On the integration of Machine Learning algorithms and operations research techniques in the development of a hybrid Recommender System

2021 ◽  
pp. 1-14
Author(s):  
Panagiotis Giannopoulos ◽  
Georgios Kournetas ◽  
Nikos Karacapilidis
Keyword(s):  
Machine Learning ◽  
Recommender Systems ◽  
Recommender System ◽  
Information Overload ◽  
Learning Algorithms ◽  
Information Filtering ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbors ◽  
Hybrid Recommender System ◽  
Hybrid Recommender

Recommender Systems is a highly applicable subclass of information filtering systems, aiming to provide users with personalized item suggestions. These systems build on collaborative filtering and content-based methods to overcome the information overload issue. Hybrid recommender systems combine the abovementioned methods and are generally proved to be more efficient than the classical approaches. In this paper, we propose a novel approach for the development of a hybrid recommender system that is able to make recommendations under the limitation of processing small amounts of data with strong intercorrelation. The proposed hybrid solution integrates Machine Learning and Multi-Criteria Decision Analysis algorithms. The experimental evaluation of the proposed solution indicates that it performs better than widely used Machine Learning algorithms such as the k-Nearest Neighbors and Decision Trees.

scholarly journals Unifying recommendation and active learning for information filtering and recommender systems

2020 ◽  
Author(s):  
Scott Cheng-Hsin Yang ◽  
Chirag Rank ◽  
Jake Alden Whritner ◽  
Olfa Nasraoui ◽  
Patrick Shafto
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Recommender Systems ◽  
Learning Algorithms ◽  
Information Filtering ◽  
Relevant Information ◽  
Machine Learning Algorithms ◽  
Negative Consequences ◽  
Parameterized Model ◽  
Recommendation Accuracy

The enormous scale of the available information and products on the Internet has necessitated the development of algorithms that intermediate between options and human users. These AI/machine learning algorithms attempt to provide the user with relevant information. In doing so, the algorithms may incur potential negative consequences stemming from the need to select items about which it is uncertain to increase predictive accuracy versus the need to select items about which it is certain to increase recommendation accuracy. This tension between predicting relevant recommendations to the users and learning about the user's interests can be considered an instantiation of the well-known exploration-exploitation tradeoff in the context of information filtering and recommender systems. Building from existing machine learning algorithms, we introduce a parameterized model that unifies and interpolates between recommending relevant information and active learning. We present three experiments investigating the unified model. Specifically, we illustrate the tradeoffs of optimizing prediction and recommendation within a tightly controlled concept-learning paradigm, show the conditions under which a broad parameter range can optimize for both, and identify the effects of human variability on algorithm performance. Thus, combining methods and models from cognitive science and computer science, we quantify implications of tradeoffs between recommendation accuracy and learning about preferences of human users, demonstrating the value of experimental approaches to understanding real world human-machine feedback loops.

Hybrid Recommender System Using Emotional Fingerprints Model

2019 ◽  
Vol 9 (3) ◽  
pp. 48-70
Author(s):  
Anthony Nosshi ◽  
Aziza Saad Asem ◽  
Mohammed Badr Senousy
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Information Overload ◽  
Experimental Simulation ◽  
Key Factors ◽  
Easy Task ◽  
Needed Information ◽  
Hybrid Recommender System ◽  
Hybrid Recommender

With today's information overload, recommender systems are important to help users in finding needed information. In the movies domain, finding a good movie to watch is not an easy task. Emotions play an important role in deciding which movie to watch. People usually express their emotions in reviews or comments about the movies. In this article, an emotional fingerprint-based model (EFBM) for movies recommendation is proposed. The model is based on grouping movies by emotional patterns of some key factors changing in time and forming fingerprints or emotional tracks, which are the heart of the proposed recommender. Then, it is incorporated into collaborative filtering to detect the interest connected with topics. Experimental simulation is conducted to understand the behavior of the proposed approach. Results are represented to evaluate the proposed recommender.

