recommender systems are such kind of models that are made to give a user-friendly environment to the user. These models are widely used in every sector of the world. Many leading companies are putting effort to make these multi-criteria recommender models effective by introducing new techniques and approaches. In the past, people used to done the recommendation manually. For example, if someone wants to buy something, then they used to ask other people who have bought that particular thing or people who has some knowledge on that thing. To take this process genuine, automatic, and more efficient, the concept of recommender system came. The first recommender system was based on single criteria. That is known as single-criteria recommender system. But in real-world scenario for recommendation, a model needs to look at more than one criterion. So, the multi-criteria recommender concept came in the picture. In this chapter, we will dig into various types of multi-criteria recommender systems. Here, we will see some innovative ideas, approaches, and methods, which are applied to a multi-criteria recommender system more efficient and effective. We will see how these new and innovative approaches give better result compared to the conventional recommender systems. Here, we have talked about so many different approaches of multi-criteria recommendation techniques done by various researchers around the globe. All these researches are done with the real-world datasets to solve the practical problems. We have also chosen five most likely research activities and explained in details how they have conducted their research and got a successful outcome. But before we dive into the hardcore details, we will see that how a recommender system was made. We talked about the various filtering techniques and the core working principles of a recommender system. At the end of the chapter, we have also discussed about the advantages and disadvantages of the recommender systems. Recommender system helps a business to grow higher and higher and also helps to analyze the risks. For these reasons, multi-criteria recommender systems are trending in the market and got high demand.
Keywords: Clustering, entertainment, mean absolute error, multi-criteria, recommender system
3.1 Introduction
In today’s digital age, there is massive amount of information available over the internet; it provides the users with enormous amount of resources or services pertaining to any domain. As the information over the internet rises, the number of resources and options also tend to increase exponentially, causing information overload which eventually creates a lot of confusion among the clients, thus making the decision-making process strenuous [1].
Recommender systems are widely used in the decision-making process and deal with the information overload. Multi-criteria recommendation system is a type of recommender system that utilizes user’s rating and preference on several criteria to make the optimal decision for the respective client. It can thus make a personalized recommendation based on the user’s demands and choices. In this paper, we compare the performance of the recommendation system among three types of settings, first by using the ratings of all the criteria using the traditional approach, second by taking multiple-criteria preference as circumstance, and third by make use of chosen criteria ratings as circumstances. Thus, recommender system is a significant tool used in the decision-making process. It produces a recommendation list items to a client based on the client’s previous likings [28–31].
The importance of recommender systems has been increasing day by day especially for the business applications, as the use of recommender system proved to be quite successful in the ecommerce sector like amazon. Many business applications started incorporating it in variety of other sectors including movie and music recommendation, books and e-books, tourism industry, hotels, restaurant’s, news, etc. These systems assist the users in figuring out the most relevant information based on their needs instead of showing an indistinguishable amount of data that is irrelevant to the user. Hence, it is crucial for the recommender systems to have high predictive accuracy and allocate the desired items at the top of the recommendation list based on the specific user’s requirements [16, 21].
The popularity of mobile devices among the users has increased the dependency on the mobile servers. People get lots of information including business information, product information, and recommendation information from the mobile devices. One of the important applications of mobile servers is movie recommendation. A movie recommendation system has been an effective tool in recommending movies to the users which, in turn, helps the viewers to cope with multiple movie options available and help them in finding the appropriate movies conveniently. However, recommendation is a complicated task as it involves various tastes of users, different genres of movies, etc. Hence, many techniques have been used to enhance the performance of the recommendation system [32].
We have a massive platform that can be used for giving individual thoughts and reviews. As there is so much data flowing over the internet, it is significant to derive new ways to collect and produce the information. Recommender system is an important component of many businesses, especially in the ecommerce domain. It usually exploits the preference history of the users to provide them with the suitable recommendations, whereas a traditional recommender system can provide only one rating value to an item [5, 24–26].
3.2 Work Related Multi-Criteria Recommender System
Multi-Criteria Recommender System (MCRS) is widely used in almost every sector. It has developed with time. Nowadays, we have many advance recommender systems. Recommender system models can be made by various methods like clustering technique, machine learning technique, deep learning techniques, neural networks, and big data sentiment analysis. There are many open source projects that are developing in the domain of MCRS. So, let us take a look on here.
Wasid and Ali came up with a MCRS based on the clustering approach. The primary objective of their method was to enhance recommendation performance by identifying more similar neighbors within the cluster of a specific user. To implement this method, they had done two major things. First, they extracted the users’ preferences for the given items based on multi-criteria ratings. Second, on the basis of the preferences of the user, the cluster centers were defined [2].
Zheng proposed a utility-based multi-criteria recommender system that depends on the utility function. He built the utility function by applying the multiple-criteria ratings to measure the similarity between the vector of user evaluations and the vector of user expectations. To calculate the utility score, they had incorporated three similarity measures. In addition, three optimization learning-to-rank methods were used to learn the user expectations [3].
Tallapally et al. adopted a deep learning–based ANN architecture technique known as stacked autoencoders to ease the recommendations problems. The functionality of the traditional stacked autoencoders was enhanced to include the multiple-criteria ratings by adding an extra layer that acted like an input layer to the autoencoders. The multiple-criteria ratings input were connected to the intermediate layer. This intermediate layer comprised of the items or the criteria. This intermediate layer was further linked to N consecutive encoding layers [4].
Musto, Gemmis, Semeraro, and Lops used MCRS using aspect-based sentiment analysis. They utilized a structure for sentiment analysis and opinion mining. It automatically extracts sentiment scores and relevant aspects from users’ reviews. They estimated the efficiency of the proposed method with other state-of-the-art baselines and compared the result [5].
García-Cumbreras et al. method utilizes the pessimistic and optimistic behaviors among users for recommender systems. The objective was to categorize the clients into distinct classes of two, namely, pessimist class and optimist class based on their cognition or behavior. The classes are defined on the report of the mean polarity of clients’ rating and reviews. Then, the derived client’s class is added as a latest attribute for the collaborative filtering (CF) algorithm [6].
Zhang et al. proposed an algorithm that considers virtual ratings or overall rating from the users’ reviews by analyzing the sentiments of the user’s opinions by using
