TY - GEN
T1 - Just in time
T2 - 35th IEEE International Conference on Data Engineering, ICDE 2019
AU - Boer, Naama
AU - Deutch, Daniel
AU - Frost, Nave
AU - Milo, Tova
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/4
Y1 - 2019/4
N2 - The interpretability of complex Machine Learning models is coming to be a critical social concern, as they are increasingly used in human-related decision-making processes such as resume filtering or loan applications. Individuals receiving an undesired classification are likely to call for an explanation - preferably one that specifies what they should do in order to alter that decision when they reapply in the future. Existing work focuses on a single ML model and a single point in time, whereas in practice, both models and data evolve over time: an explanation for an application rejection in 2018 may be irrelevant in 2019 since in the meantime both the model and the applicant's data can change. To this end, we propose a novel framework that provides users with insights and plans for changing their classification in particular future time points. The solution is based on combining state-of-the-art algorithms for (single) model explanations, ones for predicting future models, and database-style querying of the obtained explanations. We propose to demonstrate the usefulness of our solution in the context of loan applications, and interactively engage the audience in computing and viewing suggestions tailored for applicants based on their unique characteristic.
AB - The interpretability of complex Machine Learning models is coming to be a critical social concern, as they are increasingly used in human-related decision-making processes such as resume filtering or loan applications. Individuals receiving an undesired classification are likely to call for an explanation - preferably one that specifies what they should do in order to alter that decision when they reapply in the future. Existing work focuses on a single ML model and a single point in time, whereas in practice, both models and data evolve over time: an explanation for an application rejection in 2018 may be irrelevant in 2019 since in the meantime both the model and the applicant's data can change. To this end, we propose a novel framework that provides users with insights and plans for changing their classification in particular future time points. The solution is based on combining state-of-the-art algorithms for (single) model explanations, ones for predicting future models, and database-style querying of the obtained explanations. We propose to demonstrate the usefulness of our solution in the context of loan applications, and interactively engage the audience in computing and viewing suggestions tailored for applicants based on their unique characteristic.
KW - Accountability
KW - Interpretability
KW - Temporal
UR - http://www.scopus.com/inward/record.url?scp=85067942902&partnerID=8YFLogxK
U2 - 10.1109/ICDE.2019.00221
DO - 10.1109/ICDE.2019.00221
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85067942902
T3 - Proceedings - International Conference on Data Engineering
SP - 1988
EP - 1991
BT - Proceedings - 2019 IEEE 35th International Conference on Data Engineering, ICDE 2019
PB - IEEE Computer Society
Y2 - 8 April 2019 through 11 April 2019
ER -