Recommender systems (RS) are information filtering approaches that intend to foresee the rating for customers and products, mainly from big data for recommending their likes. Movie RS offers a process of assisting customers in the classification of customers with identical preferences. It makes the RS an essential part of websites and e-commerce applications. Many of the classical RS lack accuracy in the case where data utilized in the recommendation task is sparse. This paper aims to develop a movie RS by the use of density based clustering (DBC) with artificial flora (AF) called DBC-AF technique. Besides, to get rid of the sparsity problem, the content-boosted collaborative filtering technique is employed to the proposed DBC-AF based movie RS. The presented model considers the content information of the movies while computing the item similarities. The proposed DBC-AF technique improved the movie prediction accuracy and developed an integrated model combining the customer rating from Movie Lens dataset for the prediction process. The effective performance of the DBC-AF model has been evaluated utilizing the Movie lens dataset. The obtained simulation outcome indicated the effective performance of the presented DBC-AF model.

推荐系统（RS）是一种信息过滤方法，旨在预测客户和产品的评级，主要来自大数据以推荐他们的喜好。Movie RS 提供了帮助客户对具有相同偏好的客户进行分类的过程。它使 RS 成为网站和电子商务应用程序的重要组成部分。在推荐任务中使用的数据稀疏的情况下，许多经典 RS 缺乏准确性。本文旨在通过使用基于密度的聚类 (DBC) 和人工植物群 (AF) 来开发电影 RS，称为 DBC-AF 技术。此外，为了摆脱稀疏性问题，内容增强的协同过滤技术被用于提出的基于 DBC-AF 的电影 RS。所提出的模型在计算项目相似度的同时考虑了电影的内容信息。提出的 DBC-AF 技术提高了电影预测的准确性，并开发了一个结合来自 Movie Lens 数据集的客户评分的集成模型，用于预测过程。DBC-AF 模型的有效性能已经利用电影镜头数据集进行了评估。获得的模拟结果表明了所提出的 DBC-AF 模型的有效性能。