advertising will become the art and science of always-on, customised two-way conversation between two sets of AI engines- the brand-side AI and the individual-side AI (CI).

     

    It stands to reason that the business of advertising agencies will then become the business of creating proprietary AI designed to deliver the most effective communication between a brand’s AI and an individual’s CI. Brands would go to external agencies to develop this AI because of the same reasons they prefer external advertising agencies today over in-house cells – specialized expertise honed over multiple brands.

     

    The dawning of the digital and social media age allows agencies to develop the planning and creative chops to deliver effective two-way one-to-one conversations with consumers. But, alas, most traditional agencies are frittering away the opportunity by delivering digital and social media campaigns that follow the time-worn principles of aiming one-way campaigns at an amorphous mass of consumers.

     

    A few tech-driven marketing communication agencies are beginning to hone the technology and creative nous that will enable them to deliver the AI and two-way conversational advertising of tomorrow.

     

    To sum up, the age of AI in one scenario offers substantial productivity gains to both creative and media agencies. However, in the other scenario, the age of AI could make creative and media agencies obsolete.

     

    Under this scenario, marketing communication will morph into a specialised and customised AI engine that drives brand-building conversation between the brand-side AI and the consumer-side AI (CI).

     

    Tomorrow’s marketing communication agencies could then very well be AI specialists. Specialists who build and operate proprietary AI customised to a brand’s AI ecosystem to interact with various types and levels of individual AI (CIs). To nurture and develop brand-to-individual relationships.

     

  • To appeal for language equality on the Internet

    Reverie Language Technologies launches campaign

    By Our Staff

     

    Reverie Language Technologies, a language technology service start-up, has launched a video campaign to raise awareness about India’s digital language divide. Reverie is bridging this gap with its state-of-the-art technology, powered by AI and ML, by providing all 22 official Indian languages with a presence on the Internet.

     

    Said Vivekananda Pani, Co-founder and Chief Technology Officer (CTO) at Reverie Language Technologies: “The video campaign is our humble effort to bring out that while the growth of the Indian Internet rides on our Indian-language literate digital citizens, the kind of Internet they deserve is a far cry. If we view the larger picture, the citizens are either categorized as browsers or ones that depend on OTP or QR verification, depriving them of the seamless Internet that English-literate citizens experience. Despite the massive strides India has made in the digital world, our native language literate citizens are still struggling to bridge the digital language divide and reap the benefits of the Internet and all it has to offer. Significant changes will not occur if languages on the Internet are not implemented through India-owned standards for our native languages. Through our campaign, we hope to build an equitable Internet for India.”

     

  • It will create a different species of human beings way beyond the current divide driven by economic and social power, writes Ashoke Agarrwal

    Homo Proxies: Beyond Income Inequality & The Digital Divide

     

     

    By Ashoke Agarrwal

     

    Ashoke Agarrwal“As for living, our servants will do that for us.”

    From the play Axel by Auguste Villiers de I’Isle-Adam. Also used by WB Yeats as an epigraph in The Secret Rose.

    To my mind, the invention of money is at par with the control of fire as a seminal development of human society. Capital produced the class system, which is the bedrock of modern human society’s economic, political and cultural structure.

    Many who ponder humanity’s future see the emergence of Artificial Intelligence (AI) as a development that will alter the core structure of human society.

    AI’s progress over the decades has been stop-start. For decades it has been the saga of a promise fulfilled more in science fiction than reality.

    Quite often, it has been a cliche with wannabe setup trying to pass off data analytics and second-order model-building as AI.

    However, over the past few years, the exploits of Google, Deep Mind (a subsidiary of Alphabet, Google’s parent company) and OpenAI have once again brought the promise and perils of AI front and centre in the popular imagination.

    In June 2022, Blake Lemoine jolted the world by claiming that Google AI engine LaMDA (Language Model for Dialogue Application) had turned sentient. The powers that be at Google denied the claim and sacked Mr Lemoine. Was Google upset that Lemoine pre-empted the announcement of what many would think is a seminal milestone in the development of AI? Or was Google upset by the revelation of a secret it would want to, for myriad reasons, keep from the world? Or was it simply that Mr Lemoine’s claim was hyperbolic and premature?

    Whatever the case, the media attention that Mr Lemoine’s claim got is symptomatic of the widespread realisation, conscious and sub-conscious, that AI is much more than just another technological development. On the contrary, it is a recognition of AI’s power to change the very dynamics of human society.

    I have been writing in this column about one aspect of how AI, as it develops, will change an individual’s life. In my January 6, 2022 column, I have written about Concierge Intelligence (CI). CI will augment the capabilities of an individual to deliver better outcomes for her – at work, in learning and in relationships. It will be the next big thing – a consumer service whose impact will be an order of magnitude higher than, say, the emergence of the personal computer or the smartphone.

