Strategies for Optimizing Time Series Visual Data Exploration

Dealing with high-dimensional time series data makes the process of recommending visualizations with "interesting"insights difficult. The challenge originates from finding a way to obtain the recommended visualizations efficiently without compromising their quality. Identifying such visualizations manually is considered a labor-intensive and time-consuming process. In response, this paper introduces different techniques designed to optimize the automated recommendation process. These techniques are entirely based on the concept of computation sharing and pruning. Furthermore, we provide a glimpse into our future research works in PhD thesis. The objective is to broaden the scope of our current work and enhance the generality of our problem statement.