Item-based Recommendation Algorithm Research Articles

A Study on the Integrated Development of Artificial Intelligence and Tourism from the Perspective of Smart Tourism

In order to provide better travel experience for users under smart tourism, a data model that can be used for tourism analysis which is constructed by combining big data, Hadoop and crawler technology. Then, we combine with Item-based recommendation algorithm and the technology collected by crawler technology based on this model. It can provide an example of the specific integration application of big data analysis model and tourism. The results showed that the analysis model can highly recommend scenic spots favored by tourists. So it can provide reference for the integration of ARTIFICIAL intelligence and tourism, as well as a concrete example for the integration of artificial intelligence and tourism in the future.

SVR-based collaborative filtering algorithm: From dense to sparse

Recommender systems have been very important components to prevent people from dwelling in the overwhelming information. In this paper we analyze the difference between item-based recommendation algorithms and SVR-based collaborative filtering algorithms, and it can be found that item-based method performs much better while the data is not sparse significantly, and SVR-based method performs better while the data is dense and small. On this premise we propose a method that can combine the advantages of these two methods by predicting a small part of ratings using SVR method firstly and then predicting the rest of ratings using the item-based algorithm, which can solve the problem of data sparsity to certain extend. Finally, we evaluate our results compared with the benchmark on different datasets and prove our method’s advantages.

A study on collaborative recommender system using fuzzy-multicriteria approaches

In collaborative recommender systems, the overall ratings on items do not provide more detail about the reason behind the user's preferences. The multicriteria ratings give details about the user's preferences in multiple aspects and provide an opportunity to compute accurate recommendations. The user ratings collected by these systems are usually subjective, imprecise and vague, because it is based on user's perceptions and opinions. Fuzzy sets are an appropriate paradigm to handle the uncertainty and fuzziness of human behaviour. Because of these reasons, we propose a collaborative recommendation approach that uses the fuzzy linguistic approach to represent multicriteria user-item preference ratings, then finds similarities using fuzzy user-based and fuzzy item-based similarity measures and computes recommendations using fuzzy aggregation-based approach. The proposed approach's performance is evaluated empirically against traditional user-based and item-based recommendation algorithms using a music recommender system developed for this research. From the evaluation results, it is observed that the proposed approach shows improvement in recommendations than the traditional algorithms.