Skip to content

Latest commit

 

History

History
72 lines (47 loc) · 5.58 KB

File metadata and controls

72 lines (47 loc) · 5.58 KB

Predicting missing pairwise preferences in GDM

Python code for a project focusing on "Group Recommendation Systems (GRS)" and "Group Decision Making," aimed at predicting missing pairwise preference data. "Predicting missing pairwise preferences from similarity features in group decision making (Knowledge-Based-Systems 2022)"

Project Description

In group decision-making (GDM), fuzzy preference relations (FPRs) refer to pairwise preferences in the form of a matrix. Within the field of GDM, the problem of estimating missing values is of utmost importance, since many experts provide incomplete preferences. In this paper, we propose a new method called the entropy-based method for estimating the missing values in the FPR. We compared the accuracy of our algorithm for predicting the missing values with the best candidate algorithm from state of the art achievements. In the proposed entropy-based method, we took advantage of pairwise preferences to achieve good results by storing extra information compared to single rating scores, for example, a pairwise comparison of alternatives vs. the alternative’s score from one to five stars. The entropy-based method maps the prediction problem into a matrix factorization problem, and thus the solution for the matrix factorization can be expressed in the form of latent expert features and latent alternative features. Thus, the entropy-based method embeds alternatives and experts in the same latent feature space. By virtue of this embedding, another novelty of our approach is to use the similarity of experts, as well as the similarity between alternatives, to infer the missing values even when only minimal data are available for some alternatives from some experts. Note that current approaches may fail to provide any output in such cases. Apart from estimating missing values, another salient contribution of this paper is to use the proposed entropy-based method to rank the alternatives. It is worth mentioning that ranking alternatives have many possible applications in GDM, especially in group recommendation systems (GRS).

The logical diagram illustrating the process of the proposed method is as follows:

Execution Dependencies

The codes can be run directly. Also, the python code can be run by:

python ./GDM_EmtropyBPR_Roza.py

We are using pandas, numpy, scipy and warnings modules. Install them by running.

pip install numpy
pip install pandas
pip install matplotlib.pyplot

The hyperparameters for matrix factorization, group sizes and no. of generated groups can be changed through the config file.

Dataset

  • Car dataset: The dataset comprises car preferences that were provided by Abbasnejad et al. in 2013. The dataset was gathered from 60 users residing in the United States, who participated in the data collection process through Amazon's Mechanical Turk. The dataset focuses on ten distinct cars, treated as individual items for comparison purposes. Each user in the dataset provided responses for all 45 possible pairs of items, resulting in a total of 90 observations for each expert. In addition to the pairwise preference scores, the dataset also includes two additional files containing users' attributes (education, age, gender, and region) and car attributes (body type, transmission, engine capacity, and fuel consumed). However, in our project, neither the users' attributes nor the cars' attributes were used during the training of the model.
  • Food dataset: The paper utilizes a food dataset from an online experiment, Consens@OsloMet, conducted at Oslo Metropolitan University (Norway), focusing on group decision making regarding food preferences. Participants were organized into groups of five and tasked with updating or maintaining their food choices based on the group's average opinion. The experiment, registered and approved by the Norwegian Centre for Research Data, involved an online interface where experts provided pairwise scores for different food pairs. The front-end interface displayed a probability score indicating their preferences. The collected data, representing preferences in matrices, enabled the study of consensus-building within groups. The paper's methodology and experimental design are detailed in the source, aiming to predict missing pairwise preferences in group decision making.

License

MIT License


Reference

If you use this code/paper, please cite it as below.

@article{abolghasemi2022predicting,
  title={Predicting missing pairwise preferences from similarity features in group decision making},
  author={Abolghasemi, Roza and Khadka, Rabindra and Lind, Pedro G and Engelstad, Paal and Viedma, Enrique Herrera and Yazidi, Anis},
  journal={Knowledge-Based Systems},
  volume={256},
  pages={109860},
  year={2022},
  publisher={Elsevier}
}