Matching Algorithms for
Resettlement & Relocation
Limits to Traditional Resettlement & Relocation
Typical resettlement & relocation processes rely on human decisions. This can often mean inconsistent matches, bias, and wasted resources.
Traditional
Refugee
Matching
Human Bias
Matching based on assumed preferences and subjective opinions.
Inflexible, Individuals Only
Traditional systems are challenged by complex populations and needs, and often prioritise one household member.
Limited Scalability
Labour-intensive processes are difficult to scale and error-prone.
Single-Dimensional
and One-Sided
Typically consider receiving community preferences and narrow refugee attributes.
Opaque
Decisions lack clarity and explainability, with lower efficacy and equity.
Resource Misallocation
Not accounting for population-level matching can waste scarce resources.
Pairity’s Solution: Flexible, Scalable Preference-Matching
Preferences & Capacities: Participant data as matching variables centres refugee & receiving community agency.
Data-Driven Efficiency: Calculates millions of possible combinations across dozens of matching variables.
Transparent Records: Data-driven matching creates transparent records for accountability and real-time monitoring.
Optimized Resource Use: Optimises use of resources like shelter beds, sponsor capacity, and settlement services.
Adaptable: Accounts for diverse types of households, receiving communities, and pathways.
Population-Level Matching: Optimally distribute matching outcomes for entire cohorts.
Pairity’s data-driven preference-matching accounts for the aspirations, needs, and capacities of all parties. We incorporate a vast range of data, including from refugees, communities, and governments. Our data-driven, human-centred solutions are designed for complex, fast-paced environments. Population-level algorithms optimize for everyone.
Matching works across use-cases including complementary pathways, asylum seeker housing, and community sponsorship initiatives. We deliver improved integration and social cohesion, more efficient use, and objective evidence.
Our Process