Factorization Machines for Hybrid Recommendation Systems Based on Behavioral, Product, and Customer Data

2015 ◽  
Author(s):  
Stijn Geuens
Keyword(s):  
Recommendation Systems ◽  
Customer Data ◽  
Hybrid Recommendation

HybRecSys: Content-based contextual hybrid venue recommender system

2018 ◽  
Vol 45 (2) ◽  
pp. 212-226 ◽  
Author(s):  
Aysun Bozanta ◽  
Birgul Kutlu
Keyword(s):  
Recommendation System ◽  
Contextual Information ◽  
Recommendation Systems ◽  
Location Based Services ◽  
Related Information ◽  
Weather Underground ◽  
Information User ◽  
Location Based Social Networks ◽  
Hybrid Recommendation ◽  
Content Based Filtering

The popularity of location-based social networks has prompted researchers to study recommendation systems for location-based services. When used separately, each existing venue recommendation system algorithm has its own drawbacks (e.g. cold start, data sparsity, scalability). Another issue is that critical information about context is not commonly used in venue recommendation systems. This article proposes a hybrid recommendation model that combines contextual information, user-based and item-based collaborative filtering and content-based filtering. For this purpose, we collected user visit histories, venue-related information (distance, category, popularity and price) and contextual information (weather, season, date and time of visits) related to individual user visits from Twitter, Foursquare and Weather Underground. Experimental evaluation of the proposed hybrid system (HybRecSys) using a real-world dataset shows better results than baseline approaches.

scholarly journals A Survey on Hybrid Recommendation Systems

2021 ◽  
pp. 219-224
Author(s):  
Prof. Pradnya Mehta ◽  
Onkar Dongare ◽  
Rushikesh Tekale ◽  
Hitesh Umare ◽  
Rutwik Wanve
Keyword(s):  
Machine Learning ◽  
New Products ◽  
Recommendation Systems ◽  
Customer Engagement ◽  
Personalized Recommendation ◽  
Online Retail ◽  
Retail Business ◽  
Shopping Experience ◽  
Past Data ◽  
Hybrid Recommendation

As India is moving fast towards digital economy, E-commerce industry has been on rise. Many platforms such as Amazon and Flipkart provide their customers with a shopping experience better than actual physical stores. Several E-commerce websites use different methods to improve the customer engagement and revenue. One such technique is the use of personalized recommendation systems which uses customer’s data like interests, purchase history, ratings to suggest new products which they may like. Recommendation systems are used by E-commerce websites to suggest new products to their users. The products can be suggested based on the top merchants on the website, based on the interests of the user or based the past purchase pattern of the customer. Recommender systems are machine learning based systems that help users discover new products. Due to the recent pandemic situation of 2020 and 2021, many of the local retail stores have been trying to shift their business to online platforms such as dedicated websites or social media. The proposed methodology based on Machine Learning aims to enable local online retail business owners to enhance their customer engagement and revenue by providing users with personalized recommendations using past data using methods such as Collaborative Filtering and Content-Based Filtering.

scholarly journals Implicative Rating-Based Hybrid Recommendation Systems

2018 ◽  
Vol 8 (3) ◽  
pp. 223-228 ◽  
Author(s):  
Lan Phuong Phan ◽  
Hung Huu Huynh ◽  
Hiep Xuan Huynh
Keyword(s):  
Recommendation Systems ◽  
Hybrid Recommendation

scholarly journals Dealing with Pure New User Cold-Start Problem in Recommendation System Based on Linked Open Data and Social Network Features

2020 ◽  
Vol 2020 ◽  
pp. 1-20
Author(s):  
Usha Yadav ◽  
Neelam Duhan ◽  
Komal Kumar Bhatia
Keyword(s):  
Social Network ◽  
Recommendation System ◽  
Research Work ◽  
Recommendation Systems ◽  
Open Data ◽  
Computation Time ◽  
Cold Start ◽  
Linked Open Data ◽  
Hybrid Recommendation ◽  
Cold Start Problem

Preferring accuracy over computation time or vice versa is very challenging in the context of recommendation systems, which encourages many researchers to opt for hybrid recommendation systems. Currently, researchers are trying hard to produce correct and accurate recommendations by suggesting the use of ontology, but the lack of techniques renders to take its full advantage. One of the major issues in recommender systems bothering many researchers is pure new user cold-start problem which arises due to the absence of information in the system about the new user. Linked Open Data (LOD) initiative sets standards for interoperability among cross domains and has gathered enormous amount of data over the past years, which provides various ways by which recommender system’s performance can be improved by enriching user’s profile with relevant features. This research work focuses on solving pure new user cold-start problem by building user’s profile based on LOD, collaborative features, and social network-based features. Here, a new approach is devised to compute item similarity based on ontology, thus predicting the rating of nonrated item. A modified method to calculate user’s similarity based on collaborative features to deal with other issues such as accuracy and computation time is also proposed. The empirical results and comparative analysis of the proposed hybrid recommendation system dictate its better performance specifically for providing solution to pure new user cold-start problem.

scholarly journals GURILEM : A Novel Design of Customer Rating Model using K-Means and RFM

2019 ◽  
Vol 7 (2) ◽  
Author(s):  
Rolly Maulana Awangga ◽  
Syafrial Fachri Pane ◽  
Diana Asri Wijayanti
Keyword(s):  
Recommendation Systems ◽  
Time Frame ◽  
Rating System ◽  
Personalized Recommendation ◽  
Good Information ◽  
Customer Data ◽  
Customer Preference ◽  
Rating Model ◽  
Novel Design

A rating system or reviews are generally used to assist in making decisions. Rating system widely used as a technique in the recommendation of one of them used by the customer, as in determining the resort to be used. However, the credibility of the rating looks vague because the rating could only represent some points of service. So that customer preference with each other is very different. Personalized recommendation systems offer more personalized advice, precisely knowing the preferences or tastes of the customers. Especially for customers who have a transaction history or reservation as at their resorts provide good information used by managers to design a recommendation model for their customers. In this study aims to create a model of resort recommendations based on a rating of frequency. This frequency is the number of resort use by the customer within the specified time frame. With the frequency can represent the preferences of customers. The RFM method is used to measure the reservation frequency value of the customer. The K-Means method is used to categorize customer data with its frequency and classify the type of resort. Recommendation resort to the customer based on the dominant use in one of the resort types. The recommended type of resort based on the similarity between the types of resorts used with other types of resorts.

scholarly journals Techniques of Recommender System

2019 ◽  
Vol 8 (9S) ◽  
pp. 373-379
Keyword(s):  
Collaborative Filtering ◽  
Recommender System ◽  
Information Overload ◽  
Hybrid Approach ◽  
Recommendation Systems ◽  
Data Filtering ◽  
Filtering Technique ◽  
Comprehensive Introduction ◽  
Hybrid Recommendation ◽  
Content Based Filtering

The term Recommender system is described as any organization that provides personalized suggestions as a result and it effects the user in the individualized way to favorable items from the large number of opinions. The voluminous inflation of the reachable data online and also the number of users have lead to the information overload problem. To overcome this problem the recommender system came into play as it is able to prioritize and personalize the data. Recommendation systems have developed alongside with the net. Recommender system has mainly three data filtering methods such as content based filtering technique, collaborative based filtering technique and the hybrid approach to manage the data overload problem and to recommends the items to the user the items they are interested in from the dynamically generated data. This paper makes a comprehensive introduction to the recommender system with its types, content based filtering , collaborative filtering and the hybrid recommendation.

Sign in / Sign up

Export Citation Format

Share Document