Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/71227
Título: | Multi-objective grammatical evolution of decision trees for mobile marketing user conversion prediction |
Autor(es): | Pereira, Pedro José Cortez, Paulo Mendes, Rui |
Palavras-chave: | Conversion Rate (CVR) prediction Decision Trees Explainable Artificial Intelligence (XAI) Grammatical Evolution Lamarckian Evolution |
Data: | 2021 |
Editora: | Elsevier |
Revista: | Expert Systems with Applications |
Citação: | Pereira, P. J., Cortez, P., & Mendes, R. (2021). Multi-objective Grammatical Evolution of Decision Trees for Mobile Marketing user conversion prediction. Expert Systems with Applications, 168, 114287. doi: https://doi.org/10.1016/j.eswa.2020.114287 |
Resumo(s): | The worldwide adoption of mobile devices is raising the value of Mobile Performance Marketing, which is supported by Demand-Side Platforms (DSP) that match mobile users to advertisements. In these markets, monetary compensation only occurs when there is a user conversion. Thus, a key DSP issue is the design of a data-driven model to predict user conversion. To handle this nontrivial task, we propose a novel Multi-objective Optimization (MO) approach to evolve Decision Trees (DT) using a Grammatical Evolution (GE), under two main variants: a pure GE method (MGEDT) and a GE with Lamarckian Evolution (MGEDTL). Both variants evolve variable-length DTs and perform a simultaneous optimization of the predictive performance and model complexity. To handle big data, the GE methods include a training sampling and parallelism evaluation mechanism. The algorithms were applied to a recent database with around 6 million records from a real-world DSP. Using a realistic Rolling Window (RW) validation, the two GE variants were compared with a standard DT algorithm (CART), a Random Forest and a state-of-the-art Deep Learning (DL) model. Competitive results were obtained by the GE methods, which present affordable training times and very fast predictive response times. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/71227 |
DOI: | 10.1016/j.eswa.2020.114287 |
ISSN: | 0957-4174 |
Versão da editora: | https://www.sciencedirect.com/science/article/pii/S0957417420309891 |
Arbitragem científica: | yes |
Acesso: | Acesso restrito UMinho |
Aparece nas coleções: | DI/CCTC - Artigos (papers) |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
1-s2.0-S0957417420309891-main.pdf Acesso restrito! | 789,95 kB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons