Issuu

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 05 | May 2024

www.irjet.net

p-ISSN: 2395-0072

CineGenius - A Movie Web Based Project with Advance (Recommendation Algorithm) Rajiv Kumar Nath, Shivansh Pandey, Shubham Shekhar, Suryansh Sharma Associate Professor, Department of Computer Science and Engineering, Galgotias College of Engineering and Technology, Greater noida, Uttar Pradesh, India, Department of Computer Science and Engineering, Galgotias College of Engineering and Technology, Greater noida,Uttar Pradesh, India, Department of Computer Science and Engineering, Galgotias College of Engineering and Technology, Greater noida, Uttar Pradesh, India, Department of Computer Science and Engineering, Galgotias College of Engineering and Technology, Greater noida, Uttar Pradesh, India -------------------------------------------------------------------------***--------------------------------------------------------------------. its variety, volume, velocity, veracity, and value, has Abstract — CINEGENIOUS The field of Recommendation Systems is widely acknowledged and highly valuable in assisting individuals in making well-informed decisions. This approach helps users in identifying pertinent information from a vast pool of available data. Specifically, in the domain of Movie Recommendation Systems, recommendations are generated by evaluating the similarity between users (Collaborative Filtering) or by considering a specific user's preferences and activities (Content Based Filtering).To overcome the shortcomings of both collaborative filtering and content based filtering, a mix of the two is often used to build a better recommendation system. Moreover, various measures of similarity are employed to ascertain the likeness between users for the purpose of recommendation. This research paper presents a comprehensive survey of cutting-edge techniques in Content Based Filtering, Collaborative Filtering, Hybrid Approaches, and Deep Learning Based Methods for movie recommendation. Additionally, different measures of similarity are thoroughly examined. Prominent companies such as KEYWORDS: Collaborative filtering, User preferences learning, Predictive modeling, Content-based filtering, Hybrid recommendation system, Preference modeling. Facebook, LinkedIn, Pandora, Netflix, and Amazon employ recommendation systems to enhance their profitability and provide value to their customers. The main objective of this paper is to offer a concise overview of the diverse techniques and methodologies employed in movie recommendation, with the intention of fostering further exploration and research in the field of recommendation systems.

INTRODUCTION

Recommendation systems serve as techniques and methods to offer personalized recommendations to users. These recommendations cover a wide range of domains, including fashion, news, education, smartphones, movies, banking, and tourism.[1]. By taking into account contextual information, these systems generate recommendations based on user interests. The exponential growth of data, characterized by

Impact Factor value: 8.226

brought about significant transformations in various aspects of daily life. This encompasses interactions with social networks, healthcare services, ecommerce, education, and energy, among others. In order to ensure that users obtain meaningful insights into their health, education, news, and environment, it is crucial to appropriately process this vast amount of data and provide them with relevant knowledge in a timely manner. However, accurately processing such data presents a major challenge that needs to be addressed in order to make it accessible to users. One potential solution to overcome this challenge is the utilization of recommender systems, which can effectively provide users with maximum and accurate information tailored to their personalized learning needs. Contextual information is one approach that can be effectively employed to generate substantial recommendations across different fields. Nevertheless, certain issues, such as information overload, redundancy in context, and redundancy in data, must be resolved to enhance the effectiveness of recommendation systems. Furthermore, it is important to acknowledge that the user-generated data holds value and is vulnerable to phishing attacks. While there have been numerous research efforts focused on developing privacy-preserving recommendation systems, many of these studies have overlooked the crucial aspects of privacy and security. Instead, they have primarily concentrated on optimizing accuracy and scalability through algorithm development. 2.

LITERATURE SURVEY

The foundation for many of the present-day recommender systems was established during the 1990s.[2]. An experimental email system known as Tapestry introduced the concept of "Collaborative Filtering" by enabling users to create email filtering

ISO 9001:2008 Certified Journal

Page 1907