| Naslov: | AI-driven peer company identification : a semantic text-similarity approach beyond traditional industry classification systems |
|---|
| Avtorji: | ID Jagrič, Timotej (Avtor)
ID Herman, Aljaž (Avtor) |
|---|
| Datoteke: |  https://hrcak.srce.hr/en/clanak/500555
 RAZ_Jagric_Timotej_2026.pdf (449,76 KB)
MD5: 52CA00867B70E387DDC5A7F931FCF109
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Znanstveno delo |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | EPF - Ekonomsko-poslovna fakulteta
|
|---|
| Opis: | Background: Traditional classification systems, such as NACE and NAICS, primarily classify businesses by industry, limiting their ability to identify related companies. Objectives: This research aims to improve the identification of related companies by analysing their descriptions, utilising a more semantic approach. Methods/Approach: A pre-trained BERT model was employed to assess semantic text similarity for suggesting peer companies. The goal was to create a system that assists experts in comparing companies based on their descriptions, rather than developing a perfect classification tool. Results: Trained on publicly available data, the model achieved 73.6% accuracy in identifying related companies, with accuracy exceeding 90% for selected industry-pair combinations. Conclusions: While the system demonstrates promise, its outputs are intended to guide professionals who must ultimately validate the results. The findings emphasise the strengths and limitations of using AI models for this purpose, providing a foundation for future enhancements and real-world applications. However, the solution remains a conceptual idea, limited to only 13 industry categories, highlighting the need for broader testing and development. |
|---|
| Ključne besede: | industrial classification schemes, personal culture peer companies, artificial intelligence, semantic text similarity, BERT |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Datum objave: | 30.04.2026 |
|---|
| Leto izida: | 2026 |
|---|
| Št. strani: | str. 204-222 |
|---|
| Številčenje: | Vol. 17, no. 1 |
|---|
| PID: | 20.500.12556/DKUM-98300  |
|---|
| UDK: | 004.8:658 |
|---|
| COBISS.SI-ID: | 280367619 |
|---|
| DOI: | 10.2478/bsrj-2026-0010 |
|---|
| ISSN pri članku: | 1847-9375 |
|---|
| Datum objave v DKUM: | 03.06.2026 |
|---|
| Število ogledov: | 170 |
|---|
| Število prenosov: | 8 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
