Data By the Bay

Understanding the nature of the expressive and diverse audiences of applications can be transformative in the creation of powerful data products. For many industries, user interaction is the most accurate signal in audience segmentation, but the devices in the Internet of Things are often quiet and natural audience segments can be lost. In analyzing the Automatic driving data we have learned that there are many kinds of cars, but drivers themselves often act very similarly. In this study we correlate the confluence of driving style and physical models of cars with the aim to segment our audience using unsupervised learning techniques such as NMF.