Product Recommendation System Research Articles

Deep Learning-Powered Financial Product Recommendation System in Banks

Deep Learning-Powered Financial Product Recommendation System in Banks

Perancangan Website Penjualan Toko Online Pada Toko Usaha Tani Mandiri Sintang Dengan Menggunakan Framework Codeigniter

The Mandiri Farming Business Store has a need to be able to increase sales, manage goods/products so that they can be conditioned, and sales or marketing that is classified as conventional, which causes human error and farmers who have to come all the way to the store to get product information. This research aims to build a codeigniter-based sales website that has an MVC concept and a product recommendation system. This will simplify the shop activity process. The scope of the research uses the CodeIgniter framework which has an MVC concept and a product recommendation system to build sales websites. Using the midtrans API as a payment gateway. The form of research used is a case study. The research method used is DSR (Design Science Research). The design method used is the Agile Extreme Programming (XP) method. The results of this research produced a fertilizer and plant seed sales website that provides product and goods information to buyers and makes it easier for buyers to make purchases online. The conclusion of this research is that it facilitates sales and purchase transaction activities in stores. This research suggests adding other features such as delivery services.

FacetDRS: Multi-faceted Feature Matching for Personalized Product Recommendations in Dynamic E-Commerce

Dynamic Product Recommender systems play a crucial role in e-commerce, guiding users towards products that align with their preferences and enhancing the shopping experience. However, existing systems often struggle to capture the nuances of user preferences, particularly when dealing with multiple features via keyword queries and filters. Additionally, scalability challenges arise as the volume of products grows with features and values. In addition, the static filters of existing recommender systems limit the exploration by strictly adhering to user selections, hindering discovery of potentially better features within the preferred budget or category. This can lead to user dissatisfaction and missed opportunities to discover more desirable options. This research addresses these limitations by introducing FacetDRS, a novel dynamic product recommendation system that leverages flexible feature matching and a scalable architecture. FacetDRS empowers the recommendations with three distinct matching methods to cater to diverse preference nuances. Exact Match ensures precise adherence to user specifications, while High-Impact Partial Match prioritizes core features with flexibility in non-critical aspects. Extended Partial Match suggests relevant options beyond initial preferences, leveraging predefined thresholds. This multi-faceted approach captures the full spectrum of user desires while maintaining accuracy. To evaluate the effectiveness of FacetDRS, a rigorous experimental setup was conducted, comparing its performance across Keyword Match Score, First Selections in Top-K and Average Response Time metrics with established recommender systems such as DeepRec, APGNN, and TADCF. The results demonstrate that FacetDRS achieves superior performance than its counterparts in all comparison aspects. The system's flexible matching methods, combined with its robust architecture, offer a valuable solution for enhancing user satisfaction and driving conversions in the mobile commerce landscape.

Chatbot Based Online Shopping Web Application

This study presents an innovative chatbot system aimed at transforming product recommendation and customization. It integrates feature-based input analysis and user-driven updates to provide tailored product recommendations. Users can input specific product features, leading to personalized suggestions that align precisely with their preferences. Utilizing a dynamic customization framework, the chatbot consistently refines recommendations based on user interests, ensuring a personalized and evolving user experience. The project seeks to reshape the realm of product recommendation systems by providing a seamless and adaptable interface, enhancing the exploration and acquisition of products that precisely match individual needs and preferences.

Amazon product recommendation system based on a modified convolutional neural network

AbstractIn e‐commerce platforms, sentiment analysis on an enormous number of user reviews efficiently enhances user satisfaction. In this article, an automated product recommendation system is developed based on machine and deep‐learning models. In the initial step, the text data are acquired from the Amazon Product Reviews dataset, which includes 60 000 customer reviews with 14 806 neutral reviews, 19 567 negative reviews, and 25 627 positive reviews. Further, the text data denoising is carried out using techniques such as stop word removal, stemming, segregation, lemmatization, and tokenization. Removing stop‐words (duplicate and inconsistent text) and other denoising techniques improves the classification performance and decreases the training time of the model. Next, vectorization is accomplished utilizing the term frequency–inverse document frequency technique, which converts denoised text to numerical vectors for faster code execution. The obtained feature vectors are given to the modified convolutional neural network model for sentiment analysis on e‐commerce platforms. The empirical result shows that the proposed model obtained a mean accuracy of 97.40% on the APR dataset.

