Marziyeh Nourahmadi; Hojjatollah Sadeqi
Volume 3, Issue 1 , May 2022, , Pages 12-31
Abstract
Purpose: With the development of science and technology, large volumes of structured, semi-structured, and unstructured data are generated daily at breakneck speeds from various sources. This data generated by different users share many common patterns that can be filtered and analyzed to make recommendations ...
Read More
Purpose: With the development of science and technology, large volumes of structured, semi-structured, and unstructured data are generated daily at breakneck speeds from various sources. This data generated by different users share many common patterns that can be filtered and analyzed to make recommendations for a product, goods, or service of interest to users. Recommender systems are software tools that provide suggestions to users based on their needs. One of the critical issues in recommender systems is providing personalized advice that fits the users' mood.Methodology: In this research, with a bibliometric approach using the bibliometric library in R software, all the research done on applying recommended systems in personalization is reviewed.Findings: Using the bibliometrics approach while defining recommender systems and their types, we presented an overview of the personalization field and different kinds of personalization. We also discussed the personalization process and described recommender systems as an integral part. Then, the challenges of implementing recommendation systems will be discussed, and finally, the areas in which the problem of personalization of recommendation systems can be raised.Originality/Value: The present study, with a comprehensive review of all research in this field, can help researchers imagine and select appropriate methods for classifying and analyzing data as a toolbox for using recommender systems in personalization.
Marziyeh Nourahmadi; Hojjatollah Sadeqi
Volume 2, Issue 2 , September 2021, , Pages 180-194
Abstract
Purpose: One of the issues that significantly impact how people invest is the behavioural characteristics of investors. Given the importance of this issue, investors should be able to categorize investors into different classes and recommend investments appropriate to the personality type of the same ...
Read More
Purpose: One of the issues that significantly impact how people invest is the behavioural characteristics of investors. Given the importance of this issue, investors should be able to categorize investors into different classes and recommend investments appropriate to the personality type of the same class for each class. One of the solutions that can be used for this purpose is clustering. Clustering is one of the unsupervised learning methods and has a descriptive nature. In this method, the data are allocated based on a similarity criterion so that the data in each cluster are most similar and the least comparable to the data in other clusters.Methodology: This study identifies a group of investors with similar ability and willingness to accept risk using K-means clustering and Affinity propagation clustering. We also show how to allocate assets effectively using investor characteristics and clustering techniques.Findings: Use silhouette coefficient to evaluate two clustering methods to select the best method for data clustering. The k-means coefficient was equal to 0.17, and the Affinity propagation clustering was equal to 0.097. Therefore, we choose the k-means method as the optimal clustering method. Using the K-means clustering method, we cluster investors based on financial, behavioural, and demographic characteristics, and according to the clustering results, we divide individuals into seven categories with low to high-risk acceptance.Originality/Value: All calculations in this study were performed by Python 3.8. Investment managers and stock advisors can use the results of this study.
