Mustansar Ali Ghazanfar

Kernel-Mapping Recommender system algorithms

Recommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given item. In this paper, we propose a new algorithm that we call the Kernel-Mapping Recommender (KMR), which uses a novel structure learning technique. This paper makes the following contributions: we show how (1) user-based and item-based versions of the KMR algorithm can be built; (2) user-based and item-based versions can be combined; (3) more information-features, genre, etc.-can be employed using kernels and how this affects the final results; and (4) to make reliable recommendations under sparse, cold-start, and long tail scenarios. By extensive experimental results on five different datasets, we show that the proposed algorithms outperform or give comparable results to other state-of-the-art algorithms.

Incremental Kernel Mapping Algorithms for Scalable Recommender Systems

Recommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given item. Kernel Mapping Recommender (KMR) system algorithms have been proposed, which offer state-of-the-art performance. One potential drawback of the KMR algorithms is that the training is done in one step and hence they cannot accommodate the incremental update with the arrival of new data making them unsuitable for the dynamic environments. From this line of research, we propose a new heuristic, which can build the model incrementally without retraining the whole model from scratch when new data (item or user) are added to the recommender system dataset. Furthermore, we proposed a novel perceptron-type algorithm, which is a fast incremental algorithm for building the model that maintains a good level of accuracy and scales well with the data. We show empirically over two datasets that the proposed algorithms give quite accurate results while providing significant computation savings.