MARU Targets Human Bias with Topic Modelling Tool

Tech-enabled market and customer insights company Maru Group has launched an unstructured data engine, 'Maru/HUB Topic Modelling', which uses AI and machine learning to automatically group relevant comments together, without the need for user-defined rules and human biases.

Maru and its operating companies - Maru/Matchbox, Maru/Blue and Maru/HUB - combine expertise in System 1 thinking (fast, instinctive and emotional) and System 2 (slower, more deliberative and more logical), in order to deliver a 'holistic understanding' of consumer decision-making. The group's proprietary technology platform, Maru/HUB, integrates multiple data streams into a single system allowing real-time analysis of behavioral, transactional and attitudinal information.

Building on Maru/HUB, the new Topic Modelling tool allows users and researchers to identify key themes, understand relationships between trends, and uncover hidden patterns in data. The group has worked in conjunction with behavioural scientists at the University of Strathclyde to test the tool on a large scale and 'has been proven' to uncover new insights missed by traditional code frame-based textual analysis.

Steve Brockway (pictured), Chief Research Officer at Maru/Matchbox UK, and lead researcher on the project, comments on the launch: 'The technology is empowering better insights by uncovering new patterns in unstructured data, and at a faster rate than any human-machine partnership could. We have momentum in our R&D, our next step is to take machine-based learning and apply it to analysis approaches to better understand what's driving certain behavior instantaneously'.

Web site: www.marugroup.net .