Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System
Recommender systems position themselves as powerful tools in the support of relevance and personalization, presenting remarkable potential in the area of marketing. The cold-start customer problematic presents a challenge within this topic, leading to the need of distinguishing user features and pre...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/23/12749 |
_version_ | 1797400445227892736 |
---|---|
author | Leonor Fernandes Vera Miguéis Ivo Pereira Eduardo e Oliveira |
author_facet | Leonor Fernandes Vera Miguéis Ivo Pereira Eduardo e Oliveira |
author_sort | Leonor Fernandes |
collection | DOAJ |
description | Recommender systems position themselves as powerful tools in the support of relevance and personalization, presenting remarkable potential in the area of marketing. The cold-start customer problematic presents a challenge within this topic, leading to the need of distinguishing user features and preferences based on a restricted set of transactional information. This paper proposes a hybrid recommender system that aims to leverage transactional and portfolio information as indicating characteristics of customer behaviour. Four independent systems are combined through a parallelised weighted hybrid design. The first individual system utilises the price, target age, and brand of each product to develop a content-based recommender system, identifying item similarities. Secondly, a keyword-based content system uses product titles and descriptions to identify related groups of items. The third system utilises transactional data, defining similarity between products based on purchasing patterns, categorised as a collaborative model. The fourth system distinguishes itself from the previous approaches by leveraging association rules, using transactional information to establish antecedent and precedence relationships between items through a market basket analysis. Two datasets were analysed: product portfolio and transactional datasets. The product portfolio had 17,118 unique products and the included 4,408,825 instances from 2 June 2021 until 2 June 2022. Although the collaborative system demonstrated the best evaluation metrics when comparing all systems individually, the hybridisation of the four systems surpassed each of the individual systems in performance, with a 8.9% hit rate, 6.6% portfolio coverage, and with closer targeting of customer preferences and smaller bias. |
first_indexed | 2024-03-09T01:54:42Z |
format | Article |
id | doaj.art-44bf085faf564ae18a3bf80de686a25c |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T01:54:42Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-44bf085faf564ae18a3bf80de686a25c2023-12-08T15:11:36ZengMDPI AGApplied Sciences2076-34172023-11-0113231274910.3390/app132312749Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender SystemLeonor Fernandes0Vera Miguéis1Ivo Pereira2Eduardo e Oliveira3Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalFaculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalE-goi, Av. Menéres 840, 4450-190 Matosinhos, PortugalFaculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalRecommender systems position themselves as powerful tools in the support of relevance and personalization, presenting remarkable potential in the area of marketing. The cold-start customer problematic presents a challenge within this topic, leading to the need of distinguishing user features and preferences based on a restricted set of transactional information. This paper proposes a hybrid recommender system that aims to leverage transactional and portfolio information as indicating characteristics of customer behaviour. Four independent systems are combined through a parallelised weighted hybrid design. The first individual system utilises the price, target age, and brand of each product to develop a content-based recommender system, identifying item similarities. Secondly, a keyword-based content system uses product titles and descriptions to identify related groups of items. The third system utilises transactional data, defining similarity between products based on purchasing patterns, categorised as a collaborative model. The fourth system distinguishes itself from the previous approaches by leveraging association rules, using transactional information to establish antecedent and precedence relationships between items through a market basket analysis. Two datasets were analysed: product portfolio and transactional datasets. The product portfolio had 17,118 unique products and the included 4,408,825 instances from 2 June 2021 until 2 June 2022. Although the collaborative system demonstrated the best evaluation metrics when comparing all systems individually, the hybridisation of the four systems surpassed each of the individual systems in performance, with a 8.9% hit rate, 6.6% portfolio coverage, and with closer targeting of customer preferences and smaller bias.https://www.mdpi.com/2076-3417/13/23/12749artificial intelligencemachine learningrecommender systemcold-startdigital marketingcontent filtering |
spellingShingle | Leonor Fernandes Vera Miguéis Ivo Pereira Eduardo e Oliveira Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System Applied Sciences artificial intelligence machine learning recommender system cold-start digital marketing content filtering |
title | Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System |
title_full | Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System |
title_fullStr | Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System |
title_full_unstemmed | Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System |
title_short | Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender System |
title_sort | towards hyper relevance in marketing development of a hybrid cold start recommender system |
topic | artificial intelligence machine learning recommender system cold-start digital marketing content filtering |
url | https://www.mdpi.com/2076-3417/13/23/12749 |
work_keys_str_mv | AT leonorfernandes towardshyperrelevanceinmarketingdevelopmentofahybridcoldstartrecommendersystem AT veramigueis towardshyperrelevanceinmarketingdevelopmentofahybridcoldstartrecommendersystem AT ivopereira towardshyperrelevanceinmarketingdevelopmentofahybridcoldstartrecommendersystem AT eduardoeoliveira towardshyperrelevanceinmarketingdevelopmentofahybridcoldstartrecommendersystem |