Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió publicadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/223987
Applying knowledge transfer in data augmentation to improve online advertising performance of entrepreneurs
Títol de la revista
ISSN de la revista
Títol del volum
Resum
Artificial intelligence (AI) is transforming the way businesses operate, enabling entrepreneurs to achieve diagnoses that were once only possible for large companies. This transformation is evident in digital advertising, where AI not only enables advanced analytics, but also offers the possibility of developing creative designs at low cost. However, this technological progress contrasts with predictions of a slowdown in online advertising in the coming years. Thus, entrepreneurs must change their strategies to overcome the defensive positions of competitors. This study proposes the combination of AI analytical algorithms (XGBoost) with data augmentation algorithms (SMOTE) to improve targeting accuracy when launching online communication campaigns. Specifically, a case study illustrates how a lead-gathering company uses these algorithms to profile five market segments (hearing aids, NGOs, energy distributors, telecommunications and finance). Subsequently, a field experiment was conducted with one of the products, solar panels, to assess external validity. The results reveal that the combination of both algorithms improves internal validity for four of the five products, and the field experiment confirms the external validity of the energy product. Finally, recommendations on the use of these tools are proposed to entrepreneurs.
Descripció
Matèries (anglès)
Citació
Col·leccions
Citació
HUERTAS GARCÍA, Rubén, SÁEZ ORTUÑO, Laura, FORGAS COLL, Santiago, SÁNCHEZ GARCÍA, Javier. Applying knowledge transfer in data augmentation to improve online advertising performance of entrepreneurs. _Journal of Innovation & Knowledge_. 2025. Vol. 10, núm. 6. [consulta: 26 de novembre de 2025]. ISSN: 2530-7614. [Disponible a: https://hdl.handle.net/2445/223987]