JDS Journal of Data Science 1683-86021680-743X1680-743X School of Statistics, Renmin University of China JDS1236 10.6339/26-JDS1236 Computing in Data Science Maximizing Linkage in Address Data: Spatial, Exact, and Fuzzy Matching✩ ChampneyTimothy F.tfchampney@earthlink.net1∗ QinHongxun2 Formerly The MITRE Corporation, Human Systems Integration and Analysis, Washington, DC 20008, United States The MITRE Corporation, Federal Statistics and Data Science, McLean, VA 22102, United States

Approved for Public Release, Distribution Unlimited. Public Release Case Number 25-2360.

Corresponding author. Email: tfchampney@earthlink.net. 2026107202600116 Supplementary Material

Zip file contains the original Powerpoint presentation, FCSM 2024 Matching Presentation Draft 10102024 Clean_CB.pptx and Word document describing files and matching process, JDS_matching_data_and_steps.docx.

8920252952026 2026 The Author(s). Published by the School of Statistics and the Center for Applied Statistics, Renmin University of China.2026 Open access article under the CC BY license.

High quality record linkages are critical for enriching survey data with alternative data sources. To enhance the American Community Survey (ACS) (US Census Bureau, 2025), we evaluated several options to match commercially available property data to housing unit records in the ACS and the Census Master Address File (MAF) (US Census Bureau, 2022) data, with the ultimate goal of supplementing data collected in the survey with the commercial property data. Techniques to match address data come in two flavors: spatial matching and address matching. Spatial matching is done by overlaying commercial boundary shape files on the lat-long coordinates on the MAF to associate Census housing unit records to commercial property parcel records. This method is useful because it does not require matching of text fields, but performs poorly when parcels include many housing units (e.g., large apartment buildings). Address matching, or entity resolution at the address level, links records across the two sources based on the content of various address fields, and offers the possibility of disambiguating multiple matches and matching objects that cannot be successfully assigned a unique match through spatial matching. Several approaches are available for address matching, including rule-based, deterministic, fuzzy, and probabilistic methods. In our article we summarize literature comparing various combinations of spatial and address matching techniques to illustrate the trade-off between linkage rates and linkage quality. We also consider hybrid solutions that leverage spatial matching as well as several types of address matching to maximize high quality linkages for our research and discuss future directions such as incorporating probabilistic matching as an added step.

 ACS address list Census deterministic matching fuzzy matching MAF probabilistic matching spatial matching This work was partially supported by the U.S. Census Bureau. This work was supported by the U.S. Census Bureau, Department of Commerce (DOC) Contract 1331L523D13OS0003. References Aldridge RW, Shaji K, Hayward AC, Abubakar I (2015). Accuracy of probabilistic linkage using the enhanced matching system for public health and epidemiological studies. PLoS ONE, 10(8): e0136179. https://doi.org/10.1371/journal.pone.0136179 Binder A, Molfino E, Voorheis J (2022). Comparing the 2019 american housing survey to contemporary sources of property tax records: Implications for survey efficiency and quality, Technical report, U.S. Census Bureau, Center for Economic Studies. Binette O, Steorts RC (2022). (almost) all of entity resolution. Science Advances, 8(12): eabi8021. https://doi.org/10.1126/sciadv.abi8021 Brummet Q (2014). Comparison of survey, federal, and commercial address data quality, Technical Report CARRA Working Paper #2014-06, U.S. Census Bureau, Center for Administrative Records Research and Applications. Brummet Q (2015). Matching addresses between household surveys and commercial data, Technical Report CARRA Working Paper #2015-04, U.S. Census Bureau, Center for Administrative Records Research and Applications. Champney T, Qin H, Coffey S (2024). Maximizing linkage in address data: Spatial, exact, and fuzzy matching. In: Proceedings of the Federal Committee on Statistical Methodology Conference. Federal Committee on Statistical Methodology. Accessed: 2025-08-07. Clark S, Barth D, Binder A, Diagne AF, Pharris-Ciurej N, Voorheis J (2023). Acreage administrative records data research for the american community survey Technical report. U.S. Census Bureau. Clark S, Sawyer R (2018). Housing administrative records simulation, Technical report, U.S. Census Bureau. Comber S, Arribas-Bel D (2019). Demonstrating the utility of machine learning innovations in address matching to spatial socio-economic applications. REGION. Journal of ERSA, 6(2): 1–15. Cortes TR, Silveira IHd, Junger WL (2021). Improving geocoding matching rates of structured addresses in Rio de Janeiro, Brazil. Cadernos de Saúde Pública, 37: e00039321. https://doi.org/10.1590/0102-311x00039321 Dillon M (2019). Preliminary research for replacing or supplementing the acreage, number of rooms and bedrooms, tenure, property value, & real estate taxes questions on the american community survey with administrative records, Technical report, U.S. Census Bureau, Center for Economic Studies. Dusetzina SB, Tyree S, Meyer AM, Meyer A, Green L, Carpenter WR (2014). An overview of record linkage methods. In: Linking Data for Health Services Research: A Framework and Instructional Guide. Agency for Healthcare Research and Quality (U.S.). Goldberg DW, Wilson JP, Knoblock CA (2007). From Text to Geographic Coordinates: The Current State of Geocoding. URISA Journal 19(1): 33–46. Hagger-Johnson G, Harron K, Aldridge R, Fu B, Setakis E, …, Gilbert R (2017). Combining deterministic and probabilistic matching to reduce data linkage errors in hospital administrative data. International Journal of Population Data Science 1(1): 296. https://doi.org/10.23889/ijpds.v1i1.316 Lee S (2025). Mastering Shapefiles in Geospatial Analysis. Moreno D (2025). The luca process: A local government’s guide to the census address review. Pebesma E, Bivand RS (2023). Spatial data science: With applications in R. In: Handbook of Spatial Data Science. Chapman and Hall/CRC. Placekey (2024). Mastering address matching: Techniques and best practices. Industry blog/white paper. Prindle J, Suthar H, Putnam-Hornstein E (2023). An open-source probabilistic record linkage process for records with family-level information: Simulation study and applied analysis. PLoS ONE, 18(10): e0291581. https://doi.org/10.1371/journal.pone.0291581 Raim A (2016). Informing maintenance to the U.S. Census Bureaus Master Address File using statistical decision theory. Seeskin ZH (2016). Evaluating the use of commercial data to improve survey estimates of property taxes, Technical report, U.S. Census Bureau. Sloan S, Hoicowitz D (2016). Fuzzy matching: Where is it appropriate and how is it done? SAS can help. Tyris J, Dwyer G, Parikh K, Gourishankar A, Patel S (2024). Geocoding and geospatial analysis: Transforming addresses to understand communities and health. Hospital Pediatrics, 14(6): e292–e297. https://doi.org/10.1542/hpeds.2023-007383 US Census Bureau (2022). Chapter 3: Frame development. US Census Bureau (2025). ACS information guide. Wagner D, Layne M (2014). The person identification validation system (pvs): Applying the center for administrative records research and applications’ (carra) record linkage software. Technical report. U.S. Census Bureau. Zhang Z, Balsebre P, Luo S, Hai Z, Huang J (2024). StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information. In Proceedings of LREC-COLING 2024, 20–25 May 2024, pp. 15350–15361. Zhu Y, Matsuyama Y, Ohashi Y, Setoguchi S (2015). When to conduct probabilistic linkage vs. deterministic linkage? A simulation study. Journal of Biomedical Informatics, 56: 80–86. https://doi.org/10.1016/j.jbi.2015.05.012