Titulo Estágio
Household Identification using Call Records
Áreas de especialidade
Sistemas Inteligentes
Sistemas Inteligentes
Local do Estágio
CISUC
Enquadramento
When making a phone call, telecommunication companies have Call Detail Records (CDRs), which contain information about the success of the call, as well as duration, caller and receiver. This information is typically stored for all calls made, and in recent years, companies have started to use data science and machine learning techniques to improve the quality of the service provided.
One question that is still open is concerned with how we can identify households, using the CDRs. Identifying family relationships between users is important, since it allows for a better identification of telecommunication products that can be offered to clients [1,2].
1 - Wu, X. (2016, August). Study on call detail records of family members based on classification model. In 2016 International Conference on Economics, Social Science, Arts, Education and Management Engineering. Atlantis Press.
2 - Vanhoof, M., Reis, F., Smoreda, Z., & Ploetz, T. (2018). Detecting home locations from CDR data: introducing spatial uncertainty to the state-of-the-art. arXiv preprint arXiv:1808.06398.
Objetivo
The main goal of this work is to design, implement and validate data science and machine learning models to household identification.
Plano de Trabalhos - Semestre 1
1 - Review of literature.
2 - Requirements and Use Case Definition
3 - Exploratory Data Analysis
4 - Framework Design
5 - Writing of the intermediate report
Plano de Trabalhos - Semestre 2
6 - Framework Implementation
7 - Analysis of the results
8 - Framework Refinement
9 - Validation of the results
10 - Scientific Article with the main results
11 - Writing of the thesis
Condições
This work will be conducted within an industry research project between CISUC and Altice Labs. The work is to be conducted at the ECOS laboratories of CISUC. A workplace will be provided as well as the required computational resources.
There is a possibility of the student being awarded a scholarship (Bolsa de Investigação para Licenciado) for at least 6 months. The scholarship will follow the Fundação para a Ciência e Tecnologia (FCT) monthly stipend guidelines.
Observações
N/A
Orientador
Nuno Lourenço / Penousal Machado
naml@dei.uc.pt 📩