Call us Today ! +918886268863 | [email protected]

Deploying Different Clustering Techniques on aCollaborative-based Movie Recommender

Deploying Different Clustering Techniques on aCollaborative-based Movie Recommender

Introduction:

Recommendation systems are involved in many industries, for example (e-health, transportation, e-commerce, and agriculture), where Recommendation systems aim to benefit both market and user levels. They help consumers make the right decision based on their preferences without being exposed to data overload. Nowadays, there is a wide range of recommenders based on different filtering approaches, such as Collaborative-based, Content-based, hybrid-based, demographic-based filtering approaches.

Abstract:

In this paper, we present clustering-based recommendation systems. We also experiment and show the results for a collaborative-based movie recommender using different clustering techniques such as Kmeans, BIRCH Balanced Iterative Reducing and Clustering using Hierarchies) and DBSCAN (Density-based Spatial Clustering of Applications with Noise). We intended to choose different clustering approaches such as partitional, hierarchical, and density-based clustering approaches. We incorporated Item-based Collaborative filtering, then applied multiple clustering techniques on the dataset based on the users’ ratings. We checked the performance using accuracy measures such as MAE (Mean Absolute Error), RMSE (Root mean square error), and the computed time. These measures were calculated for analysis and comparison purposes.

Existing work:

A Content-based filtering system [8] uses the information/content of the items/ratings to build the needed algorithm. It recommends items/products based on the users’ history of interaction, ratings, decisions, and preferences.

Content-based filtering systems are used in domains related to movies and education recommendations. Various research work is introduced to incorporate clustering-based recommenders to increase accuracy and solve problems like data scalability and sparsity. In [34], [35], the authors proposed a new recommender system based on clustering to recommend movies to the user level. In [33] a collaborative filtering system was used along with K-means (KM) to introduce the MOVREC recommendation system, considering each user’s previous rating. In [36], the authors proposed different recommenders to classify the movies by their rates. Recommendation systems face some challenges, where some of those raised challenges are data scalability, data sparsity,and cold start.

Disadvantage:

One of the main disadvantages of using a content-based filtering system is that it needs users’ history to build an accurate model. It also does not perform well in sparse data.

Proposed work:

We present clustering-based recommendation systems. We also experiment and show the results for a collaborative-based movie recommender using different clustering techniques such as Kmeans, BIRCH Balanced Iterative Reducing and Clustering using Hierarchies) and DBSCAN (Density-based Spatial Clustering of Applications with Noise). We intended to choose different clustering approaches such as partitional, hierarchical, and density-based clustering approaches. We incorporated Item-based Collaborative filtering, then applied multiple clustering techniques on the dataset based on the users’ ratings.

Advantage:

K-means clustering combined with item-based collaborative filtering outperformed the other clustering algorithms measured by the MAE, RMSE, and computational time.

Algorithms:Kmeans, BIRCH Balanced Iterative Reducing and Clustering using Hierarchies) and DBSCAN (Density-based Spatial Clustering of Applications with Noise).

System requirements:

  Software requirements:

Hardware components:

System                   :   Pentium IV 2.4 GHz or intel

Hard Disk              :   40 GB.

Floppy Drive         :   1.44 Mb.

Mouse                    :   Optical Mouse.

Ram                       :   512 Mb.

Conclusion:

In this paper, we compared various clustering algorithms in combination with collaborative filtering to achieve better accuracy and reduce sparsity. We experimented (K-means, BIRCH, and DBs Ca N). We have implemented many iterations and evaluated the predicted recommendations for each clustering algorithm. Experimental results show that the k-means clustering combined with item-based collaborative filtering outperformed the other clustering algorithms measured by the MAE, RMSE, and computational time. Future directions include adopting additional quality measures as the MAE/RMSE metrics measure the performance offline. We will also include other clustering techniques to check the recommendation system’s performance using a broader scope of various clustering algorithms.

March 14, 2022

0 responses on "<strong>Deploying Different Clustering Techniques on aCollaborative-based Movie Recommender</strong>"

Leave a Message

Template Design © VibeThemes. All rights reserved.