Sequential Recommendation Model Based on User’s Long and Short Term Preference

Abstract

Aiming at the problem that the existing sequence recommendation model ignores the personalized behavior of different users,the model cannot fully capture the interest drift caused by users’ dynamic preferences,a sequence recommendation model based on users’ long and short term preferences(ULSP-SRM)is proposed.Firstly,the dynamic category embedding of the user is generated according to the category and time information of the interactive items in the user’s sequence,thereby effectively establishing the correlation between the items and reducing the sparsity of the data.Secondly,according to the time interval information of the user’s current clicked item and the last clicked item,a personalized time series position embedding matrix is generated to simulate the user’s personalized aggregation phenomenon and better reflect the dynamic change of user preference.Then,the user’s long-term preference sequence fused with the personalized time-series position embedding matrix is input into the gated recurrent unit in units of sessions to generate the user’s long-term preference representation,and the user’s long and short term preferences are fused through the attention mechanism to generate the final preference representation of the user,to achieve the purpose of fully capturing the user’s preference.Finally,the final user preference representation is input to the recommendation prediction layer for the next recommendation prediction.Experiments are carried out on seven subsets of Amazon public data set,and the area under curve(AUC ),recall rate and precision rate indicators are used for comprehensive evaluation.Experimental results show that the proposed model outperforms other advanced benchmark models,effectively improving recommended perfor-mance.

Keywords

• sequence recommendation|long and short term preference|personalized time series location|interest in the drift|attention mechanism