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

This paper presents a pioneering methodology for refining product recommender systems, introducing a synergistic integration of unsupervised models—K-means clustering, content-based filtering (CBF), and hierarchical clustering—with the cutting-edge GPT-4 large language model (LLM). Its innovation lies in utilizing GPT-4 for model evaluation, harnessing its advanced natural language understanding capabilities to enhance the precision and relevance of product recommendations. A flask-based API simplifies its implementation for e-commerce owners, allowing for the seamless training and evaluation of the models using CSV-formatted product data. The unique aspect of this approach lies in its ability to empower e-commerce with sophisticated unsupervised recommender system algorithms, while the GPT model significantly contributes to refining the semantic context of product features, resulting in a more personalized and effective product recommendation system. The experimental results underscore the superiority of this integrated framework, marking a significant advancement in the field of recommender systems and providing businesses with an efficient and scalable solution to optimize their product recommendations.

ShopSculpt : Crafting Your Cart with Intelligent Ingenuity

In the present world from small companies to giant company’s product recommendation system plays a very major role, also people are very much interested in online shopping these days, so Recommendations are utilized to make the customer's job easier and faster. The majority of these recommendations are made based on their previous transaction history and association rules generated from it. Apriori Algorithm is the most widely used method for generating association rules based on frequent product sets. But it has a drawback, while generating association rules it uses the whole transactions list and frequent product sets, ignoring the seasonal transactions for generating rules. Hence seasonal transactions are not considered for mining rules, if a person is buying a cake for Christmas, it’s very likely that recommender system recommends birthday balloons, birthday caps as recommendations. But actually, it should recommend Christmas related products for recommendation. To solve this problem, we proposed a model using chi square test with improvised Apriori algorithm. This research paper introduces ShopSculpt, an innovative automated shopping cart system designed to enhance the user shopping experience by leveraging intelligent algorithms. ShopSculpt employs a multifaceted approach, considering user shopping interests, patterns, seasonal trends, and current weather conditions to provide personalized and context-aware product recommendations. The aim is to create a dynamic and responsive shopping environment that adapts to individual preferences and external factors, thereby optimizing the user's shopping journey.

Consumer Product Recommendation System Using Adapted PSO With Federated Learning Method

Consumer Product Recommendation System Using Adapted PSO With Federated Learning Method

Deep learning-based information retrieval with normalized dominant feature subset and weighted vector model

Multimedia data, which includes textual information, is employed in a variety of practical computer vision applications. More than a million new records are added to social media and news sites every day, and the text content they contain has gotten increasingly complex. Finding a meaningful text record in an archive might be challenging for computer vision researchers. Most image searches still employ the tried and true language-based techniques of query text and metadata. Substantial work has been done in the past two decades on content-based text retrieval and analysis that still has limitations. The importance of feature extraction in search engines is often overlooked. Web and product search engines, recommendation systems, and question-answering activities frequently leverage these features. Extracting high-quality machine learning features from large text volumes is a challenge for many open-source software packages. Creating an effective feature set manually is a time-consuming process, but with deep learning, new actual feature demos from training data are analyzed. As a novel feature extraction method, deep learning has made great strides in text mining. Automatically training a deep learning model with the most pertinent text attributes requires massive datasets with millions of variables. In this research, a Normalized Dominant Feature Subset with Weighted Vector Model (NDFS-WVM) is proposed that is used for feature extraction and selection for information retrieval from big data using natural language processing models. The suggested model outperforms the conventional models in terms of text retrieval. The proposed model achieves 98.6% accuracy in information retrieval.

