Daniel Alves de Oliveira
Research Subjects
Daniel Alves de Oliveira has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Duarte Coelho
E-goi
6 shared publications - Ivo Pereira
Interdisciplinary Studies Research Center (ISRC), Instituto Superior de Engenharia do Porto, Porto, Portugal
6 shared publications - Ana Madureira
ISRC - Interdisciplinary Studies Research Center, ISEP
5 shared publications - Miguel Ângelo Rebelo
E-goi
3 shared publications - Inês César
ISRC - Interdisciplinary Studies Research Center, ISEP
2 shared publications - Susana Nicola
Polytechnic of Porto
2 shared publications
Latest Publications
- 27 July 2025
- Published by Springer Nature
- p. 187-196
SMS Send Frequency Prediction: A Case Study
- Open Access
- 23 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8196
Leveraging Feature Extraction to Perform Time-Efficient Selection for Machine Learning Applications
In the age of rapidly advancing machine learning capabilities, the pursuit of maximum performance encounters the practical limitations imposed by limited resources in several fields. This work presents a cost-effective proposal for feature selection, which is a crucial part of machine learning processes, and intends to partly solve this problem through computational time reduction. The proposed methodology aims to strike a careful balance between feature exploration and strict computational time concerns, by enhancing the quality and relevance of data. This approach focuses on the use of interim representations of feature combinations to significantly speed up a potentially slow and computationally expensive process. This strategy is evaluated in several datasets against other feature selection methods, and the results indicate a significant reduction in the temporal costs associated with this process, achieving a mean percentage decrease of 85%. Furthermore, this reduction is achieved while maintaining competitive model performance, demonstrating that the selected features remain effective for the learning task. These results emphasize the method’s feasibility, confirming its ability to transform machine learning applications in environments with limited resources.
- 23 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8196
Open AccessLeveraging Feature Extraction to Perform Time-Efficient Selection for Machine Learning Applications
In the age of rapidly advancing machine learning capabilities, the pursuit of maximum performance encounters the practical limitations imposed by limited resources in several fields. This work presents a cost-effective proposal for feature selection, which is a crucial part of machine learning processes, and intends to partly solve this problem through computational time reduction. The proposed methodology aims to strike a careful balance between feature exploration and strict computational time concerns, by enhancing the quality and relevance of data. This approach focuses on the use of interim representations of feature combinations to significantly speed up a potentially slow and computationally expensive process. This strategy is evaluated in several datasets against other feature selection methods, and the results indicate a significant reduction in the temporal costs associated with this process, achieving a mean percentage decrease of 85%. Furthermore, this reduction is achieved while maintaining competitive model performance, demonstrating that the selected features remain effective for the learning task. These results emphasize the method’s feasibility, confirming its ability to transform machine learning applications in environments with limited resources.
- Open Access
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 118706-118723
Enhancing Consumer Insights Through Multimodal Artificial Intelligence and Affective Computing
The growing interest in learning more about consumer behaviors through analytical techniques requires the integration of innovative approaches that relate their needs to strategic marketing procedures. Multimodality and Affective Computing combined a series of robust optimizations for this challenge, implying the complexity of each application. However, the entanglement of different modalities demands new and tailored refinements to enhance adaptability and accuracy in the field. This paper outlines the implementation of a Multimodal Artificial Intelligence methodology with Affective Computing to enhance consumer insights and marketing strategies. The application combines different data modalities, such as textual, visual, and audio inputs, to tackle complex issues in dealing with consumer sentiment. The proposed approach uses advanced preprocessing techniques, including word embeddings, neural networks, and recurrent models, to extract information from diverse modalities. Fusion strategies, such as attention-based and late fusion procedures, are utilized to combine knowledge, facilitating robust sentiment detection. The implementation includes the analysis of real-time customer feedback on social media and product assessments, demonstrating improvements in predicting engagement and shaping consumer behavior. The results underscore the practical viability of the suggested method, promoting progress in multimodal sentiment analysis to extract actionable consumer insights in marketing.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 118706-118723
Open AccessEnhancing Consumer Insights Through Multimodal Artificial Intelligence and Affective Computing
The growing interest in learning more about consumer behaviors through analytical techniques requires the integration of innovative approaches that relate their needs to strategic marketing procedures. Multimodality and Affective Computing combined a series of robust optimizations for this challenge, implying the complexity of each application. However, the entanglement of different modalities demands new and tailored refinements to enhance adaptability and accuracy in the field. This paper outlines the implementation of a Multimodal Artificial Intelligence methodology with Affective Computing to enhance consumer insights and marketing strategies. The application combines different data modalities, such as textual, visual, and audio inputs, to tackle complex issues in dealing with consumer sentiment. The proposed approach uses advanced preprocessing techniques, including word embeddings, neural networks, and recurrent models, to extract information from diverse modalities. Fusion strategies, such as attention-based and late fusion procedures, are utilized to combine knowledge, facilitating robust sentiment detection. The implementation includes the analysis of real-time customer feedback on social media and product assessments, demonstrating improvements in predicting engagement and shaping consumer behavior. The results underscore the practical viability of the suggested method, promoting progress in multimodal sentiment analysis to extract actionable consumer insights in marketing.
