MxMIndia

Tag: User Generated Content

  • 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.

     

  • It doesn't really matter which industry you choose, every one of them will eventually be a job in the media, writes Paritosh Joshi

    Paritosh Joshi: So you want a job in the Media?

    By Paritosh Joshi

     

    MBA from a leading business school in the American Midwest, two years with a boutique investment bank in Boston and then this young man lands up for a chat about what he needs to do to get a job in the media.

     

    It is still easy to think there is a clear demarcation that sets the media apart from the rest of the world. Aamir, Ashton, Arnab and Aishwarya are in the Media. (They don’t even need surnames to identify them). Media people ‘need no introduction’. Us grunts have nothing worth introducing and thus, don’t need to be introduced.

     

    Or is it so simple?

     

    There were the Media people but they were few and readily identified as such. M J Akbar dazzled us with his insight in columns for a newspaper he edited. Rajat Sharma put people into the dock, quite literally, as he hosted a talk show. Derek O’Brien got all of us furiously scratching our heads even as he quizzed school kids. Madhuri Dixit sent testosterone levels into orbit merely by counting from 1 to 13. And Lalu had to invoke Sridevi’s cheeks in search of a universally comprehensible metaphor for Bihar’s roads.

     

    Then Tim Berners-Lee came along and changed everything, although for years after he thought up hypertext in an obscure corner of CERN, we would scarcely have known it.

     

    By the late 90s, regular blokes discovered that it was possible to find a wider audience for their periodic rants on WWW than they previously could muster around a water cooler or in a cafe. The web log, then portmanteau-ed to weblog and finally truncated to blog was born either in 1995 or 1997 (you can find an interesting history here).

     

    Then blogger came along in 1999, bang in the heady days of the Dotcom Boom and setting up a blog became Luddite-proof. From the very beginning, the blogging community had a wide range of interests and capability. The largest majority would create an account in an idle moment never to visit it ever again. A few would invest time and effort in their posts and endeavour to reach out to an audience with regular, engaging updates. Remember that these were people operating far away from the conventional notion, but what they were doing was indisputably publishing.

     

    Everyman had just stormed Fortress Media.

     

    It began with the written word. Soon enough, authors had found ways of adding pictures to their words. And the web was becoming more clever all the time. It was able to transport not just text but sound and video too. Also, devices to record audio and video had started to shrink in price and size even as they got massively more powerful, thus putting near professional quality sound and image acquisition within reach. Events unfolded at a rapid pace thereafter. Amazon pioneered a lightweight handheld device for reading digital publications. The Kindle was a runaway success and for the first time, books could be self-published by anyone with a good idea and capable penmanship without ever being imprinted onto the dead-tree medium. Soundcloud allowed wannabe speakers, singers and instrumentalists to distribute their art and craft without surrendering themselves to the crafty gnomes of the music industry. Youtube opened doors for every standup comic, ballerina, burlesque queen and cute kitten to show off its talents on glorious Technicolor video.

     

    But wait, we were talking about an investment banker contemplating a career in the media. So what’s with this long riff about what we now refer to, rather condescendingly I might add, as User Generated Content?

     

    Well, it wasn’t just individuals that got inspired to start using the all new powers of WWW to talk to their “Audience”. Businesses of every stripe saw the opportunity too. To be rather more honest, what they saw was consumers – happy and irate, sounding off about their brand experiences in these wide open spaces and were left with little choice but to deal, for better or worse, with what they were getting. Surely we’ve all heard the now almost apocryphal story of Coca Cola’s attempt to take down a fan page on Facebook that spectacularly backfired? To the point where they had to pretty much say ‘Let bygones be bygones and let’s be friends’? (Moral: Don’t clobber, co-opt).

     

    You see what’s happening here. Companies and brands were becoming broadcasters and publishers.

     

    At no time before in the history of our human civilization has communication across every conventional fence and barrier been so easy, inexpensive and by implication pervasive or ubiquitous. And barring the rare exception, individuals and entities find it more productive to be participants in this endless feast of reason and flow of soul than mere mute spectators. There’s even a taxonomy to describe different levels of involvement with media: Paid media are, as the name suggests, those that you have to buy access to. Earned media are where the media voluntarily carry news or content about you. Finally, owned media are, again as evidenced by the name, those that you own and control. Who doesn’t want earned and owned media?

     

    And what was it that we were talking about when we began this ramble? Ah, yes. A job in the media.

     

    I told the young man, he could stop looking. After all, every job- FMCG, Banking, Automobiles, Telecommunication, <insert randomly chosen industry name here> eventually, was going to be a job in the Media.

     

    Paritosh Joshi was until recently CEO, Star CJ. He has been a marketer, a mediaperson and a key officebearer on industry bodies. He is Strategic Advisor, Ormax Media. He can reached via his Twitter handle @paritoshZero