METHOD OF FORMING RECOMMENDATIONS USING TEMPORAL CONSTRAINTS IN A SITUATION OF CYCLIC COLD START OF THE RECOMMENDER SYSTEM

The problem of the formation of the recommended list of items in the situation of cyclic cold start of the recommendation system is considered. This problem occurs when building recommendations for occasional users. The interests of such consumers change significantly over time. These users are considered “cold” when accessing the recommendation system. A method for building recommendations in a cyclical cold start situation using temporal constraints is proposed. Temporal constraints are formed on the basis of the selection of repetitive pairs of actions for choosing the same objects at a given level of time granulation. Input data is represented by a set of user choice records. For each entry, a time stamp is indicated. The method includes the phases of the formation of temporal constraints, the addition of source data using these constraints, as well as the formation of recommendations using the collaborative filtering algorithm. The proposed method makes it possible, with the help of temporal constraints, to improve the accuracy of recommendations for “cold” users with periodic changes in their interests.

[1]  Deng Cai,et al.  Addressing the Item Cold-Start Problem by Attribute-Driven Active Learning , 2018, IEEE Transactions on Knowledge and Data Engineering.

[2]  Viktor Levykin,et al.  Development of a method for the probabilistic inference of sequences of a business process activities to support the business process management , 2018, Eastern-European Journal of Enterprise Technologies.

[3]  Nipa Chowdhury,et al.  Self-training Temporal Dynamic Collaborative Filtering , 2014, PAKDD.

[4]  Jaap Kamps,et al.  The Continuous Cold-start Problem in e-Commerce Recommender Systems , 2015, CBRecSys@RecSys.

[5]  Serhii Chalyi,et al.  THE METHOD OF CONSTRUCTING RECOMMENDATIONS ONLINE ON THE TEMPORAL DYNAMICS OF USER INTERESTS USING MULTILAYER GRAPH , 2019, EUREKA: Physics and Engineering.

[6]  Sophie Ahrens,et al.  Recommender Systems , 2012 .

[7]  Francesco Ricci,et al.  A survey of active learning in collaborative filtering recommender systems , 2016, Comput. Sci. Rev..

[8]  Chalyi Sergii,et al.  Causality-based model checking in business process management tasks , 2018, 2018 IEEE 9th International Conference on Dependable Systems, Services and Technologies (DESSERT).

[9]  Matthias Braunhofer.  Hybrid Solution of the Cold-Start Problem in Context-Aware Recommender Systems , 2014, UMAP.

[10]  Yevgeniy V. Bodyanskiy,et al.  Implementation of search mechanism for implicit dependences in process mining , 2013, 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS).

[11]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[12]  Viktor Levykin,et al.  METHOD OF DETERMINING WEIGHTS OF TEMPORAL RULES IN MARKOV LOGIC NETWORK FOR BUILDING KNOWLEDGE BASE IN INFORMATION CONTROL SYSTEMS , 2018 .

[13]  Le Hoang Son.  Dealing with the new user cold-start problem in recommender systems: A comparative review , 2016, Inf. Syst..

[14]  Stathes Hadjiefthymiades,et al.  Facing the cold start problem in recommender systems , 2014, Expert Syst. Appl..

[15]  Bernd Ludwig,et al.  Matrix factorization techniques for context aware recommendation , 2011, RecSys '11.

[16]  Jimeng Sun,et al.  Temporal recommendation on graphs via long- and short-term preference fusion , 2010, KDD.