An optimally weighted user- and item-based collaborative filtering approach to predicting baseline data for Friedreich’s Ataxia patients

In this paper, a modified collaborative filtering (MCF) algorithm with improved performance is developed for recommendation systems application in predicting baseline data of Friedreich’s Ataxia (FRDA) patients. The proposed MCF combines the individual merits both user-based (UBCF) method and item-based (IBCF) method, where positively negatively correlated neighbors are taken into account. weighting parameters introduced to quantify degrees utilizations UBCF IBCF methods rating prediction, particle swarm optimization applied optimize order achieve an adequate tradeoff between terms values. To demonstrate prediction algorithm, employed assist collection FRDA effectiveness confirmed by extensive experiments and, furthermore, it shown that our outperforms some conventional approaches.