Spacematch: Using environmental preferences to match occupants to suitable activity-based workspaces

TL;DR

This paper presents Spacematch, a platform that uses occupant environmental preferences and IoT sensor data to optimize activity-based workspace allocation, improving comfort and space efficiency in office environments.

Contribution

The paper introduces a novel web-based platform that merges occupant feedback with IoT data to personalize workspace assignment in ABW settings.

Findings

Occupants can be segmented into user types based on preferences.

Preference data can inform personalized workspace recommendations.

The platform effectively merges feedback with environmental data for optimization.

Abstract

The activity-based workspace (ABW) paradigm is becoming more popular in commercial office spaces. In this strategy, occupants are given a choice of spaces to do their work and personal activities on a day-to-day basis. This paper shows the implementation and testing of the Spacematch platform that was designed to improve the allocation and management of ABW. An experiment was implemented to test the ability to characterize the preferences of occupants to match them with suitable environmentally-comfortable and spatially-efficient flexible workspaces. This approach connects occupants with a catalog of available work desks using a web-based mobile application and enables them to provide real-time environmental feedback. In this work, we tested the ability for this feedback data to be merged with indoor environmental values from Internet-of-Things (IoT) sensors to optimize space and energy use by grouping occupants with similar preferences. This paper outlines a case study implementation of this platform on two office buildings. This deployment collected 1,182 responses from 25 field-based research participants over a 30-day study. From this initial data set, the results show that the ABW occupants can be segmented into specific types of users based on their accumulated preference data, and matching preferences can be derived to build a recommendation platform.