Towards a Workload for Evolutionary Analytics

TL;DR

This paper introduces a new workload for evolutionary analytics, emphasizing the need for systems to support iterative, exploratory data analysis with frequent query revisions and complex functions.

Contribution

The paper defines the properties of evolutionary analytics, proposes a specific workload and metrics to evaluate system support for this analytical style.

Findings

Identifies key properties of evolutionary analytics

Proposes a workload and metrics for evaluation

Provides methodologies for workload execution

Abstract

Emerging data analysis involves the ingestion and exploration of new data sets, application of complex functions, and frequent query revisions based on observing prior query answers. We call this new type of analysis evolutionary analytics and identify its properties. This type of analysis is not well represented by current benchmark workloads. In this paper, we present a workload and identify several metrics to test system support for evolutionary analytics. Along with our metrics, we present methodologies for running the workload that capture this analytical scenario.