Toward a Hybrid Recommender System for E-learning Personnalization Based on Data Mining Techniques

2018 ◽  
Vol 2 (4) ◽  
pp. 271 ◽  
Author(s):  
Outmane Bourkoukou ◽  
Essaid El Bachari
Keyword(s):  
Learning Style ◽  
Recommender System ◽  
Adaptive Learning ◽  
Learning Objects ◽  
Research Field ◽  
Learning System ◽  
K Nearest Neighbors ◽  
E Learning ◽  
Hybrid Recommender System ◽  
Hybrid Recommender

Personalized courseware authoring based on recommender system, which is the process of automatic learning objects selecting and sequencing, is recognized as one of the most interesting research field in intelligent web-based education. Since the learner’s profile of each learner is different from one to another, we must fit learning to the different needs of learners. In fact from the knowledge of the learner’s profile, it is easier to recommend a suitable set of learning objects to enhance the learning process. In this paper we describe a new adaptive learning system-LearnFitII, which can automatically adapt to the dynamic preferences of learners. This system recognizes different patterns of learning style and learners’ habits through testing the psychological model of learners and mining their server logs. Firstly, the device proposed a personalized learning scenario to deal with the cold start problem by using the Felder and Silverman’s model. Next, it analyzes the habits and the preferences of the learners through mining the information about learners’ actions and interactions. Finally, the learning scenario is revisited and updated using hybrid recommender system based on K-Nearest Neighbors and association rule mining algorithms. The results of the system tested in real environments show that considering the learner’s preferences increases learning quality and satisfies the learner.

scholarly journals Movie Recommender System Using Machine Learning Algorithms

2021 ◽  
Vol 1916 (1) ◽  
pp. 012052
Author(s):  
Piyush Kumar ◽  
Shaik Golam Kibriya ◽  
Yuva Ajay ◽  
Ilampiray
Keyword(s):  
Machine Learning ◽  
Recommender System ◽  
Learning Algorithms ◽  
Machine Learning Algorithms

scholarly journals Predicting hospitalization following psychiatric crisis care using machine learning

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Matthijs Blankers ◽  
Louk F. M. van der Post ◽  
Jack J. M. Dekker
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Nearest Neighbors ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Ensemble Model ◽  
K Nearest Neighbors ◽  
Crisis Care

Abstract Background Accurate prediction models for whether patients on the verge of a psychiatric criseis need hospitalization are lacking and machine learning methods may help improve the accuracy of psychiatric hospitalization prediction models. In this paper we evaluate the accuracy of ten machine learning algorithms, including the generalized linear model (GLM/logistic regression) to predict psychiatric hospitalization in the first 12 months after a psychiatric crisis care contact. We also evaluate an ensemble model to optimize the accuracy and we explore individual predictors of hospitalization. Methods Data from 2084 patients included in the longitudinal Amsterdam Study of Acute Psychiatry with at least one reported psychiatric crisis care contact were included. Target variable for the prediction models was whether the patient was hospitalized in the 12 months following inclusion. The predictive power of 39 variables related to patients’ socio-demographics, clinical characteristics and previous mental health care contacts was evaluated. The accuracy and area under the receiver operating characteristic curve (AUC) of the machine learning algorithms were compared and we also estimated the relative importance of each predictor variable. The best and least performing algorithms were compared with GLM/logistic regression using net reclassification improvement analysis and the five best performing algorithms were combined in an ensemble model using stacking. Results All models performed above chance level. We found Gradient Boosting to be the best performing algorithm (AUC = 0.774) and K-Nearest Neighbors to be the least performing (AUC = 0.702). The performance of GLM/logistic regression (AUC = 0.76) was slightly above average among the tested algorithms. In a Net Reclassification Improvement analysis Gradient Boosting outperformed GLM/logistic regression by 2.9% and K-Nearest Neighbors by 11.3%. GLM/logistic regression outperformed K-Nearest Neighbors by 8.7%. Nine of the top-10 most important predictor variables were related to previous mental health care use. Conclusions Gradient Boosting led to the highest predictive accuracy and AUC while GLM/logistic regression performed average among the tested algorithms. Although statistically significant, the magnitude of the differences between the machine learning algorithms was in most cases modest. The results show that a predictive accuracy similar to the best performing model can be achieved when combining multiple algorithms in an ensemble model.

scholarly journals Predicting Hospitalization following Psychiatric Crisis Care using Machine Learning

2019 ◽  
Author(s):  
Matthijs Blankers ◽  
Louk F. M. van der Post ◽  
Jack J. M. Dekker
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Learning Algorithms ◽  
Nearest Neighbors ◽  
Machine Learning Algorithms ◽  
Predictor Variables ◽  
Gradient Boosting ◽  
K Nearest Neighbors ◽  
Psychiatric Crisis ◽  
Crisis Care

