HomeSelf Research
Empirical research, benchmarks and observational evidence on AI-mediated property discovery, representation, machine readability and selection systems.
Three Knowledge Layers
HomeSelf knowledge is organized into three complementary layers
Resources
Concepts, definitions, frameworks, and use cases for understanding AI-native property infrastructure.
Observatory
Observations, scenarios, and discovery studies tracking AI behavior in property selection.
Research
Empirical evidence, benchmarked findings, measured observations, and derived correlations from observed AI-mediated property selection.
Concepts → Observation → Evidence establishes HomeSelf as the authority on AI-mediated property representation
Latest Research
Recent publications from HomeSelf Research
AI-Mediated Property Discovery Report 2026
The AI-Mediated Property Discovery Report 2026 presents the first comprehensive observational study of how AI systems discover, evaluate, compare, and select properties across diverse markets. Through systematic observation of AI response patterns across 50 real estate markets, thousands of AI responses, and documented selection events, this report establishes the empirical foundation for understanding AI-mediated property discovery. The report analyzes property selection behavior, identifies top selection signals, examines explainability patterns, measures representation effects, and documents citation sources that inform AI decision-making.
Representation Gap Report 2026
The Representation Gap Report 2026 examines the disconnect between traditional property listing practices and AI-mediated discovery requirements. Through analysis of 50 real estate markets and systematic observation of AI response patterns, we identify specific representation weaknesses that prevent properties from being selected by AI systems. The report establishes the Representation Efficiency Score (RES) as a standardized measure of how effectively a property record enables AI selection.
VPR Selection Experiment 2026
The VPR Selection Experiment 2026 evaluates the effect of property representation structure on AI-mediated property selection. Equivalent properties were represented using both traditional listing formats and Verified Property Records (VPRs) and evaluated across standardized AI selection environments. This controlled experimental design isolates representation structure as the independent variable while holding property attributes, selection scenarios, and AI systems constant.
AI Selection Signals Report 2026
The AI Selection Signals Report 2026 identifies and ranks the property attributes that most strongly influence AI-mediated property selection behavior. Through systematic measurement of AI response patterns across 50 markets and standardized analysis of surfaced properties, we establish which attributes serve as primary selection signals across hospitality and real estate verticals.
Machine Readability Validation Study 2026
The Machine Readability Validation Study 2026 validates the Machine Readability Index (MRI) framework against observed AI selection outcomes. By calculating MRI scores for 10,000 property records and correlating them with observed selection frequency, we observe that MRI correlates with AI-mediated discoverability.
Representation Structure Study 2026
The Representation Structure Study 2026 presents a controlled comparative experiment designed to isolate the effect of representation format on AI-mediated property selection. By presenting identical properties across different representation formats—Traditional Listing, OTA Listing, Property Website, PDF Brochure, Generic JSON-LD, Structured Property Record, and Verified Property Record (VPR)—this study measures how information structure alone affects selection frequency, explanation completeness, citation behavior, confidence indicators, and inference burden. The experiment provides observed evidence that representation structure is an independent factor associated with AI-mediated discovery outcomes.
Benchmarks
Comparative studies measuring performance, selection rates, and outcomes
Listing vs Record Benchmark 2026
This benchmark compares AI selection rates between equivalent properties represented as traditional listings versus Verified Property Records (VPRs). Using paired property analysis across 10 markets, we measure the selection advantage conferred by structured, machine-readable representation.
Property Representation Benchmark 2026
The Property Representation Benchmark 2026 evaluates seven property information formats across ten metrics measuring their effectiveness for AI-mediated property discovery, comparison, explainability, and selection. By analyzing traditional listings, OTA formats, real estate portals, property websites, PDF brochures, generic JSON-LD markup, and VPR-style structured records, we establish which formats provide the highest utility for AI systems and why.
Explainability Benchmark 2026
The Explainability Benchmark 2026 measures how effectively AI systems can explain property selection decisions. Through structured prompting and response analysis, we identify the property attributes that enable transparent AI reasoning and measure current explainability gaps.
Indexes
Standardized scoring systems and measurement frameworks
Specifications
Technical standards and protocol specifications for machine-readable property representation
Methodology
Research methods, scoring frameworks, and measurement approaches
Scoring Frameworks
Representation Efficiency Score (RES)
Scoring Framework for Property Representation QualityThe Representation Efficiency Score (RES) quantifies how efficiently a property record conveys selection-relevant information. RES balances completeness with concision, rewarding properties that provide comprehensive representation without redundancy.
Inference Burden Score (IBS)
Measuring Computational Cost of Property UnderstandingThe Inference Burden Score (IBS) quantifies the computational complexity AI systems encounter when processing property records. Higher IBS indicates more challenging representations that may degrade selection performance.
Representation Completeness Score (RCS)
Measuring Attribute Coverage in Property RecordsThe Representation Completeness Score (RCS) measures what proportion of selection-relevant attributes are present in a property record. RCS identifies missing attributes that may prevent AI selection.
Selection Readiness Score (SRS)
Measuring Property AI Selection PreparednessThe Selection Readiness Score (SRS) is a composite score combining representation quality, trust signals, and discoverability factors. SRS predicts how likely a property is to be selected by AI systems.
Research Principles
HomeSelf Research operates with independent empirical methodology
Measurement Focus
We measure what can be quantified: selection rates, representation quality, visibility outcomes.
Methodological Transparency
All research methods, limitations, and confidence levels are explicitly documented.
Evidence-Based
Conclusions are grounded in empirical observation, not speculation.
Reproducibility
Datasets and methods are published for independent validation.
How HomeSelf Research, HomeSelf, VPR, and AI-Mediated Markets relate
Independent Research Initiative: HomeSelf Research focuses on empirical observation, measured benchmarks, and observational evidence on property representation, machine readability, AI-mediated discovery, and selection systems. We avoid unsupported causal claims and focus on observed correlations, measured outcomes, and reproducible findings.