    CI will be an AI companion of the individual, assisting her in all her interactions with the world. CI will enable the individual to communicate better, learn more and better, work better and even shop better. It will do so by developing a deep understanding of the individual’s capabilities, biases, needs and desires. CI will combine this depth of knowledge about the individual with near-encyclopedic knowledge and awareness of the world to deliver solutions and assistance at the speed of a computer.

    The overall impact of CI on society will be more or less egalitarian, as is increasingly the case with personal computers and smartphones. As the CI technology matures, most people who cross the poverty and subsistence lines will be able to afford CI.

    However, there will be an aspect of CI that has the potential to further immeasurably the class divide. This divide will go much beyond the divide of being able to afford a better brand of smartphone or PC. It will even go beyond the digital divide that separates people with access to the digital world and those deprived of it.

    The divide that a specialised aspect of CI can produce could be to create an almost different species of humans. Not yet Harari’s Homo Deus (as posited in his book ‘Homo Deus. A Brief History of Tomorrow’) but on the way. An era of Homo Proxies.

    ‘Proxies’ is the name I have given this species-creating aspect of CI. I have borrowed this concept from Jennifer Egan’s latest book, ‘The Candy House’. Egan comes to the idea of Proxies from a different technological development – the ability to download one’s memories – conscious and sub-conscious. In her imagining, Proxies are an escape hatch devised by those wanting to escape the tyranny of this technology.

    In that sense, I have only borrowed the label from Egan. In my imagining, Proxies are a result of CI, and a means for individuals to distort the technology to entrench their power and pelf further.

    Proxies will be a form of super CI that an individual will use to create multiple identities. As much of human society’s endeavours – economic, social, cultural and political – move online, an individual using Proxies will have the means to exist as multiple entities. Proxies will be a turbocharged CI – say a Super CI – that will enable an individual to digitally live and interact as multiple entities that multiply the time and the legal and social presence available to the individual. In that sense, Proxies go beyond the concept of fake identities.

    While this Super CI will be expensive, the inequality that will result from proxies goes beyond the cost aspect of it. Instead, it will be more to do with the individual’s capabilities. For example, proxies-driven multiple identities are valuable and produce more economic and social capital only if the individual is either a knowledge worker or an entrepreneur.

    Imagine a world where a class of individuals will enjoy unlimited “me-time” while their multiple proxies take care of worldly endeavours. It will create a different species of human beings way beyond the current divide driven by economic and social power.

    Dig below the anxiety that the coming age of AI produces among many, and you will find that the possibility of proxies is part of it.

    As the 21st century slips into middle age over the next couple of decades, a new leisure class will likely emerge. And to paraphrase Auguste Villiers, an elite who says, “as for earning fame and money, our proxies will do that for us”.

     

  • Starting a new fortnightly column by advertising and marketing services veteran Ashoke Agarrwal. Here he discusses the concept of Concierge Intelligence, as AI with soul

    The Coming Post-Digital Age

     

     

    Starting a new fortnightly column by advertising and marketing services veteran Ashoke Agarrwal

     

    By Ashoke Agarrwal

     

    Ashoke AgarrwalThe inexorable rise of digital and social media has rocked the world of mass media, marketing, and marketing communication.

    However, I believe the current disruption is only the tip of the iceberg.

    Media, marketing, and marketing communication professionals should prepare for a more profound disruption driven by the rapid and widespread development and adoption of Artificial Intelligence (AI) leading to a Post-Digital Age.

    Studying the possible contours of AI in marketing and marketing communication, I have developed a concept called “Concierge Intelligence” (CI), as outlined later in this article (I had published a blog post on CI back in Feb 2021).

    Over the past few months, scandals have rocked the world of social media and digital advertising, threatening the lynchpin of social media and programmatic advertising – cookie-based tracking and cookie pools – with stringent and widespread regulations.

    The other critical development is a shift in the outlook of start-up capital – there is a clear trend towards favoring start-ups in deep tech areas.

    Both these trends bode well for the accelerated arrival of the Post-Digital Age.

    There is a growing realisation that Facebook, Google, and its kin are critical fuelers of fissiparous tendencies in societies worldwide.

    Social media’s power to divide is a result of algorithms (algos in techspeak) that drive engagement, in the process reinforcing tribal tendencies and conspiracy theories.

    The digital and social media giants are reluctant to change these algos, as they are the engines that drive their primary source of revenue and profits -advertising.

    Change in the outlook of social media, digital media, and e-commerce giants will come when they face emergent competition from the likes of Concierge Intelligence that will usher in a Post-Digital Age.

    The increasing disquiet among marketers and advertisers with social media and digital advertising effectiveness will be at the core of this emergence.