- Open Access
- 12 June 2024
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20 (3) , 2001-2020
A case study on phishing detection with a machine learning net
Phishing attacks aims to steal sensitive information and, unfortunately, are becoming a common practice on the web. Email phishing is one of the most common types of attacks on the web and can have a big impact on individuals and enterprises. There is still a gap in prevention when it comes to detecting phishing emails, as new attacks are usually not detected. The goal of this work was to develop a model capable of identifying phishing emails based on machine learning approaches. The work was performed in collaboration with E-goi, a multi-channel marketing automation company. The data consisted of emails collected from the E-goi servers in the electronic mail format. The problem consisted of a classification problem with unbalanced classes, with the minority class corresponding to the phishing emails and having less than 1% of the total emails. Several models were evaluated after careful data selection and feature extraction based on the email content and the literature regarding these types of problems. Due to the imbalance present in the data, several sampling methods based on under-sampling techniques were tested to see their impact on the model’s ability to detect phishing emails. The final model consisted of a neural network able to detect more than 80% of phishing emails without compromising the remaining emails sent by E-goi clients.
- 12 June 2024
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 20 (3) , 2001-2020
Open AccessA case study on phishing detection with a machine learning net
Phishing attacks aims to steal sensitive information and, unfortunately, are becoming a common practice on the web. Email phishing is one of the most common types of attacks on the web and can have a big impact on individuals and enterprises. There is still a gap in prevention when it comes to detecting phishing emails, as new attacks are usually not detected. The goal of this work was to develop a model capable of identifying phishing emails based on machine learning approaches. The work was performed in collaboration with E-goi, a multi-channel marketing automation company. The data consisted of emails collected from the E-goi servers in the electronic mail format. The problem consisted of a classification problem with unbalanced classes, with the minority class corresponding to the phishing emails and having less than 1% of the total emails. Several models were evaluated after careful data selection and feature extraction based on the email content and the literature regarding these types of problems. Due to the imbalance present in the data, several sampling methods based on under-sampling techniques were tested to see their impact on the model’s ability to detect phishing emails. The final model consisted of a neural network able to detect more than 80% of phishing emails without compromising the remaining emails sent by E-goi clients.
- Open Access
- 15 April 2024
- Published by MDPI AG in Informatics
- Vol. 11 (2) , 19
A Machine Learning as a Service (MLaaS) Approach to Improve Marketing Success
The exponential growth of data in the digital age has led to a significant demand for innovative approaches to assess data in a manner that is both effective and efficient. Machine Learning as a Service (MLaaS) is a category of services that offers considerable potential for organisations to extract valuable insights from their data while reducing the requirement for heavy technical expertise. This article explores the use of MLaaS within the realm of marketing applications. In this study, we provide a comprehensive analysis of MLaaS implementations and their benefits within the domain of marketing. Furthermore, we present a platform that possesses the capability to be customised and expanded to address marketing’s unique requirements. Three modules are introduced: Churn Prediction, One-2-One Product Recommendation, and Send Frequency Prediction. When applied to marketing, the proposed MLaaS system exhibits considerable promise for use in applications such as automated detection of client churn prior to its occurrence, individualised product recommendations, and send time optimisation. Our study revealed that AI-driven campaigns can improve both the Open Rate and Click Rate. This approach has the potential to enhance customer engagement and retention for businesses while enabling well-informed decisions by leveraging insights derived from consumer data. This work contributes to the existing body of research on MLaaS in marketing and offers practical insights for businesses seeking to utilise this approach to enhance their competitive edge in the contemporary data-oriented marketplace.
- 15 April 2024
- Published by MDPI AG in Informatics
- Vol. 11 (2) , 19
Open AccessA Machine Learning as a Service (MLaaS) Approach to Improve Marketing Success
The exponential growth of data in the digital age has led to a significant demand for innovative approaches to assess data in a manner that is both effective and efficient. Machine Learning as a Service (MLaaS) is a category of services that offers considerable potential for organisations to extract valuable insights from their data while reducing the requirement for heavy technical expertise. This article explores the use of MLaaS within the realm of marketing applications. In this study, we provide a comprehensive analysis of MLaaS implementations and their benefits within the domain of marketing. Furthermore, we present a platform that possesses the capability to be customised and expanded to address marketing’s unique requirements. Three modules are introduced: Churn Prediction, One-2-One Product Recommendation, and Send Frequency Prediction. When applied to marketing, the proposed MLaaS system exhibits considerable promise for use in applications such as automated detection of client churn prior to its occurrence, individualised product recommendations, and send time optimisation. Our study revealed that AI-driven campaigns can improve both the Open Rate and Click Rate. This approach has the potential to enhance customer engagement and retention for businesses while enabling well-informed decisions by leveraging insights derived from consumer data. This work contributes to the existing body of research on MLaaS in marketing and offers practical insights for businesses seeking to utilise this approach to enhance their competitive edge in the contemporary data-oriented marketplace.
- 28 March 2023
- Published by Springer Nature
- p. 404-413
Analysing and Modeling Customer Success in Digital Marketing
- 28 March 2023
- Published by Springer Nature
- p. 404-413
Analysing and Modeling Customer Success in Digital Marketing