CONSUMER INSIGHTS AS A GAME
The globalization and digitalization of the world have given consumers more information and choices than ever before. At the same time, it has become easier for businesses to collect consumer data from online surveys and other sources. Thus, Data Intelligence has become a key pillar of business strategy.
The objective of Data Intelligence and Analytics is to find valuable business insights. We view Consumer Insights as a game where companies try to uncover as much relevant information as possible about consumers, with the least costs and efforts. The goal of the game is to capture consumer utility functions. These functions are predictive quantitative models of consumer choices, which lie at the heart of our research in Computational Economics and our Decision Games.
We believe that human-driven technology is the key to enhancing human capabilities in Data Intelligence. By leveraging computational and algorithmic power, we create new techniques to make Consumer Insights more powerful and efficient.
AI & MACHINE LEARNING FOR BETTER INSIGHTS
We believe that human-driven technology is the key to enhancing human capabilities in Data Intelligence. We use Artificial Intelligence (AI) and Machine Learning to create new techniques to make Consumer Insights more powerful and efficient.
HD-AI Consumer Analytics
HD-AI stands for Human-Driven Artificial Intelligence. Fundamentally, no AI or machine can generate data insights on its own, without human intelligence. We believe that AI and Machine Learning are tools to support human reasoning, like calculators and spreadsheets have done in the past. They cannot replace humans for the task of identifying insights with business value.
The purpose of HD-AI analytics is to automatically identify a small set of potentially interesting relationships in data from many thousands of possibilities, so that human analysis can quickly hone in on the most valuable business insights. Our technology is based on cutting-edge research in hierarchical Bayesian networks, tree learning algorithms, and constraint based preference encodings.
Specifically, we use custom algorithms to automatically identify all significant correlations and clusters in consumer datasets. While correlation does not imply causation, the lack of correlation always implies the lack of causation. This means that if a variable does not exhibit a significant relationship to another variable, it can be ignored.
Dynamic Online Surveys
Beyond data analytics, HD-AI can also be used to optimize the design of online surveys used for Consumer Insights. We view survey design and data collection as an information-maximization and cost-minimization problem. The objective is to learn information from each survey question, but each question has a cost. Therefore, it is important to only ask questions that give valuable insights, rather than wasting valuable respondent time on useless questions. Asking the right questions increases the quality of consumer data, which in turns improves business insights.
We propose a new dynamic approach to online surveys where HD-AI analytics are applied on the data after an initial set of responses have been collected, to refine survey questions. The goal is to automatically test for potential variable correlations (or the lack thereof) and adjust the set of survey questions based on the results. Questions that are highly unlikely to yield insights are removed and replaced with other questions.
The automated approach of HD-AI reduces the cost and time of data analysis, making it easier for humans to test the quality of survey data “on the fly” and adjust survey questions accordingly. This testing process can be repeated throughout data collection to hone in on the most valuable set of questions – leading to higher quality consumer data.
Automatic Free-Text Analysis
Consumer surveys often ask open-ended questions where respondents enter their own answers as free text. While free-form text questions remove the bias of multiple-choice questions, as there is no pre-defined set of answer choices, they are also traditionally very time and labor-intensive to analyze even for small sample sizes. Typos, multiple-word inputs, lack of word space all make free-form text questions hard to analyze with common statistical tools. It requires human workers to manually read, classify, and count text responses.
Our technology based on Natural Language Processing (NLP) and Computational Linguistics can process free text fully automatically. It turns free text inputs into normalized quantitative data that can be analyzed by statistical tools, as shown in the example below.