In the name of Allah the Merciful 232156039370 ALBAHA UNIVERSITY FACULTY OF COMPUTER SCIENCE AND INFORMATION TECHNOLOGY DEPARTMENT
In the name of Allah the Merciful
FACULTY OF COMPUTER SCIENCE AND INFORMATION TECHNOLOGY DEPARTMENT, ALBAHA
“Recommendation Systems (RS) “Submitted the seminar in the partial fulfillment of requirements
for award of the Degree of Bachelor Computer Science 2017
Name : Batool Ateah AlzahraniGroup: 71
Under the Supervision of
Dr. Ali Saeed.
AlBaha University, AlBaha.
2.Collaborative filtering (CF) 5
2.1.Correlation-Based Similarity. 6
2.2Memory-based CF algorithms 7
2.3Model- based CF 7
3.Content-Based Recommendation 8
4.Knowledge-based recommender systems 9
Figure Or Table Index page
1.Fig : 1 Diagram of Recommendation Systems 4
2.Fig : 2 Type Collaborative filtering 8
3.Fig : 3 Diagram of Content-Based 13
4. Fig : 4 Diagram of Knowledge-based 14
1.INTRODUCTIONIn everyday life, people rely on recommendations from other people by spoken words, reference letters, news reports from news media, general surveys, travel guides, and so forth. Recommender systems assist and augment this natural social process to help people sift through available books, articles, webpages, movies, music, restaurants, jokes, grocery products, and so forth to find the most interesting and valuable information for them.
12714306741918Fig : 1 Diagram of Recommendation Systems
00Fig : 1 Diagram of Recommendation Systems
0293730400Most recommendation algorithms start by finding a set of customers whose purchased and rated items overlap the user’s purchased and rated items.2 The algorithm aggregates items from these similar customers, eliminates items the user has already purchased or rated, and recommends the remaining items to the user. Two popular versions of these algorithms are collaborative filtering and cluster models. Other algorithms — including search-based methods and our own item-to-item collaborative filtering — focus on finding similar items, not similar customers. For each of the user’s purchased and rated items, the algorithm attempts to find similar items. It then aggregates the simi- lar items and recommends them.
2.Collaborative filtering (CF)
is one of the most successful rec- ommender techniques. Broadly, there are memory-based CF techniques such as the neighborhood-based CF algorithm; model-based CF techniques such as Bayesian belief nets CF algorithms, clustering CF algorithms, and MDP-based CF algorithms; and hybrid CF techniques such as the content- boosted CF algorithm and Personality diagnosis.
As a representative memory-based CF technique, neigh- borhood-based CF computes similarity between users or items, and then use the weighted sum of ratings or simple weighted average to make predictions based on the similarity values. Pearson correlation and vector cosine similarity are commonly used similarity calculations, which are usually conducted between co-rated items by a certain user or both users that have co-rated a certain item. To make top- N recommendations, neighborhood-based methods can be used according to the similarity values.
1077595174747Fig : 2 Diagram of Type Collaborative filtering
00Fig : 2 Diagram of Type Collaborative filtering
In this case, similarity wu,v between two users u and v, or wi,j between two items i and j, is measured by computing the Pearson correlation or other correlation-based similarities.
Pearson correlation measures the extent to which two variables linearly relate with each other 5. For the user- based algorithm, the Pearson correlation between users u and v is where the i ? I summations are over the items that both the users u and v have rated and ru is the average rating of the co-rated items of the uth user.
Usually the number of users in the computation of similarity is regarded as the neighborhood size of the active user, and similarity based CF is deemed as neighborhood- based CF.
37443977089000To make a prediction for the active user, a, on a certain item, i, we can take a weighted average of all the ratings on that item according to the following formula 5:
Note the prediction is based on the neighborhood of the active users.
2.2Memory-based CF algorithms
0201301100are easy to implement and have good perfor- mances for dense datasets. Shortcomings of memory-based CF algorithms include their dependence on user ratings, decreased performance when data are sparse, new users and items problems, and limited scalability for large datasets, and so forth 11, 42, 133. Memory-based CF on imputed rating data and on dimensionality-reduced rating data will produce more accurate predictions than on the original sparse rating data 24, 25, 37.
