Back to publications

A visualization methodology for association rules through an intermediate representation

Fernandez-Basso, Carlos and Ruiz, M.D. and Molina-Solana, Miguel and Martin-Bautista, M.J.
Expert Systems with Applications , under review, pp. (SUBMITTED)

Abstract:

Discovering new trends and co-occurrences in massive data is a key step when analysing social media, data coming from sensors, etc. Although, nowadays Data Mining techniques are very useful and widely used in industry, business and government, the main limitation of applying Machine Learning or Data Mining algorithms in other fields is the interpretability and complexity of obtained results for non-expert users in Computer or Data Science. For this reason, one of the most important phases in the knowledge discovery process is the interpretation and evaluation of results. In the case of association rules it is essential that results are interpretable by endusers. One of the most useful tools to achieve this goal is visualization, because it can help with the interpretation of results, being easier to understand and analyze them in order to explain the behaviour of data or to make a decision in a posteriori step.

Links:

DOI:
PDF:

Bibtex:

@article{Fernandez2019b,
  author = {Fernandez-Basso, Carlos and Ruiz, M.D. and Molina-Solana, Miguel and Martin-Bautista, M.J.},
  title = {A visualization methodology for association rules through an intermediate representation},
  journal = {Expert Systems with Applications},
  year = {SUBMITTED},
  volume = {under review},
  doi = {},
  comment = {},
  timestamp = {24}
}