Abstract Background: It is difficult to accurately predict whether a patient on the verge of a potential psychiatric crisis will need to be hospitalized. Machine learning may be helpful to improve the accuracy of psychiatric hospitalization prediction models. In this paper we evaluate and compare the accuracy of ten machine learning algorithms including the commonly used generalized linear model (GLM/logistic regression) to predict psychiatric hospitalization in the first 12 months after a psychiatric crisis care contact, and explore the most important predictor variables of hospitalization. Methods: Data from 2,084 patients with at least one reported psychiatric crisis care contact included in the longitudinal Amsterdam Study of Acute Psychiatry were used. The accuracy and area under the receiver operating characteristic curve (AUC) of the machine learning algorithms were compared. We also estimated the relative importance of each predictor variable. The best and least performing algorithms were compared with GLM/logistic regression using net reclassification improvement analysis. Target variable for the prediction models was whether or not the patient was hospitalized in the 12 months following inclusion in the study. The 39 predictor variables were related to patients’ socio-demographics, clinical characteristics and previous mental health care contacts. Results: We found Gradient Boosting to perform the best (AUC=0.774) and K-Nearest Neighbors performing the least (AUC=0.702). The performance of GLM/logistic regression (AUC=0.76) was above average among the tested algorithms. Gradient Boosting outperformed GLM/logistic regression and K-Nearest Neighbors, and GLM outperformed K-Nearest Neighbors in a Net Reclassification Improvement analysis, although the differences between Gradient Boosting and GLM/logistic regression were small. Nine of the top-10 most important predictor variables were related to previous mental health care use. Conclusions: Gradient Boosting led to the highest predictive accuracy and AUC while GLM/logistic regression performed average among the tested algorithms. Although statistically significant, the magnitude of the differences between the machine learning algorithms was modest. Future studies may consider to combine multiple algorithms in an ensemble model for optimal performance and to mitigate the risk of choosing suboptimal performing algorithms.

scholarly journals Movie Recommenadation System

2021 ◽  
Vol 9 (4) ◽  
pp. 13-16
Author(s):  
Gandhali Malve ◽  
Lajree Lohar ◽  
Tanay Malviya ◽  
Shirish Sabnis
Keyword(s):  
Machine Learning ◽  
Recommender System ◽  
Recommendation System ◽  
Learning Algorithms ◽  
Recommendation Systems ◽  
Machine Learning Algorithms ◽  
The Internet ◽  
Amount Of Information ◽  
System Recommendation ◽  
User Ratings

Today the amount of information in the internet growth very rapidly and people need some instruments to find and access appropriate information. One of such tools is called recommendation system. Recommendation systems help to navigate quickly and receive necessary information. Many of us find it difficult to decide which movie to watch and so we decided to make a recommender system for us to better judge which movie we are more likely to love. In this project we are going to use Machine Learning Algorithms to recommend movies to users based on genres and user ratings. Recommendation system attempt to predict the preference or rating that a user would give to an item.

Intelligent Techniques in Recommender Systems and Contextual Advertising

2013 ◽  
pp. 105-128 ◽  
Author(s):  
Giuliano Armano ◽  
Alessandro Giuliani ◽  
Eloisa Vargiu
Keyword(s):  
Recommender System ◽  
Information Filtering ◽  
Relevant Information ◽  
Web Page ◽  
Contextual Advertising ◽  
Generic Hybrid ◽  
Unified View ◽  
Hybrid Recommender System ◽  
Hybrid Recommender ◽  
The Web

Information Filtering deals with the problem of selecting relevant information for a given user, according to her/his preferences and interests. In this chapter, the authors consider two ways of performing information filtering: recommendation and contextual advertising. In particular, they study and analyze them according to a unified view. In fact, the task of suggesting an advertisement to a Web page can be viewed as the task of recommending an item (the advertisement) to a user (the Web page), and vice versa. Starting from this insight, the authors propose a content-based recommender system based on a generic solution for contextual advertising and a hybrid contextual advertising system based on a generic hybrid recommender system. Relevant case studies have been considered (i.e., a photo recommender and a Web advertiser) with the goal of highlighting how the proposed approach works in practice. In both cases, results confirm the effectiveness of the proposed solutions.

Sign in / Sign up

Export Citation Format

Share Document