    Many in the marketing community started as enthusiastic advocates of digital marketing. It seemed to hold the promise of better ROIs over the short term and more robust, interactive brand-consumer relationships over the more extended period.

    However, the reality of digital marketing has belied most of these high hopes. Today, digital marketing does not represent interactive access to a more clearly defined target consumer. Instead, it obfuscates behind attribution in terms of “views” and “click-throughs”, numbers that cloud as much as they reveal.

    If most marketers are dissatisfied with digital marketing, the question arises as to why the share of digital in most brands’ marketing budgets grows year on year? The reason for this inexorable growth is, I believe, two-fold.

    First, the rise of digital media is weakening mass media. OTT platforms steal audiences away from linear TV, cinema, and radio. Social media and news aggregation are decimating print newspapers and magazines. It forces big brands to allocate an increasing part of their marketing budgets to digital marketing to reach their audience.

    Secondly, digital marketing is growing at a pace is because of the modularity it affords. Smaller brands with smaller budgets can reach out to smaller target markets, a positive development fostering increased consumer choice. But unfortunately, it also encourages hucksterism and fraud on the flip side of the coin.

    After the Arab Spring of a decade ago, social media was much ballyhooed as the force that would bring about and strengthen egalitarianism and democracy in societies across the world. Instead, in nations after nations, social media today is seen as one of the forces feeding tribalism, extremism, encouraging authoritarianism and threatening anarchy. The rallying cry of the likes of Zuckerberg and Pichai seems to be, “Surrender your data, and I will feed you, for free, the opium of tribal comfort while putting your psyche to power my advertising revenues, a la The Matrix”.

    However, I believe that the page will likely turn again, and social media will get back to being a force for good over the coming decade or two. This transformation will come about under the gathering onslaught of regulators, brands, and public opinion. Under this emergent paradigm, individuals will own the data gathered through their digital footprint.

    I envisage a time when a public utility like service will gather all such data and store it in a digital locker solely owned by the individual, managed by a Data Utility provider. The individual would be free to upload more information into her digital locker, including brand and shopping preferences, recent purchases and intentions, demographic details, and attitudinal batteries. Brands could approach the Data Utility and, based on anonymised information, choose to seek more information about a particular type of individuals – say, individuals who currently own a six-year-old mid-size sedan or those who have expressed an intention to purchase a luxury SUV. The Data Utility would inform the individual of the interest and the fee the brand is willing to pay for their access. The brand will be allowed a permitted level of access with explicit permission from the consumer. Blockchain technology will ensure that a significant part of this payment would go to the consumer (the actual owner of the data) and the rest to the Data Utility provider.

    Central to the above ecosystem will be an AI product I call “Concierge Intelligence” that will mediate for the individual between brands and the Data Utility provider. The individual will own the Concierge Intelligence platform, much like owning a house, a car, or an electronic device.

    The era of Concierge Intelligence will avoid the concerns raised by the age of marketing to bots like Alexa or Siri, posited by some technology forecasters. Instead, Concierge Intelligence will emerge as a tool for individual empowerment instead of yet another money-making and control-enhancing platform for data aggregators, data miners, marketers, or the government. As a result, Concierge Intelligence could be the next big consumer product category of the coming decades, just as the smartphone has been for the past couple of decades.

    The individual will buy his Concierge Intelligence (CI) — a software application -from the market and load it onto all the devices she uses. Then, CI will get to work to learn the consumer’s interests and preferences. The individual will set the scope and depth of this learning.

    CI will be mediate between the world and the individual. First, it will map the individual’s learning patterns and maximize the speed and efficacy of the individual’s learning. It will continuously keep a tab on the individual’s inherent talents and emergent capabilities and connect her with opportunities to put these talents and abilities to use, in the process not just maximizing her earnings but also increasing her sense of self-worth. Finally, it will perceive the individual’s relationship and leisure needs and help her meet them. One of the duties of CI will be as the gatekeeper to the Data Utility service and brands that seek to message and sell to the individual.

    While the CI will have powerful capabilities, it will be under the total command of the individual. She can change its functionalities whenever she wants and even switch it off if she desires, much like today’s smartphones.

    To my mind, CI will, over the next decade, become the most widely prevalent form of AI. I like to think of a CI as AI with soul. A form of augmented intelligence fusing an individual’s psyche, with all its complexity and humanity intact, with AI’s power, speed, and reach.

     

    Ashoke Agarrwal is a veteran advertising professional with around four decades in advertising and marketing services. Agarrwal, a chemical engineer from IIT Mumbai and a postgraduate from IIM Bangalore, is a pro-entrepreneur with past and current ventures in market research, advertising, CGI, e-learning and brand consultancy.