Major League Baseball (MLB) has a long history of providing detailed, high-quality data, leading to a tremendous surge in sports analytics research in recent years. In 2015, MLB.com released the StatCast spatiotemporal data-tracking system, which has been used in approximately 2,500 games since its inception to capture player and ball locations as well as semantically meaningful game events. This article presents a visualization and analytics infrastructure to help query and facilitate the analysis of this new tracking data. The goal is to go beyond descriptive statistics of individual plays, allowing analysts to study diverse collections of games and game events. The proposed system enables the exploration of the data using a simple querying interface and a set of flexible interactive visualization tools.

No abstract

No abstract

While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-toend ML data processing pipelines. However, these follow a besteffort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.

No abstract