Training data:
A naive comparison of S1 against S2+S3 would require approximately 22.8 trillion pairs. Therefore, candidate generation / blocking is essential.
The problem is not one-to-one.
An S1 entity can have:
Therefore, the final system must support one-to-many matching.
S1:
Among true S2/S3 matches:
Conclusion:
Manual inspection of true matches showed:
& vs andExamples:
Electronic Energy Ventures ↔ Electronic-Energy VenturesNavratra Solutions Private Limited ↔ PRIVATE NAVRATRA SOLUTIONS LIMITEDObsidian, LLC ↔ Nylabelo dba Obsidian, LLCTherefore, exact string equality is insufficient.
Non-ASCII names:
Among true matches:
For true matches with non-ASCII matched names:
Conclusion:
Cross-script matching is a significant part of the problem. Plain token similarity can completely fail for some genuine matches.
We have not yet concluded that multilingual embeddings are necessary.
Using Unicode-preserving normalization and token Jaccard:
True-match distribution:
| Name Jaccard | Share |
|---|---|
| 0–0.10 | 14.53% |
| 0.10–0.25 | 1.61% |
| 0.25–0.50 | 19.74% |
| 0.50–0.75 | 32.35% |
| 0.75–0.90 | 4.01% |
| 0.90–0.99 | ~0% |
| 0.99–1.00 | 27.73% |
Only ~21.85% of true matches have exactly equal names after the initial ASCII-oriented normalization.
Conclusion:
Name similarity is useful, but exact name equality is too restrictive.
For true matches, token Jaccard on normalized addresses:
Conclusion:
Address similarity is useful, but addresses contain substantial noise and missingness.
We generated S1-S2 candidates using exact normalized business name.
Results:
Conclusion:
Exact-name blocking reduces the search space dramatically, but captures only about 1 in 5 true S1-S2 matches.
It is useful as one blocker, but cannot be the only blocking strategy.
Among true S1-S2 pairs:
For the missed true matches:
Distribution of missed matches:
| Name Jaccard | Share |
|---|---|
| 0–0.10 | 20.81% |
| 0.10–0.25 | 1.72% |
| 0.25–0.50 | 23.70% |
| 0.50–0.75 | 40.83% |
| 0.75–0.90 | 5.32% |
| 0.90–1.00 | 7.63% |
About 53.8% of true matches missed by exact-name blocking still have name Jaccard ≥ 0.5.
Conclusion:
Approximate name retrieval is strongly justified as a second blocking experiment.
However, about 20.8% of missed matches have name Jaccard < 0.1, so name-based blocking alone will still miss a substantial group.
We generated S1-S2 candidates using exact normalized address.
Results:
Conclusion:
Exact-address blocking is highly precise but has low recall.
It produces far fewer candidates than exact-name blocking and a much higher proportion of true matches, but it misses many genuine matches because addresses are noisy.
Among true S1-S2 pairs missed by exact-address blocking:
Distribution:
| Address Jaccard | Share |
|---|---|
| 0–0.10 | 5.17% |
| 0.10–0.25 | 2.14% |
| 0.25–0.50 | 22.92% |
| 0.50–0.75 | 40.61% |
| 0.75–0.90 | 16.41% |
| 0.90–1.00 | 12.75% |
About 69.8% of true matches missed by exact-address blocking still have address Jaccard ≥ 0.5.
Conclusion:
Approximate address retrieval is also strongly justified.
| Blocker | Candidates | Precision | Recall |
|---|---|---|---|
| Exact normalized name | 10.35M | 7.66% | 21.44% |
| Exact normalized address | 564K | 81.68% | 12.48% |
The two blockers have different strengths:
No single blocking rule appears sufficient.
The likely direction is to combine multiple candidate-generation strategies:
The approximate approaches are experiments to test, not yet confirmed solutions.