The market for kitchen blenders is highly competitive. Characterized by near constant product innovation, consumers face an overwhelming number of choices, each boasting the latest features designed to make their lives easier in the kitchen.
But, when it comes to blenders, what are consumers’ unmet wants and needs? And, which features do consumers truly care about? Manufacturers that can accurately answer these questions innovate more successfully than those that can’t, allowing them to outperform the competition at the first moment of truth in the store and beyond.
Traditional market research is effective, but it takes significant time and money to do well. When data already exists, machine learning, a technique that mines data for insights, is a fast and inexpensive alternative. It is also as comprehensive and accurate as traditional research methods. Machine learning can be used to analyze data from a variety of sources, including discussion forums, online reviews, call center data, and survey open-ends. Here, we used our breakthrough machine learning approach to mine existing user-generated content (UGC) in the form of blender product reviews on e-commerce websites. Using this approach, we uncovered what’s truly important to blender purchasers.
What We Did
Working with researchers at MIT, AMS used machine learning to identify a full set of customer wants and needs relating to blenders. AMS first identified product reviews to evaluate. Then, we extracted the content and trained the machine learning algorithm to distinguish informative content, which contains wants and needs, from uninformative content. Next, we ran the algorithm. In a matter of minutes, the machine assessed more than eighteen thousand records of data and uncovered 2,000 consumer statements that contained unique consumer insights related to blenders. Trained AMS analysts then reviewed these statements and formulated a comprehensive list of customer wants and needs, quickly and cost-effectively. The research study took less than one week to complete and cost about a third of what traditional qualitative research, such as interviews, ethnographies or focus groups, would cost.
Using our machine learning technique, AMS identified 97 unique consumer wants and needs related to blenders, covering 34 different topic areas. Topics included cleanliness, durability, ease of use, portability, safety, and the terms of warranty. The needs identified were highly detailed and actionable, allowing a blender manufacturer to develop features to address the needs that blender purchasers care about most. For example, the needs detailed exactly the types of foods consumers are looking to pulverize and which types of foods blenders currently on the market struggle to grind up. Our machine-learning approach accomplished all of this at a fraction of the time and cost of traditional research methods.