Active learning for collaborative data exploration in the design process

In design processes, the integration of advanced technologies, such as machine learning, can unlock insights designers could hardly come by in the past. This research explores the potential of machine learning models to translate data into actionable design insights, empowering designers to refine their prototypes and enhance overall user experience without compromising creative agency over the design process.

Enhancing Data Understanding: 

Designers can collect large volumes of telemetry data from sensors embedded in prototypes. This data, if left unprocessed, is underutilized. Machine learning models can convert this data into meaningful patterns, offering designers a new material—data—as a tangible component of the design process.

Insights from actual User Data

Real-time, actionable insights, through in situ user interaction, data can enable designers to iteratively refine their prototypes more effectively. This way of using machine learning aids in identifying unexpected behaviors and novel user interactions, thus informing more precise design adjustments.

Addressing Usability Challenges: 

Many designers have limited experience with machine learning and complex data analysis. This project aims to create intuitive and user-friendly tools that make these advanced techniques accessible to designers of varying expertise levels. Simplifying the interface and interaction with machine learning models is crucial for democratizing access to these powerful tools.

The primary goal of this research project is to empower designers with machine learning that intuitively enhances their creative process. This integration aims to offer deeper insights into user behavior without compromising design autonomy. By leveraging telemetry data to identify and classify user movements, this machine learning tool seeks to reveal unexpected user interactions, enabling designers to refine product functionality and enhance user experience​.