Article 10bis of the Paris Convention as the common denominator for protection against unfair competition in national and regional contexts

Abstract This article explains the historical development of Article 10bis of the Paris Convention and discusses core concepts underlying the international provision, in particular, the overarching requirement of honest practices in industrial or commercial matters, the question of a competitive relationship and the examples of unfair practices given in Article 10bis. It also sheds light on guidance following from the Model Provisions on Protection Against Unfair Competition which the World Intellectual Property Organization presented in 1996. The analysis shows that the honest practices test need not be understood in a traditional, empirical sense. More modern, functional approaches can be adopted to align the application of Article 10bis with a broader spectrum of policy goals: not only fair play between competitors but also consumer protection and the general public interest in a well-functioning marketplace. Similarly, the requirement of a competitive relationship need not focus on direct competition in the same market segment. An indirect competitive relationship can be deemed sufficient. While the prohibited acts listed in Article 10bis(3) reflect central categories of unfair behaviour and harm, current developments and challenges—ranging from computational advertising, influencer marketing and product recommender systems to questions surrounding data exclusivity and sustainability issues—raise the question whether an update and enrichment of the catalogue of prohibited acts could be necessary to provide guidance at the international level.

A novel framework for an intelligent deep learning based product recommendation system using sentiment analysis (SA)

Social media and e-commerce are the two most prominent and quickly expanding industries today. These two areas exhibit the greatest influence on platform users. Numerous new people sign up for these networks on a daily basis. This platform offers extremely quick user networking and communication. These platforms are used to create an online product-based recommender system that will help grow online business by recommending products. Online product recommendations are entirely dependent on the views, feedback, and comments of consumers. Online recommender systems have become a regular part of consumers’ everyday routines, with their widespread use observed in e-commerce, social networking platforms, and news websites. This paper offers a novel framework for product recommendation based on sentiment analysis (SA) and collaborative filtering (CF). The SA was performed using an LSTM-based model. On the basis of CF, two distinct recommendation systems were built. The proposed SA model was integrated with the best recommendation system to enhance the recommendations. The experimental findings showed that the proposed system for product recommendation outperformed the existing methods. The outcomes demonstrated the potential of combining CF and SA to improve consumer satisfaction and product recommendation in e-commerce systems.

Implementation of a Product-Recommender System in an IoT-Based Smart Shopping Using Fuzzy Logic and Apriori Algorithm

The Internet of Things (IoT) has recently become important in accelerating various functions, from manufacturing and business to healthcare and retail. A recommender system can handle the problem of information and data buildup in IoT-based smart commerce systems. These technologies are designed to determine users' preferences and filter out irrelevant information. Identifying items and services that customers might be interested in and then convincing them to buy is one of the essential parts of effective IoT-based smart shopping systems. Due to the relevance of product-recommender systems from both the consumer and shop perspectives, this article presents a new IoT-based smart product-recommender system based on an apriori algorithm and fuzzy logic. The suggested technique employs association rules to display the interdependencies and linkages among many data objects. The most common use of association rule discovery is “shopping cart analysis.” Customers' buying habits and behavior are studied based on the numerous goods they place in their shopping carts. As a result, the association rules are generated using a fuzzy system. The apriori algorithm then selects the product based on the provided fuzzy association rules. The results revealed that the suggested technique had achieved acceptable results in terms of mean absolute error, root-mean-square error, precision, recall, diversity, novelty, and catalog coverage when compared to cutting-edge methods. Finally, the method helps increase recommender systems' diversity in IoT-based smart shopping.

An E-Commerce Based Personalized Health Product Recommendation System Using CNN-Bi-LSTM Model

An E-Commerce Based Personalized Health Product Recommendation System Using CNN-Bi-LSTM Model

Personalized Recommendation Method of E-Commerce Products Based on In-Depth User Interest Portraits

In dynamic e-commerce environments, researchers strive to understand users' interests and behaviors to enhance personalized product recommendations. Traditional collaborative filtering (CF) algorithms have encountered computational challenges such as similarity errors and user rating habits. This research addresses these issues by emphasizing user profiling techniques. This article proposes an innovative user profile updating technique that explores the key components of user profile (basic information, behavior, and domain knowledge). An enhanced kernel fuzzy mean clustering algorithm constructs a dynamic user portrait based on domain knowledge mapping. This dynamic portrait is combined with e-commerce personalized recommendation to improve the accuracy of inferring user interests, thus facilitating accurate recommendation on the platform. The method proposed in this article greatly improves the overall performance and provides strong support for developing smarter and more personalized e-commerce product recommendation systems.

