Online ISSN: 2515-8260

Keywords : collaborative filtering

Mechanism For Recommending Web Series

Dr.M.Rajaiah, Mr.A.Venkateswarlu,Mr.T.Sai Sudeep, Mr.T.Harish, Mr.S.Sumanth, Mr.Sk.Wahed Ali .

European Journal of Molecular & Clinical Medicine, 2023, Volume 10, Issue 2, Pages 703-719

Many businesses today aim to provide useful product suggestions to online users in order to increase their consumption on websites. People usually choose or buy a new product based on the recommendations of friends, comparisons of similar products, or feedback from other users. A recommender system must be implemented in order for all of these tasks to be completed automatically. Recommender systems are tools that provide suggestions that best suit the client's needs, even if the client is unaware of it.Personalized content offers are based on past behaviour, and they entice customers to return to the website. A web series recommendation mechanism for Netflix/Prime/Disney plus Hotstar will be built in this paper. The dataset used in this study contains over 5 K web series and 500 K+ customers. Popularity, Collaborative Filtering, Content-based Filtering, and Hybrid Approaches are the four main types of recommender algorithms. This paper will introduce all of them. We will choose the algorithms that best fit the data, implement them, and compare them


Jaichandran R; Leelavathy S; Kanaga Suba Raja; Pranav Kumar; Sailendra Kumar Majhi; Vikas Singh Thakur

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2800-2807

In this competitive era, getting right education and right job is always a challenge. Organization who are in need of skilled people in certain departments also find it difficult to identify right candidate with good talented skill set. In the proposed system, we propose 2 logins namely job seeker and employer. The proposed system tries to make the recruitment process simpler and efficient by integrating text mining and natural language processing techniques. The proposed architecture consists of unique and essential features like study materials, de-duplication process, resume analysis and weightage analysis. The employer can upload study materials while posting the job requirement so that the job seeker will have a fair knowledge of the exact job role. The recommendation of exact profile based on the skill required is processed using collaborative filtering algorithm. To optimize the cloud storage we have integrated de-duplication technique to eliminate saving same resume n number of times which would increase encryption cost and storage. The de-duplicaton process is performed using Proactive Replica Checking approach (PRCR). Also applying natural processing techniques in both job seeker and employer side provides efficient results saving much of time. In the employer side, we use web crawler to extract job description and requirements. In the job seeker side, once the resume is posted, stop word filtering and text segmentation is performed. After text segmentation, the scoring is provide based on the education, work experience, skills, personality traits and frequency of degree. Finally our proposed system provides a recommendation system for the upcoming generation in which degree of education major job requirements are coming.

Web based Tender Bid Analysis and Recommendation System using Collaborative Filtering

Jaichandran R; Muthuselvan S; Usha Kiruthika; Raja prakash S; Veda Priyan; Mathi B

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 3031-3038

Now a days all government projects, infrastructure enhancement are provided to individuals through tender system. But in the exiting approach, there is no transparency and government officials intervention is there, because of this the right vendor might be missed to get the order as there is lack of transparency. To address this issue, a web based tender analysis and recommendation system is proposed system using collaborative filtering. Proposed method selects the best bid provided by the vendors for a respective tender. It also provides transparency and enhances opportunity for new vendors to participate in bid. For experimental results, we used java for this web based tender analysis and recommendation system. Promising results obtained by continuously refining the trained model utilizing new goals information, scope of type of tenders and anticipating whether any activity is specified. The proposed system saves time of processing, easy decision making, reduces tender costs for governments and motivates new players to participate and perform the bid.