Template-Based Schema Matching of Multi-Layout Tenancy Schedules:A Comparative Study of a Template-Based Hybrid Matcher and the ALITE Full Disjunction Model

TL;DR

This paper introduces a hybrid, template-based schema matching approach for tenancy schedules that improves alignment accuracy and usability over traditional models like ALITE by combining schema and instance-based metrics.

Contribution

It presents a novel hybrid matcher that integrates schema and data metrics with optimal assignment algorithms, enhancing schema matching for multi-layout tenancy schedules.

Findings

Peak F1-score of 0.881 with the hybrid matcher

45.7% nulls in the optimized matching results

Superior performance compared to ALITE on ground truth datasets

Abstract

The lack of standardized tabular formats for tenancy schedules across real estate firms creates significant inefficiencies in data integration. Existing automated integration methods, such as Full Disjunction (FD)-based models like ALITE, prioritize completeness but result in schema bloat, sparse attributes and limited business usability. We propose a novel hybrid, template-based schema matcher that aligns multi-layout tenancy schedules to a predefined target schema. The matcher combines schema (Jaccard, Levenshtein) and instance-based metrics (data types, distributions) with globally optimal assignments determined via the Hungarian Algorithm. Evaluation against a manually labeled ground truth demonstrates substantial improvements, with grid search optimization yielding a peak F1-score of 0.881 and an overall null percentage of 45.7%. On a separate ground truth of 20 semantically similar column sets, ALITE achieves an F1-score of 0.712 and 75.6% nulls. These results suggest that combining structured business knowledge with hybrid matching can yield more usable and business-aligned schema mappings. The approach assumes cleanly extracted tabular input, future work could explore extending the matcher to support complex, composite tables.