Sentiment analysis-based recommendation system for agricultural products

Sentiment analysis-based recommendation system for agricultural products

An Improved Product Recommender System Using Collaborative Filtering and a Comparative Study of ML Algorithms

Abstract One of the methods most frequently used to recommend films is collaborative filtering. We examine the potential of collaborative filtering in our paper’s discussion of product suggestions. In addition to utilizing collaborative filtering in a new application, the proposed system will present a better technique that focuses especially on resolving the cold start issue. The suggested system will compute similarity using the Pearson Correlation Coefficient (PCC). Collaborative filtering that uses PCC suffers from the cold start problem or a lack of information on new users to generate useful recommendations. The proposed system solves the issue of cold start by gauging each new user by certain arbitrary parameters and recommending based on the choices of other users in that demographic. The proposed system also solves the issue of users’ reluctance to provide ratings by implementing a keyword-based perception system that will aid users in finding the right product for them.

Retracted: A Social-aware and Mobile Computing-based E-Commerce Product Recommendation System.

[This retracts the article DOI: 10.1155/2022/9501246.].

Developing a Convenience Store Product Recommendation System through Store-Based Collaborative Filtering

Providing personalized product recommendations in offline retail stores, especially small-format offline retail businesses such as convenience stores, poses a great challenge. To address this issue, this study aimed to find a solution by shifting the perspective on recommendation methods and altering the target of recommendations. In this study, recommending products was defined as suggesting products that should be introduced and displayed within the store. This recommendation system proposes products that individual stores have not yet introduced but are anticipated to be purchased by customers. Building upon this, we developed a store-based collaborative filtering recommendation system. Furthermore, various rules and logic pertinent to store operations and business considerations for convenience stores were integrated to implement this recommendation system. The accuracy and effectiveness of the system were demonstrated through its application in actual convenience stores. Results from the pilot implementation of the system showed that 88% of the newly recommended products in individual stores were sold within a week, and the sales revenue was 1.75 times higher than the average sales of those products across the entire stores. Survey results on business owners’ satisfaction yielded a score of 4.2 out of 5, indicating a high level of contentment. This research holds significance in extending the scope of personalized recommendation studies from primarily online platforms to offline retail businesses such as convenience stores. The study also suggests avenues for future research to address some of the identified limitations.

A New Sentiment and Fuzzy Aware Product Recommendation System Using Weighted Aquila Optimization and GRNN in e-Commerce

Customer reviews are playing an important role in e-commerce for increasing sales by knowing the customer’s purchase pattern and expectations. The reviews that are collected after completing their purchase reflect the quality and services in e-commerce. The user’s reviews are characterized and categorized through sentiment and semantic analysis. Moreover, the sentiment and semantic classification processes are also performed to predict the user’s purchase patterns and liked products. However, the available classification is not able to predict the user’s purchase patterns. In this paper, we propose a new Product Recommendation System (PRS) to predict the appropriate product for users based on their purchase behavior and pattern. The proposed recommendation system incorporates the standard data preprocessing tasks like tokenization process, Parts of Speech (PoS) tagging process, and parsing, a new sentiment and semantic score calculation procedure, and a new feature optimization technique called the Weighted Aquila Optimization Method (WAOM). Moreover, the sentiment and semantic classification processes are performed by applying a General Regression Neural Network with the incorporation of fuzzy temporal features (FTGRNN) and obtaining better classification results. The newly developed PRS is evaluated by conducting experiments in this work and also proved as superior than other systems available in this direction in terms of prediction accuracy, precision, recall, serendipity and nDCG.

E-Commerce Product Recommendation System Using Case-Based Reasoning (CBR) and K-Means Clustering

This research proposes and implements an e-commerce product recommendation system that combines Case-Based Reasoning (CBR) and K-Means Clustering algorithms. The main aim of this research is to provide more personalized and relevant product recommendations to e-commerce users. The CBR approach leverages users' transaction history to provide customized recommendations, whereas K-Means Clustering groups users with similar preferences increase the relevance of recommendations. This study assesses the effectiveness of the system by conducting a comprehensive evaluation by comparing system recommendations with actual user preferences. The results of this study reveal that the combined approach of CBR and K-Means Clustering can improve the performance of e-commerce product recommendations, ensure the accuracy of recommendations, and produce a more satisfying shopping experience for users. Although there are limitations in terms of the dataset used and the choice of algorithm parameters, this research makes an important contribution in developing a more adaptive and personalized recommendation system for e-commerce platforms.