# Speculative Execution for Guided Visual Analytics

## TL;DR

This paper introduces Speculative Execution for Visual Analytics, enabling automatic generation of alternative models to enhance exploration, reduce bias, and accelerate optimization in model analysis.

## Contribution

It presents a novel concept of Speculative Execution in visual analytics, demonstrating its potential through five application scenarios and discussing future research directions.

## Key findings

- Speeds up model exploration and optimization processes.
- Reduces confirmation bias in visual analytics.
- Shows promising potential in five application scenarios.

## Abstract

We propose the concept of Speculative Execution for Visual Analytics and discuss its effectiveness for model exploration and optimization. Speculative Execution enables the automatic generation of alternative, competing model configurations that do not alter the current model state unless explicitly confirmed by the user. These alternatives are computed based on either user interactions or model quality measures and can be explored using delta-visualizations. By automatically proposing modeling alternatives, systems employing Speculative Execution can shorten the gap between users and models, reduce the confirmation bias and speed up optimization processes. In this paper, we have assembled five application scenarios showcasing the potential of Speculative Execution, as well as a potential for further research.