Building Context-Aware Recommendation Systems: A Software Engineering Point of View

Inzunza, Sergio; Juárez‐Ramírez, Reyes

doi:10.1109/conisoft.2016.34

Cited by 1 publication

(1 citation statement)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recommender systems are a kind of information filtering systems that aim to make sensible recommen-item. These systems use user rating or item interactions, context in which ratings/interactions were produced, user's aspects and context at request time to make predictions [11,12]. Knowledge-based Recommendation Systems use knowledge about users and products, and analyze which products satisfy the user's requirements [7].…”

Section: Introductionmentioning

confidence: 99%

Evolutionary neural networks for improving the prediction performance of recommender systems

Seref¹,

Bostancı²,

Güzel³

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Recommender systems provide recommendations to users using background data such as ratings of users about items and features of items. These systems are used in several areas such as e-commerce, news websites and article websites. By using recommender systems, customers are provided with relevant data as soon as possible and are able to make good decisions. There are more studies about recommender systems and improving performance of them. In this study, prediction performances of neural networks were evaluated and their performances were improved using genetic algorithms. Performance of this study was compared with other studies, after that, superiority of this study was shown. While multilayer perceptron, generalized feed-forward network and CANFIS (Coactive Neuro Fuzzy Inference Systems) were used as a neural network algorithms, Movielens 100K and Movielens 1M datasets which are preferred in recommender systems studies mostly were used to train and test the system. Mean square error and root mean square error were employed as performance metrics. As a result, it was observed that genetic algorithm improves performance of neural networks and prediction performance of hybrid combination of neural networks and genetic algorithm is superior to prediction performance of recommender systems available in the literature.

show abstract

Section: Introductionmentioning

confidence: 99%