Breakthrough Machine Learning Study Published in Marketing Science

By Rachael Yeadon and John Mitchell

Across industries, companies are faced with the challenge of how to sift through the massive amount of readily available user-generated content (UGC) to uncover valuable customer insights.  A new study published in Marketing Science describes how to use machine learning to expedite the discovery of customer needs from user-generated content. The details of this approach are published in “Identifying Customer Needs from User-Generated Content” by Artem Timoshenko and John Hauser of the MIT Sloan School. This study is the culmination of the authors’ work over the past several years. Applied Marketing Science (AMS) was instrumental in the development, testing, and refinement of the aforementioned algorithm, and has used the process various times to help clients identify consumer insights.

AMS has applied Timoshenko and Hauser’s approach across a broad spectrum of industry categories, uncovering customer needs in small kitchen appliances, skin and hair-care products, prepared foods, oral care products, drug-device combination products, and even snowplows.

Machine learning, when partnered with professional analysts, can be a game changer for product managers and marketers, leading to better and faster innovation. Key advantages of the method include:

•        User-generated content is virtually free
•        Machine learning can draw on comments from thousands of people
•        Content contains insights that are freely volunteered at moments of truth
•        Machine-based analysis can overcome human bias
•        Ability to identify infrequently mentioned and unique insights

How does this method work? To start, we work with a client to crystalize their research questions and find the right sources of UGC to analyze. In some cases, good content exists on product review sites, social media pages, customer forums, or blogs. In others, it exists in call center data, transcripts of customer interviews from prior studies, or open-ended survey questions. A trained algorithm sifts through the UGC and pulls out the informative content, which is then processed and analyzed by market research professionals. Clients have praised the machine’s ability to uncover “needle in the haystack” insights that are barely or never mentioned in more traditional qualitative research.

Thanks to this emerging advancement in machine learning, clients in almost every industry are able to uncover customer insights faster and cheaper.

Read more about the power of machine learning in the newly published article.