TL;DR: In this article , the authors compared two distinct recommendation frameworks: a single algorithm and an ensemble algorithm model, and found that the ensemble algorithm-based recommendation engine has proven to provide better recommendations in comparison to individual algorithms.
Abstract: In the realm of computer science, RSS is a set of tools and methods for making useful product recommendations to end users. To maintain footholds in competitive industry, telecoms provide a wide range of offerings. It is challenging for a client to choose the best-fit product from the huge bouquet of products available. It is possible to increase suggestion quality by using the large amounts of textual contextual data detailing item qualities which are accessible with rating data in various recommender’s domains. Users have a hard time making purchases in the telecom industry. Here, fresh strategy for improving recommendation systems in the telecommunications industry is proposed. Users may choose the recommended services which is loaded onto their devices. Using a recommendation engine is a simple way for telecoms to increase trust and customer satisfaction index. The suggested recommendation engine allows users to pick and choose services they need. The present study compared two distinct recommendation frameworks: a single algorithm and an ensemble algorithm model. Experiments were conducted to compare the efficacy of separate algorithms and ensemble algorithm. Interestingly, the ensemble algorithm-based recommendation engine has proven to provide better recommendations in comparison to individual algorithms.
25 Nov 2022
TL;DR: In this paper , the authors proposed a system that sorts through information and makes suggestions based on how people have behaved in the past to solve the problem of too much data and give users relevant recommendations based on their interests and the data that is being created in real time.
Abstract: In recent times, the amount of data sent and received through wireless networks has grown quickly. Smartphones and the growth of Internet access around the world are two big reasons for this volume. Due to the current state of global health, which is mostly caused by Covid-19, telecommunications companies have a great chance to find new ways to make money by using Big Data Analytics (BDA) solutions. This is because data traffic has gone up. After all, more customers are using telecommunications services. As most of the world's data is now made by smartphones and sent through the telecom network, telecom operators are facing an information explosion that makes it harder to make decisions based on the data they need to predict how people will act. This problem was solved by making a system that sorts through information and makes suggestions based on how people have behaved in the past. Content-based filtering, collaborative filtering, and a hybrid approach are the three main ways that recommender systems filter data to solve the problem of too much data and give users relevant recommendations based on their interests and the data that is being created in real-time. Distance algorithms like Cosine, Euclidean, Manhattan, and Minkowski are at the heart of the suggested recommender system, which aims to research and design an effective recommendation strategy. The suggested model suggests different telecom packages to meet the needs of users to increase revenue per subscriber and get consumers, telecom providers, and corporations to sign long-term contracts.