Explanations by Counterfactual Argument in Recommendation Systems

dc.accession.numberT01132
dc.classification.ddc006.31 PAT
dc.contributor.advisorRana, Arpit
dc.contributor.authorPathak, Yash
dc.date.accessioned2024-08-22T05:21:22Z
dc.date.accessioned2025-06-28T10:27:15Z
dc.date.available2024-08-22T05:21:22Z
dc.date.issued2023
dc.degreeM. Tech
dc.description.abstractIn recent advances in the domains of Artificial Intelligence (AI) and MachineLearning (ML), complex models are used. Due to their complexity and approaches,they have black box type of nature and raise the question of a trustworthy for decisionprocess especially in the high cost decisions scenario. To overcome thisproblem, users of these systems can ask for an explanation about the decisionwhich can be provided by system in various ways. One way of generating theseexplanations is by the help of Counterfactual (CF) arguments. Although there is adebate on how AI can generate these explanations, either by Correlation or CausalInference, in Recommendation Systems (RecSys) the aim is to generate these explanationswith minimum Oracle calls and have near optimal length (eg., in termsof interactions) of provided explanations. In this study we analyze the nature ofCFs and different methods (eg., Model Agnostic approach, Genetic Algorithms(GA)) to generate them along with the quality measures. Extensive experimentsshow that the generation of CFs can be done through multiple approaches andselecting optimal CFs will improve the explanations.
dc.identifier.citationPathak, Yash (2023). Explanations by Counterfactual Argument in Recommendation Systems. Dhirubhai Ambani Institute of Information and Communication Technology. vii, 43 p. (Acc. # T01132).
dc.identifier.urihttp://drsr.daiict.ac.in/handle/123456789/1191
dc.publisherDhirubhai Ambani Institute of Information and Communication Technology
dc.student.id202111053
dc.subjectRecommendation Systems
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subjectCounterfactual (CF) arguments
dc.titleExplanations by Counterfactual Argument in Recommendation Systems
dc.typeDissertation

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
202111053.pdf
Size:
653.61 KB
Format:
Adobe Portable Document Format