Datenschutzerklärung|Data Privacy
Impressum

02.11.2021
Martin Pagel

Mo 08.11.2021, 2 pm, Virtual Event: Incorporating External Data in Recommender Systems (Evgeniya Sokolova)

DIMA/IAM presentation: "Incorporating External Data in Recommender Systems" by Evgeniya Sokolova

Abstract:
Classic collaborative filtering approaches suffer from the cold-start problem, in case not enough ratings for the corresponding user or item are provided.
On the other hand, content-based approaches are less prone to such problem.
The presented approach proposes a meta-model for movie recommendation utilizing user and item features as well as collaborative filtering features.
This allows to significantly alleviate the cold-start problem, surpassing the results of classic approaches by a wide margin in terms of RMSE and MAE.

Bio:
Evgeniya Sokolova, MSc Applied Mathematics and Informatics (Moscow Institute of Physics and Technology).

Log-in information:
If you are interested in attending the event, please contact web@bifold.berlin!