12941303429222Fig : 2 Diagram of Memory-based CF
00Fig : 2 Diagram of Memory-based CF
2.3Model- based CF
Is Model-based CF techniques need to train algorithmic models, such as Bayesian belief nets, clustering techniques, or MDP-based ones to make predictions for CF tasks. Advanced Bayesian belief nets CF algorithms with the ability to deal with missing data are found to have better performance than simple Bayesian CF models and Pearson correlation-based algorithms 11. Clustering CF algorithms make recommen- dations within small clusters rather than the whole dataset, and achieve better scalability. An MDP-based CF algorithm incorporates the users’ action of taking the recommendation or not into the model, and the optimal solution to the MDP is to maximize the function of its reward stream. The MDP-based CF algorithm brings profits to the customized system deploying it. There are downsides of model-based CF techniques, for example, they may not be practical when the data are extremely sparse, the solutions using dimensionality reduction or transformation of multiclass data into binary ones may decrease their recommendation performance, the model-building expense may be high, and there is a tradeoff between prediction performance and scalability for many algorithms.
Besides addressing the above challenges, future CF techniques should also be able to make accurate predictions in the presence of shilling attacks and noisy data, and be effectively applied in fast-growing mobile applications as well.
There are many evaluation metrics for CF techniques. The most commonly used metric for prediction accuracy include mean absolute error (MAE), recall and precision, and ROC sensitivity. Because artificial data are usually not reliable due to the characteristics of CF tasks, real-world datasets from live experiments are more desirable for CF research.
-2764473480435Fig : 3 Diagram of Content-Based
00Fig : 3 Diagram of Content-Based
A content-based approach provides recommendations by com- paring representations of content contained in an item with rep- resentations of content that the user is interested in. In this ap- proach, a model of user ratings is first developed. Algorithms in this category use probabilities and envision the collaborative filter- ing process by computing the expected value of a user prediction given the user’s ratings on other items. The model building pro- cess is performed by three different machine learning algorithms: (1) Bayesian network 5, (2) clustering 3, 5, and (3) rule-based models 35.
The systems described in Section 2.3.1 only provide recommen- dations based on collaborative filtering. However, some systems provide better recommendations by combining collaborative filter- ing with content information. Fab 2 uses relevance feedback to simultaneously construct a personal filter along with a communal “topic” filter. Web pages are initially ranked by the topic filter and then sent to user’s personal filters. The user then provides rele- vance feedback for that Web page, and this feedback is used to modify both the personal filter and the originating topic filter. Basu et al. 3 integrate content and collaboration in a framework where they treat recommendation as a classification task. Melville et al. 29 overcome drawbacks of collaborative filtering systems in their recommender system by exploiting content information of items already rated. In recent study on recommender systems, Schafer et al. 36 introduce a new class of recommender system that pro- vides users with personalized control over the generation of a single recommendation list formed from a combination of rich data using multiple information resources and recommendation techniques.
4.Knowledge-based recommender systems
Knowledge-based recommender systems perform a needed function in a world of ever-expanding information resources. Unlike other recommender systems, they do not depend on large bodies of statistical data about particular rated items or particular users. Our experience has shown that the knowledge component of these systems need not be prohibitively large, since we need only enough knowledge to judge items as similar to each other.
Further, knowledge-based recommender systems actually help users explore and thereby understand an information space. Users are an integral part of the knowledge discovery process, elaborating their information needs in the course of interacting with the system. One need only have general knowledge about the set of items and only an informal knowledge of one’s needs; the system knows about the tradeoffs, category boundaries, and useful search strategies in the domain.
Knowledge-based recommender systems are strongly complementary to other types of recommender systems. We have shown one way that a hybrid knowledge- based/collaborative system might be successfully constructed, but this is a fertile research area with much room for future experimentation.
2171472673350016277414103278Fig : 4 Diagram of Knowledge-based
00Fig : 4 Diagram of Knowledge-based